{"object":"list","data":[{"id":"gpt-6.2-astra","object":"model","created":1794938423,"owned_by":"openai","mode":"chat","context_length":1050000,"capabilities":{"input_modalities":["file","image","text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":8e-6,"output_cost_per_token":0.00004,"cache_read_input_token_cost":4e-7,"input_cost_per_token_batches":4e-6,"input_cost_per_token_priority":0.000016,"output_cost_per_token_batches":0.00002,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"output_cost_per_token_priority":0.00008,"cache_creation_input_token_cost":0.00001,"cache_read_input_token_cost_batches":2e-7,"cache_read_input_token_cost_priority":8e-7,"input_cost_per_token_above_272k_tokens":0.000016,"output_cost_per_token_above_272k_tokens":0.00006,"cache_creation_input_token_cost_priority":0.00002,"cache_creation_input_token_cost_above_12hr":0.00002,"cache_read_input_token_cost_above_272k_tokens":8e-7,"input_cost_per_token_above_272k_tokens_priority":0.000032,"output_cost_per_token_above_272k_tokens_priority":0.00012,"cache_creation_input_token_cost_above_272k_tokens":0.00002,"cache_creation_input_token_cost_above_12hr_priority":0.00004,"cache_read_input_token_cost_above_272k_tokens_priority":1.6e-6,"cache_creation_input_token_cost_above_272k_tokens_priority":0.00004,"cache_creation_input_token_cost_above_12hr_above_272k_tokens":0.00004,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_priority":0.00008},"pricing_endpoint":"openai/gpt-6.2-astra","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"openai/gpt-6.2-astra","object":"model","created":1794938423,"owned_by":"openai","model_name":"gpt-6.2-astra","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-6.2 Astra is the flagship model in the GPT-6.2 series from OpenAI, built for the hardest projects.","source":null,"capabilities":{"input_modalities":["file","image","text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":8e-6,"output_cost_per_token":0.00004,"cache_read_input_token_cost":4e-7,"input_cost_per_token_batches":4e-6,"input_cost_per_token_priority":0.000016,"output_cost_per_token_batches":0.00002,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"output_cost_per_token_priority":0.00008,"cache_creation_input_token_cost":0.00001,"cache_read_input_token_cost_batches":2e-7,"cache_read_input_token_cost_priority":8e-7,"input_cost_per_token_above_272k_tokens":0.000016,"output_cost_per_token_above_272k_tokens":0.00006,"cache_creation_input_token_cost_priority":0.00002,"cache_creation_input_token_cost_above_12hr":0.00002,"cache_read_input_token_cost_above_272k_tokens":8e-7,"input_cost_per_token_above_272k_tokens_priority":0.000032,"output_cost_per_token_above_272k_tokens_priority":0.00012,"cache_creation_input_token_cost_above_272k_tokens":0.00002,"cache_creation_input_token_cost_above_12hr_priority":0.00004,"cache_read_input_token_cost_above_272k_tokens_priority":1.6e-6,"cache_creation_input_token_cost_above_272k_tokens_priority":0.00004,"cache_creation_input_token_cost_above_12hr_above_272k_tokens":0.00004,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_priority":0.00008},"list_pricing":{"input_cost_per_token":8e-6,"output_cost_per_token":0.00004,"cache_read_input_token_cost":4e-7,"input_cost_per_token_batches":4e-6,"input_cost_per_token_priority":0.000016,"output_cost_per_token_batches":0.00002,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"output_cost_per_token_priority":0.00008,"cache_creation_input_token_cost":0.00001,"cache_read_input_token_cost_batches":2e-7,"cache_read_input_token_cost_priority":8e-7,"input_cost_per_token_above_272k_tokens":0.000016,"output_cost_per_token_above_272k_tokens":0.00006,"cache_creation_input_token_cost_priority":0.00002,"cache_creation_input_token_cost_above_12hr":0.00002,"cache_read_input_token_cost_above_272k_tokens":8e-7,"input_cost_per_token_above_272k_tokens_priority":0.000032,"output_cost_per_token_above_272k_tokens_priority":0.00012,"cache_creation_input_token_cost_above_272k_tokens":0.00002,"cache_creation_input_token_cost_above_12hr_priority":0.00004,"cache_read_input_token_cost_above_272k_tokens_priority":1.6e-6,"cache_creation_input_token_cost_above_272k_tokens_priority":0.00004,"cache_creation_input_token_cost_above_12hr_above_272k_tokens":0.00004,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_priority":0.00008},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":1},{"id":"gpt-6.2-sol","object":"model","created":1794938371,"owned_by":"openai","mode":"chat","context_length":1050000,"capabilities":{"input_modalities":["file","image","text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"cache_read_input_token_cost":1e-7,"input_cost_per_token_batches":1e-6,"input_cost_per_token_priority":4e-6,"output_cost_per_token_batches":5e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"output_cost_per_token_priority":0.00002,"cache_creation_input_token_cost":2.5e-6,"cache_read_input_token_cost_batches":5e-8,"cache_read_input_token_cost_priority":2e-7,"input_cost_per_token_above_272k_tokens":4e-6,"output_cost_per_token_above_272k_tokens":0.000015,"cache_creation_input_token_cost_priority":5e-6,"cache_creation_input_token_cost_above_12hr":5e-6,"cache_read_input_token_cost_above_272k_tokens":2e-7,"input_cost_per_token_above_272k_tokens_priority":8e-6,"output_cost_per_token_above_272k_tokens_priority":0.00003,"cache_creation_input_token_cost_above_272k_tokens":5e-6,"cache_creation_input_token_cost_above_12hr_priority":0.00001,"cache_read_input_token_cost_above_272k_tokens_priority":4e-7,"cache_creation_input_token_cost_above_272k_tokens_priority":0.00001,"cache_creation_input_token_cost_above_12hr_above_272k_tokens":0.00001,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_priority":0.00002},"pricing_endpoint":"openai/gpt-6.2-sol","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"openai/gpt-6.2-sol","object":"model","created":1794938371,"owned_by":"openai","model_name":"gpt-6.2-sol","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-6.2 Sol is an upgrade to GPT-6.1 Sol from OpenAI, positioned below the flagship GPT-6.2 Astra in the GPT-6.2 series.","source":null,"capabilities":{"input_modalities":["file","image","text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"cache_read_input_token_cost":1e-7,"input_cost_per_token_batches":1e-6,"input_cost_per_token_priority":4e-6,"output_cost_per_token_batches":5e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"output_cost_per_token_priority":0.00002,"cache_creation_input_token_cost":2.5e-6,"cache_read_input_token_cost_batches":5e-8,"cache_read_input_token_cost_priority":2e-7,"input_cost_per_token_above_272k_tokens":4e-6,"output_cost_per_token_above_272k_tokens":0.000015,"cache_creation_input_token_cost_priority":5e-6,"cache_creation_input_token_cost_above_12hr":5e-6,"cache_read_input_token_cost_above_272k_tokens":2e-7,"input_cost_per_token_above_272k_tokens_priority":8e-6,"output_cost_per_token_above_272k_tokens_priority":0.00003,"cache_creation_input_token_cost_above_272k_tokens":5e-6,"cache_creation_input_token_cost_above_12hr_priority":0.00001,"cache_read_input_token_cost_above_272k_tokens_priority":4e-7,"cache_creation_input_token_cost_above_272k_tokens_priority":0.00001,"cache_creation_input_token_cost_above_12hr_above_272k_tokens":0.00001,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_priority":0.00002},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"cache_read_input_token_cost":1e-7,"input_cost_per_token_batches":1e-6,"input_cost_per_token_priority":4e-6,"output_cost_per_token_batches":5e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"output_cost_per_token_priority":0.00002,"cache_creation_input_token_cost":2.5e-6,"cache_read_input_token_cost_batches":5e-8,"cache_read_input_token_cost_priority":2e-7,"input_cost_per_token_above_272k_tokens":4e-6,"output_cost_per_token_above_272k_tokens":0.000015,"cache_creation_input_token_cost_priority":5e-6,"cache_creation_input_token_cost_above_12hr":5e-6,"cache_read_input_token_cost_above_272k_tokens":2e-7,"input_cost_per_token_above_272k_tokens_priority":8e-6,"output_cost_per_token_above_272k_tokens_priority":0.00003,"cache_creation_input_token_cost_above_272k_tokens":5e-6,"cache_creation_input_token_cost_above_12hr_priority":0.00001,"cache_read_input_token_cost_above_272k_tokens_priority":4e-7,"cache_creation_input_token_cost_above_272k_tokens_priority":0.00001,"cache_creation_input_token_cost_above_12hr_above_272k_tokens":0.00001,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_priority":0.00002},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":1},{"id":"qwen4-max","object":"model","created":1794841974,"owned_by":"qwen","mode":"chat","context_length":1000000,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":9.75e-7,"output_cost_per_token":2.9250000000000004e-6,"cache_read_input_token_cost":4.8749999999999996e-8,"cache_creation_input_token_cost":1.21875e-6},"pricing_endpoint":"qwen/qwen4-max","regions":[{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"deepinfra/Qwen/Qwen4-Max","object":"model","created":1794841974,"owned_by":"deepinfra","model_name":"Qwen/Qwen4-Max","context_length":1000000,"max_input_tokens":null,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"Qwen4 Max is the flagship model in Alibaba's Qwen4 series.","source":null,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.4129999999999999e-6,"output_cost_per_token":4.24e-6,"cache_read_input_token_cost":7.100000009999998e-8},"list_pricing":{"input_cost_per_token":1.4129999999999999e-6,"output_cost_per_token":4.24e-6,"cache_read_input_token_cost":7.100000009999998e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"qwen/qwen4-max","object":"model","created":1794795526,"owned_by":"qwen","model_name":"qwen4-max","context_length":1000000,"max_input_tokens":991808,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"Qwen4-Max is the next-generation flagship multimodal model in the Qwen family, combining text generation, image and video understanding, and deep reasoning. It is designed for coding, office productivity, frontend design, and complex agentic tasks. With support for web search, tool calling, and structured outputs, along with compatibility with the OpenAI and Anthropic APIs, it enables developers to build intelligent applications capable of multimodal understanding and task execution.","source":null,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":9.75e-7,"output_cost_per_token":2.9250000000000004e-6,"cache_read_input_token_cost":4.8749999999999996e-8,"cache_creation_input_token_cost":1.21875e-6},"list_pricing":{"input_cost_per_token":1.5e-6,"output_cost_per_token":4.5e-6,"cache_read_input_token_cost":7.5e-8,"cache_creation_input_token_cost":1.875e-6},"discount":0.35,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":2},{"id":"gemini-4-hydrogen","object":"model","created":1794506460,"owned_by":"google","mode":"chat","context_length":1048576,"capabilities":{"input_modalities":["audio","file","image","text","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.5e-6,"output_cost_per_token":7.5e-6,"input_cost_per_token_flex":7.5e-7,"input_cost_per_audio_token":1.5e-6,"input_cost_per_image_token":1.5e-6,"output_cost_per_token_flex":3.75e-6,"cache_read_input_token_cost":7.5e-8,"input_cost_per_token_priority":2.7e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.0000135,"cache_creation_input_token_cost":8.33333333333333e-8,"output_cost_per_reasoning_token":7.5e-6,"cache_read_input_token_cost_flex":3.75e-8,"cache_read_input_audio_token_cost":7.5e-8,"cache_read_input_token_cost_priority":1.35e-7,"google_maps_grounding_cost_per_query":0.014},"pricing_endpoint":"google/gemini-4-hydrogen","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"google/gemini-4-hydrogen","object":"model","created":1794506460,"owned_by":"google","model_name":"gemini-4-hydrogen","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"Gemini 4 Hydrogen is the high-efficiency workhorse model of the Gemini 4 family from Google, built for high-throughput agentic workflows, coding and multi-model routing at lower cost and latency than...","source":null,"capabilities":{"input_modalities":["audio","file","image","text","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.5e-6,"output_cost_per_token":7.5e-6,"input_cost_per_token_flex":7.5e-7,"input_cost_per_audio_token":1.5e-6,"input_cost_per_image_token":1.5e-6,"output_cost_per_token_flex":3.75e-6,"cache_read_input_token_cost":7.5e-8,"input_cost_per_token_priority":2.7e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.0000135,"cache_creation_input_token_cost":8.33333333333333e-8,"output_cost_per_reasoning_token":7.5e-6,"cache_read_input_token_cost_flex":3.75e-8,"cache_read_input_audio_token_cost":7.5e-8,"cache_read_input_token_cost_priority":1.35e-7,"google_maps_grounding_cost_per_query":0.014},"list_pricing":{"input_cost_per_token":1.5e-6,"output_cost_per_token":7.5e-6,"input_cost_per_token_flex":7.5e-7,"input_cost_per_audio_token":1.5e-6,"input_cost_per_image_token":1.5e-6,"output_cost_per_token_flex":3.75e-6,"cache_read_input_token_cost":7.5e-8,"input_cost_per_token_priority":2.7e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.0000135,"cache_creation_input_token_cost":8.33333333333333e-8,"output_cost_per_reasoning_token":7.5e-6,"cache_read_input_token_cost_flex":3.75e-8,"cache_read_input_audio_token_cost":7.5e-8,"cache_read_input_token_cost_priority":1.35e-7,"google_maps_grounding_cost_per_query":0.014},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"vertex/gemini-4-hydrogen@eu","object":"model","created":1794506460,"owned_by":"vertex","model_name":"gemini-4-hydrogen","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"Gemini 4 Hydrogen is the high-efficiency workhorse model of the Gemini 4 family from Google, built for high-throughput agentic workflows, coding and multi-model routing at lower cost and latency than...","source":null,"capabilities":{"input_modalities":["audio","file","image","text","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.65e-6,"output_cost_per_token":8.25e-6,"input_cost_per_audio_token":1.65e-6,"input_cost_per_image_token":1.65e-6,"cache_read_input_token_cost":8.25e-8,"input_cost_per_token_priority":2.9700000000000004e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.00001485,"cache_creation_input_token_cost":9.166666666666664e-8,"output_cost_per_reasoning_token":8.25e-6,"cache_read_input_audio_token_cost":8.25e-8,"input_cost_per_audio_token_priority":2.9700000000000004e-6,"cache_read_input_token_cost_priority":1.485e-7,"google_maps_grounding_cost_per_query":0.015400000000000002},"list_pricing":{"input_cost_per_token":1.65e-6,"output_cost_per_token":8.25e-6,"input_cost_per_audio_token":1.65e-6,"input_cost_per_image_token":1.65e-6,"cache_read_input_token_cost":8.25e-8,"input_cost_per_token_priority":2.9700000000000004e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.00001485,"cache_creation_input_token_cost":9.166666666666664e-8,"output_cost_per_reasoning_token":8.25e-6,"cache_read_input_audio_token_cost":8.25e-8,"input_cost_per_audio_token_priority":2.9700000000000004e-6,"cache_read_input_token_cost_priority":1.485e-7,"google_maps_grounding_cost_per_query":0.015400000000000002},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"vertex/gemini-4-hydrogen","object":"model","created":1794506460,"owned_by":"vertex","model_name":"gemini-4-hydrogen","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"Gemini 4 Hydrogen is the high-efficiency workhorse model of the Gemini 4 family from Google, built for high-throughput agentic workflows, coding and multi-model routing at lower cost and latency than...","source":null,"capabilities":{"input_modalities":["audio","file","image","text","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.5e-6,"output_cost_per_token":7.5e-6,"input_cost_per_audio_token":1.5e-6,"input_cost_per_image_token":1.5e-6,"cache_read_input_token_cost":7.5e-8,"input_cost_per_token_priority":2.7e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.0000135,"cache_creation_input_token_cost":8.33333333333333e-8,"output_cost_per_reasoning_token":7.5e-6,"cache_read_input_audio_token_cost":7.5e-8,"input_cost_per_audio_token_priority":2.7e-6,"cache_read_input_token_cost_priority":1.35e-7,"google_maps_grounding_cost_per_query":0.014},"list_pricing":{"input_cost_per_token":1.5e-6,"output_cost_per_token":7.5e-6,"input_cost_per_audio_token":1.5e-6,"input_cost_per_image_token":1.5e-6,"cache_read_input_token_cost":7.5e-8,"input_cost_per_token_priority":2.7e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.0000135,"cache_creation_input_token_cost":8.33333333333333e-8,"output_cost_per_reasoning_token":7.5e-6,"cache_read_input_audio_token_cost":7.5e-8,"input_cost_per_audio_token_priority":2.7e-6,"cache_read_input_token_cost_priority":1.35e-7,"google_maps_grounding_cost_per_query":0.014},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"vertex/gemini-4-hydrogen@us","object":"model","created":1794506460,"owned_by":"vertex","model_name":"gemini-4-hydrogen","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"Gemini 4 Hydrogen is the high-efficiency workhorse model of the Gemini 4 family from Google, built for high-throughput agentic workflows, coding and multi-model routing at lower cost and latency than...","source":null,"capabilities":{"input_modalities":["audio","file","image","text","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.65e-6,"output_cost_per_token":8.25e-6,"input_cost_per_audio_token":1.65e-6,"input_cost_per_image_token":1.65e-6,"cache_read_input_token_cost":8.25e-8,"input_cost_per_token_priority":2.9700000000000004e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.00001485,"cache_creation_input_token_cost":9.166666666666664e-8,"output_cost_per_reasoning_token":8.25e-6,"cache_read_input_audio_token_cost":8.25e-8,"input_cost_per_audio_token_priority":2.9700000000000004e-6,"cache_read_input_token_cost_priority":1.485e-7,"google_maps_grounding_cost_per_query":0.015400000000000002},"list_pricing":{"input_cost_per_token":1.65e-6,"output_cost_per_token":8.25e-6,"input_cost_per_audio_token":1.65e-6,"input_cost_per_image_token":1.65e-6,"cache_read_input_token_cost":8.25e-8,"input_cost_per_token_priority":2.9700000000000004e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.00001485,"cache_creation_input_token_cost":9.166666666666664e-8,"output_cost_per_reasoning_token":8.25e-6,"cache_read_input_audio_token_cost":8.25e-8,"input_cost_per_audio_token_priority":2.9700000000000004e-6,"cache_read_input_token_cost_priority":1.485e-7,"google_maps_grounding_cost_per_query":0.015400000000000002},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":4},{"id":"~gemini-flash-latest","object":"model","created":1794506460,"owned_by":"google","mode":"chat","context_length":1048576,"capabilities":{"input_modalities":["audio","file","image","text","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.5e-6,"output_cost_per_token":7.5e-6,"input_cost_per_token_flex":7.5e-7,"input_cost_per_audio_token":1.5e-6,"input_cost_per_image_token":1.5e-6,"output_cost_per_token_flex":3.75e-6,"cache_read_input_token_cost":7.5e-8,"input_cost_per_token_priority":2.7e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.0000135,"cache_creation_input_token_cost":8.33333333333333e-8,"output_cost_per_reasoning_token":7.5e-6,"cache_read_input_token_cost_flex":3.75e-8,"cache_read_input_audio_token_cost":7.5e-8,"cache_read_input_token_cost_priority":1.35e-7,"google_maps_grounding_cost_per_query":0.014},"pricing_endpoint":"google/gemini-4-hydrogen","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":"gemini-4-hydrogen","endpoints":[{"id":"google/gemini-4-hydrogen","object":"model","created":1794506460,"owned_by":"google","model_name":"gemini-4-hydrogen","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"Gemini 4 Hydrogen is the high-efficiency workhorse model of the Gemini 4 family from Google, built for high-throughput agentic workflows, coding and multi-model routing at lower cost and latency than...","source":null,"capabilities":{"input_modalities":["audio","file","image","text","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.5e-6,"output_cost_per_token":7.5e-6,"input_cost_per_token_flex":7.5e-7,"input_cost_per_audio_token":1.5e-6,"input_cost_per_image_token":1.5e-6,"output_cost_per_token_flex":3.75e-6,"cache_read_input_token_cost":7.5e-8,"input_cost_per_token_priority":2.7e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.0000135,"cache_creation_input_token_cost":8.33333333333333e-8,"output_cost_per_reasoning_token":7.5e-6,"cache_read_input_token_cost_flex":3.75e-8,"cache_read_input_audio_token_cost":7.5e-8,"cache_read_input_token_cost_priority":1.35e-7,"google_maps_grounding_cost_per_query":0.014},"list_pricing":{"input_cost_per_token":1.5e-6,"output_cost_per_token":7.5e-6,"input_cost_per_token_flex":7.5e-7,"input_cost_per_audio_token":1.5e-6,"input_cost_per_image_token":1.5e-6,"output_cost_per_token_flex":3.75e-6,"cache_read_input_token_cost":7.5e-8,"input_cost_per_token_priority":2.7e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.0000135,"cache_creation_input_token_cost":8.33333333333333e-8,"output_cost_per_reasoning_token":7.5e-6,"cache_read_input_token_cost_flex":3.75e-8,"cache_read_input_audio_token_cost":7.5e-8,"cache_read_input_token_cost_priority":1.35e-7,"google_maps_grounding_cost_per_query":0.014},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"vertex/gemini-4-hydrogen@eu","object":"model","created":1794506460,"owned_by":"vertex","model_name":"gemini-4-hydrogen","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"Gemini 4 Hydrogen is the high-efficiency workhorse model of the Gemini 4 family from Google, built for high-throughput agentic workflows, coding and multi-model routing at lower cost and latency than...","source":null,"capabilities":{"input_modalities":["audio","file","image","text","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.65e-6,"output_cost_per_token":8.25e-6,"input_cost_per_audio_token":1.65e-6,"input_cost_per_image_token":1.65e-6,"cache_read_input_token_cost":8.25e-8,"input_cost_per_token_priority":2.9700000000000004e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.00001485,"cache_creation_input_token_cost":9.166666666666664e-8,"output_cost_per_reasoning_token":8.25e-6,"cache_read_input_audio_token_cost":8.25e-8,"input_cost_per_audio_token_priority":2.9700000000000004e-6,"cache_read_input_token_cost_priority":1.485e-7,"google_maps_grounding_cost_per_query":0.015400000000000002},"list_pricing":{"input_cost_per_token":1.65e-6,"output_cost_per_token":8.25e-6,"input_cost_per_audio_token":1.65e-6,"input_cost_per_image_token":1.65e-6,"cache_read_input_token_cost":8.25e-8,"input_cost_per_token_priority":2.9700000000000004e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.00001485,"cache_creation_input_token_cost":9.166666666666664e-8,"output_cost_per_reasoning_token":8.25e-6,"cache_read_input_audio_token_cost":8.25e-8,"input_cost_per_audio_token_priority":2.9700000000000004e-6,"cache_read_input_token_cost_priority":1.485e-7,"google_maps_grounding_cost_per_query":0.015400000000000002},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"vertex/gemini-4-hydrogen","object":"model","created":1794506460,"owned_by":"vertex","model_name":"gemini-4-hydrogen","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"Gemini 4 Hydrogen is the high-efficiency workhorse model of the Gemini 4 family from Google, built for high-throughput agentic workflows, coding and multi-model routing at lower cost and latency than...","source":null,"capabilities":{"input_modalities":["audio","file","image","text","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.5e-6,"output_cost_per_token":7.5e-6,"input_cost_per_audio_token":1.5e-6,"input_cost_per_image_token":1.5e-6,"cache_read_input_token_cost":7.5e-8,"input_cost_per_token_priority":2.7e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.0000135,"cache_creation_input_token_cost":8.33333333333333e-8,"output_cost_per_reasoning_token":7.5e-6,"cache_read_input_audio_token_cost":7.5e-8,"input_cost_per_audio_token_priority":2.7e-6,"cache_read_input_token_cost_priority":1.35e-7,"google_maps_grounding_cost_per_query":0.014},"list_pricing":{"input_cost_per_token":1.5e-6,"output_cost_per_token":7.5e-6,"input_cost_per_audio_token":1.5e-6,"input_cost_per_image_token":1.5e-6,"cache_read_input_token_cost":7.5e-8,"input_cost_per_token_priority":2.7e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.0000135,"cache_creation_input_token_cost":8.33333333333333e-8,"output_cost_per_reasoning_token":7.5e-6,"cache_read_input_audio_token_cost":7.5e-8,"input_cost_per_audio_token_priority":2.7e-6,"cache_read_input_token_cost_priority":1.35e-7,"google_maps_grounding_cost_per_query":0.014},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"vertex/gemini-4-hydrogen@us","object":"model","created":1794506460,"owned_by":"vertex","model_name":"gemini-4-hydrogen","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"Gemini 4 Hydrogen is the high-efficiency workhorse model of the Gemini 4 family from Google, built for high-throughput agentic workflows, coding and multi-model routing at lower cost and latency than...","source":null,"capabilities":{"input_modalities":["audio","file","image","text","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.65e-6,"output_cost_per_token":8.25e-6,"input_cost_per_audio_token":1.65e-6,"input_cost_per_image_token":1.65e-6,"cache_read_input_token_cost":8.25e-8,"input_cost_per_token_priority":2.9700000000000004e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.00001485,"cache_creation_input_token_cost":9.166666666666664e-8,"output_cost_per_reasoning_token":8.25e-6,"cache_read_input_audio_token_cost":8.25e-8,"input_cost_per_audio_token_priority":2.9700000000000004e-6,"cache_read_input_token_cost_priority":1.485e-7,"google_maps_grounding_cost_per_query":0.015400000000000002},"list_pricing":{"input_cost_per_token":1.65e-6,"output_cost_per_token":8.25e-6,"input_cost_per_audio_token":1.65e-6,"input_cost_per_image_token":1.65e-6,"cache_read_input_token_cost":8.25e-8,"input_cost_per_token_priority":2.9700000000000004e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.00001485,"cache_creation_input_token_cost":9.166666666666664e-8,"output_cost_per_reasoning_token":8.25e-6,"cache_read_input_audio_token_cost":8.25e-8,"input_cost_per_audio_token_priority":2.9700000000000004e-6,"cache_read_input_token_cost_priority":1.485e-7,"google_maps_grounding_cost_per_query":0.015400000000000002},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":4},{"id":"gemma-4-31b-it-fp8","object":"model","created":1794443601,"owned_by":"google","mode":"chat","context_length":102400,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6.60840258388541e-7,"output_cost_per_token":1.321680516777082e-6,"cache_read_input_token_cost":9.912603875828116e-8},"pricing_endpoint":"tsystems/gemma-4-31B-it-FP8","regions":[{"code":"eu","name":"Europe"}],"alias_of":null,"endpoints":[{"id":"tsystems/gemma-4-31B-it-FP8","object":"model","created":1794443601,"owned_by":"tsystems","model_name":"gemma-4-31B-it-FP8","context_length":102400,"max_input_tokens":null,"max_output_tokens":32768,"quantization":null,"retirement_date":null,"description":"Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6.60840258388541e-7,"output_cost_per_token":1.321680516777082e-6,"cache_read_input_token_cost":9.912603875828116e-8},"list_pricing":{"input_cost_per_token":6.60840258388541e-7,"output_cost_per_token":1.321680516777082e-6,"cache_read_input_token_cost":9.912603875828116e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":1},{"id":"glm-5.2","object":"model","created":1794443601,"owned_by":"zai","mode":"chat","context_length":1048576,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":true,"supports_json_mode":true,"supports_structured_outputs":true},"pricing":{"input_cost_per_token":1.7e-7,"output_cost_per_token":5.4e-7,"cache_read_input_token_cost":1.53e-8},"pricing_endpoint":"compactifai/glm-5-2","regions":[{"code":"ap","name":"Asia"},{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"tsystems/GLM-5.2","object":"model","created":1794443601,"owned_by":"tsystems","model_name":"GLM-5.2","context_length":1000000,"max_input_tokens":null,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GLM 5.2 is a large-scale reasoning model from Z.ai.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.6521006459713525e-6,"output_cost_per_token":3.854901507266489e-6,"cache_read_input_token_cost":2.478150968957029e-7},"list_pricing":{"input_cost_per_token":1.6521006459713525e-6,"output_cost_per_token":3.854901507266489e-6,"cache_read_input_token_cost":2.478150968957029e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"arkanecloud/zai-org/GLM-5.2","object":"model","created":1792768060,"owned_by":"arkanecloud","model_name":"zai-org/GLM-5.2","context_length":200000,"max_input_tokens":null,"max_output_tokens":100000,"quantization":null,"retirement_date":null,"description":"GLM 5.2 is a large-scale reasoning model from Z.ai.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.3e-6,"output_cost_per_token":4.2e-6,"cache_read_input_token_cost":2.5e-7},"list_pricing":{"input_cost_per_token":1.3e-6,"output_cost_per_token":4.2e-6,"cache_read_input_token_cost":2.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null},{"id":"greenpt/glm-5.2","object":"model","created":1791839241,"owned_by":"greenpt","model_name":"glm-5.2","context_length":1000000,"max_input_tokens":null,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"GLM 5.2 is a large-scale reasoning model from Z.ai.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.707170667503731e-6,"output_cost_per_token":5.066441980978815e-6,"cache_read_input_token_cost":4.4056017225902734e-7},"list_pricing":{"input_cost_per_token":1.707170667503731e-6,"output_cost_per_token":5.066441980978815e-6,"cache_read_input_token_cost":4.4056017225902734e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"tencent/glm-5.2","object":"model","created":1790867221,"owned_by":"tencent","model_name":"glm-5.2","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GLM 5.2 is a large-scale reasoning model from Z.ai.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.4e-6,"output_cost_per_token":4.4e-6,"cache_read_input_token_cost":2.6e-7,"input_cost_per_token_cache_hit":2.6e-7,"cache_creation_input_token_cost":0.0},"list_pricing":{"input_cost_per_token":1.4e-6,"output_cost_per_token":4.4e-6,"cache_read_input_token_cost":2.6e-7,"input_cost_per_token_cache_hit":2.6e-7,"cache_creation_input_token_cost":0.0},"discount":null,"discount_ends_at":null,"regions":[{"code":"ap","name":"Asia"}],"zero_data_retention":true,"alias_of":null},{"id":"compactifai/glm-5-2","object":"model","created":1788457256,"owned_by":"compactifai","model_name":"glm-5-2","context_length":null,"max_input_tokens":null,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"GLM 5.2 is a large-scale reasoning model from Z.ai.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.7e-7,"output_cost_per_token":5.4e-7,"cache_read_input_token_cost":1.53e-8},"list_pricing":{"input_cost_per_token":1.7e-7,"output_cost_per_token":5.4e-7,"cache_read_input_token_cost":1.53e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null},{"id":"compactifai/glm-5-2@us","object":"model","created":1788457256,"owned_by":"compactifai","model_name":"glm-5-2","context_length":null,"max_input_tokens":null,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"GLM 5.2 is a large-scale reasoning model from Z.ai.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.7e-7,"output_cost_per_token":5.4e-7,"cache_read_input_token_cost":1.53e-8},"list_pricing":{"input_cost_per_token":1.7e-7,"output_cost_per_token":5.4e-7,"cache_read_input_token_cost":1.53e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":null,"alias_of":null},{"id":"mistral/zai-glm-5-2@eu","object":"model","created":1787288981,"owned_by":"mistral","model_name":"zai-glm-5-2","context_length":1048576,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.54e-6,"output_cost_per_token":4.84e-6,"cache_read_input_token_cost":1.5400000000000003e-7},"list_pricing":{"input_cost_per_token":1.54e-6,"output_cost_per_token":4.84e-6,"cache_read_input_token_cost":1.5400000000000003e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"mistral/zai-glm-5-2","object":"model","created":1787288981,"owned_by":"mistral","model_name":"zai-glm-5-2","context_length":1048576,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.4e-6,"output_cost_per_token":4.4e-6,"cache_read_input_token_cost":1.4e-7},"list_pricing":{"input_cost_per_token":1.4e-6,"output_cost_per_token":4.4e-6,"cache_read_input_token_cost":1.4e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"tensorx/z-ai/glm-5.2","object":"model","created":1787003349,"owned_by":"tensorx","model_name":"z-ai/glm-5.2","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":64000,"quantization":"fp8","retirement_date":null,"description":"Served by TensorX at fp8 quantization.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-6,"output_cost_per_token":4.5e-6,"cache_read_input_token_cost":3.75e-7},"list_pricing":{"input_cost_per_token":1.5e-6,"output_cost_per_token":4.5e-6,"cache_read_input_token_cost":3.75e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"flexai/GLM-5.2","object":"model","created":1786610410,"owned_by":"flexai","model_name":"GLM-5.2","context_length":1048576,"max_input_tokens":null,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"GLM 5.2 is a large-scale reasoning model from Z.ai.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6e-7,"output_cost_per_token":2e-6,"cache_read_input_token_cost":9e-8},"list_pricing":{"input_cost_per_token":6e-7,"output_cost_per_token":2e-6,"cache_read_input_token_cost":9e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"databricks/databricks-glm-5-2","object":"model","created":1785417770,"owned_by":"databricks","model_name":"databricks-glm-5-2","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"GLM-5.2 is a mixture of experts (MoE) language model with 753B total parameters developed by Zhipu AI. The model supports a context length of 1M tokens and is optimized for long-horizon reasoning, coding, and agentic tool use.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.4e-6,"output_cost_per_token":4.4e-6,"input_dbu_cost_per_token":0.00002,"output_dbu_cost_per_token":0.000062857,"cache_read_input_token_cost":1.4e-7,"input_cost_per_token_priority":2.45e-6,"cache_creation_input_token_cost":1.4e-6,"cache_creation_input_token_cost_priority":2.45e-6},"list_pricing":{"input_cost_per_token":1.4e-6,"output_cost_per_token":4.4e-6,"input_dbu_cost_per_token":0.00002,"output_dbu_cost_per_token":0.000062857,"cache_read_input_token_cost":1.4e-7,"input_cost_per_token_priority":2.45e-6,"cache_creation_input_token_cost":1.4e-6,"cache_creation_input_token_cost_priority":2.45e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"scaleway/glm-5.2","object":"model","created":1782376549,"owned_by":"scaleway","model_name":"glm-5.2","context_length":256000,"max_input_tokens":null,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"GLM 5.2 is a large-scale reasoning model from Z.ai.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.9893591390053648e-6,"output_cost_per_token":6.078597369183059e-6},"list_pricing":{"input_cost_per_token":1.9893591390053648e-6,"output_cost_per_token":6.078597369183059e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"nebius/zai-org/GLM-5.2","object":"model","created":1781877753,"owned_by":"nebius","model_name":"zai-org/GLM-5.2","context_length":432000,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true,"supports_json_mode":true,"supports_structured_outputs":true},"pricing":{"input_cost_per_token":1.4e-6,"output_cost_per_token":4.4e-6},"list_pricing":{"input_cost_per_token":1.4e-6,"output_cost_per_token":4.4e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"cloudflare/@cf/zai-org/glm-5.2","object":"model","created":1781631930,"owned_by":"cloudflare","model_name":"@cf/zai-org/glm-5.2","context_length":262144,"max_input_tokens":262144,"max_output_tokens":131072,"quantization":null,"retirement_date":"2098-12-31","description":"GLM 5.2 is a large-scale reasoning model from Z.ai.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.4e-6,"output_cost_per_token":4.4e-6,"cache_read_input_token_cost":2.6e-7},"list_pricing":{"input_cost_per_token":1.4e-6,"output_cost_per_token":4.4e-6,"cache_read_input_token_cost":2.6e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"deepinfra/zai-org/GLM-5.2","object":"model","created":1781631930,"owned_by":"deepinfra","model_name":"zai-org/GLM-5.2","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":163840,"quantization":"fp4","retirement_date":"2098-12-31","description":"GLM 5.2 is a large-scale reasoning model from Z.ai.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":7.499999999999999e-7,"output_cost_per_token":2.4e-6,"cache_read_input_token_cost":1.400000025e-7},"list_pricing":{"input_cost_per_token":7.499999999999999e-7,"output_cost_per_token":2.4e-6,"cache_read_input_token_cost":1.400000025e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"mistral/glm-5-2@eu","object":"model","created":1781631930,"owned_by":"mistral","model_name":"glm-5-2","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":131072,"quantization":"fp4","retirement_date":null,"description":"GLM 5.2 is a large-scale reasoning model from Z.ai.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.54e-6,"output_cost_per_token":4.84e-6,"cache_read_input_token_cost":1.5400000000000003e-7,"input_cost_per_token_batches":7.7e-7,"output_cost_per_token_batches":2.42e-6,"cache_read_input_token_cost_batches":7.700000000000001e-8},"list_pricing":{"input_cost_per_token":1.54e-6,"output_cost_per_token":4.84e-6,"cache_read_input_token_cost":1.5400000000000003e-7,"input_cost_per_token_batches":7.7e-7,"output_cost_per_token_batches":2.42e-6,"cache_read_input_token_cost_batches":7.700000000000001e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"mistral/glm-5-2","object":"model","created":1781631930,"owned_by":"mistral","model_name":"glm-5-2","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":131072,"quantization":"fp4","retirement_date":null,"description":"GLM 5.2 is a large-scale reasoning model from Z.ai.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.4e-6,"output_cost_per_token":4.4e-6,"cache_read_input_token_cost":1.4e-7,"input_cost_per_token_batches":7e-7,"output_cost_per_token_batches":2.2e-6,"cache_read_input_token_cost_batches":7e-8},"list_pricing":{"input_cost_per_token":1.4e-6,"output_cost_per_token":4.4e-6,"cache_read_input_token_cost":1.4e-7,"input_cost_per_token_batches":7e-7,"output_cost_per_token_batches":2.2e-6,"cache_read_input_token_cost_batches":7e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"qwen/glm-5.2","object":"model","created":1781631930,"owned_by":"qwen","model_name":"glm-5.2","context_length":1000000,"max_input_tokens":1048576,"max_output_tokens":131072,"quantization":"fp8","retirement_date":null,"description":"GLM-5.2 is the latest flagship model from Zhipu AI, designed for long-horizon tasks with support for an ultra-long 1M context window. It features powerful logical reasoning, long-text comprehension, and code generation capabilities, balancing performance with inference efficiency. It excels across multi-task benchmarks and is well-suited for intelligent interaction, enterprise applications, and development assistance scenarios.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":9.1e-7,"output_cost_per_token":2.86e-6,"cache_read_input_token_cost":1.8200000000000002e-7},"list_pricing":{"input_cost_per_token":1.4e-6,"output_cost_per_token":4.4e-6,"cache_read_input_token_cost":2.8e-7},"discount":0.35,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null},{"id":"together_ai/zai-org/GLM-5.2","object":"model","created":1781631930,"owned_by":"together_ai","model_name":"zai-org/GLM-5.2","context_length":1048575,"max_input_tokens":1048575,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"GLM 5.2 is a large-scale reasoning model from Z.ai.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.4e-6,"output_cost_per_token":4.4e-6,"cache_read_input_token_cost":2.5999999999999995e-7},"list_pricing":{"input_cost_per_token":1.4e-6,"output_cost_per_token":4.4e-6,"cache_read_input_token_cost":2.5999999999999995e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null},{"id":"zai/glm-5.2","object":"model","created":1781631930,"owned_by":"zai","model_name":"glm-5.2","context_length":1048576,"max_input_tokens":1000000,"max_output_tokens":131072,"quantization":"fp8","retirement_date":null,"description":"GLM 5.2 is a large-scale reasoning model from Z.ai.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.4e-6,"output_cost_per_token":4.4e-6,"cache_read_input_token_cost":2.6e-7,"cache_creation_input_token_cost":0.0},"list_pricing":{"input_cost_per_token":1.4e-6,"output_cost_per_token":4.4e-6,"cache_read_input_token_cost":2.6e-7,"cache_creation_input_token_cost":0.0},"discount":null,"discount_ends_at":null,"regions":[{"code":"ap","name":"Asia"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":20},{"id":"glm-5.3-flash","object":"model","created":1794443601,"owned_by":"zai","mode":"chat","context_length":1048576,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":8.8e-8,"output_cost_per_token":2.5e-7,"cache_read_input_token_cost":1.32e-8},"pricing_endpoint":"flexai/GLM-5.3-Flash","regions":[{"code":"ap","name":"Asia"},{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"tsystems/GLM-5.3-Flash","object":"model","created":1794443601,"owned_by":"tsystems","model_name":"GLM-5.3-Flash","context_length":1000000,"max_input_tokens":null,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.2028008612951367e-7,"output_cost_per_token":6.60840258388541e-7,"cache_read_input_token_cost":3.304201291942705e-8},"list_pricing":{"input_cost_per_token":2.2028008612951367e-7,"output_cost_per_token":6.60840258388541e-7,"cache_read_input_token_cost":3.304201291942705e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"arkanecloud/zai-org/GLM-5.3-Flash","object":"model","created":1793900129,"owned_by":"arkanecloud","model_name":"zai-org/GLM-5.3-Flash","context_length":1000000,"max_input_tokens":null,"max_output_tokens":500000,"quantization":null,"retirement_date":null,"description":"GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":3e-8},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":3e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"},{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"mistral/zai-glm-5-3-flash@eu","object":"model","created":1792693170,"owned_by":"mistral","model_name":"zai-glm-5-3-flash","context_length":1048576,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.65e-7,"output_cost_per_token":5.5e-7,"cache_read_input_token_cost":3.3e-8},"list_pricing":{"input_cost_per_token":1.65e-7,"output_cost_per_token":5.5e-7,"cache_read_input_token_cost":3.3e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"mistral/zai-glm-5-3-flash","object":"model","created":1792693170,"owned_by":"mistral","model_name":"zai-glm-5-3-flash","context_length":1048576,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":3e-8},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":3e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"sference/zai-org/GLM-5.3-Flash","object":"model","created":1792636080,"owned_by":"sference","model_name":"zai-org/GLM-5.3-Flash","context_length":1048576,"max_input_tokens":null,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":7e-8},"list_pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":7e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"greenpt/glm-5.3-flash","object":"model","created":1791839241,"owned_by":"greenpt","model_name":"glm-5.3-flash","context_length":1000000,"max_input_tokens":null,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.2115404737123253e-7,"output_cost_per_token":4.846161894849301e-7,"cache_read_input_token_cost":2.4230809474246503e-8},"list_pricing":{"input_cost_per_token":1.2115404737123253e-7,"output_cost_per_token":4.846161894849301e-7,"cache_read_input_token_cost":2.4230809474246503e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"greenference/glm-5.3-flash","object":"model","created":1790948154,"owned_by":"greenference","model_name":"glm-5.3-flash","context_length":1048576,"max_input_tokens":null,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.3e-7,"output_cost_per_token":4.45e-7,"input_cost_per_image_token":0.0,"cache_read_input_token_cost":3e-8,"cache_creation_input_token_cost":0.0},"list_pricing":{"input_cost_per_token":1.3e-7,"output_cost_per_token":4.45e-7,"input_cost_per_image_token":0.0,"cache_read_input_token_cost":3e-8,"cache_creation_input_token_cost":0.0},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"flexai/GLM-5.3-Flash","object":"model","created":1790170741,"owned_by":"flexai","model_name":"GLM-5.3-Flash","context_length":1048576,"max_input_tokens":null,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":8.8e-8,"output_cost_per_token":2.5e-7,"cache_read_input_token_cost":1.32e-8},"list_pricing":{"input_cost_per_token":8.8e-8,"output_cost_per_token":2.5e-7,"cache_read_input_token_cost":1.32e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"databricks/databricks-glm-5-3-flash","object":"model","created":1788671370,"owned_by":"databricks","model_name":"databricks-glm-5-3-flash","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"GLM-5.3-Flash is a natively multimodal mixture-of-experts model with 320B total parameters and 18B active parameters, developed by Zhipu AI. It supports text and image input, a context length of 1,048,576 tokens, reasoning, coding, and agentic tool use.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":5e-7,"input_dbu_cost_per_token":2.143e-6,"output_dbu_cost_per_token":7.143e-6,"cache_read_input_token_cost":1.5e-8,"cache_creation_input_token_cost":1.5e-7,"cache_creation_input_token_cost_priority":2.625e-7},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":5e-7,"input_dbu_cost_per_token":2.143e-6,"output_dbu_cost_per_token":7.143e-6,"cache_read_input_token_cost":1.5e-8,"cache_creation_input_token_cost":1.5e-7,"cache_creation_input_token_cost_priority":2.625e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"fireworks_ai/accounts/fireworks/models/glm-5p3-flash","object":"model","created":1788498545,"owned_by":"fireworks_ai","model_name":"accounts/fireworks/models/glm-5p3-flash","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":3e-8,"input_cost_per_token_priority":1.875e-7,"output_cost_per_token_priority":6.25e-7,"cache_read_input_token_cost_priority":3.75e-8},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":3e-8,"input_cost_per_token_priority":1.875e-7,"output_cost_per_token_priority":6.25e-7,"cache_read_input_token_cost_priority":3.75e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"tensorx/z-ai/glm-5.3-flash","object":"model","created":1787929919,"owned_by":"tensorx","model_name":"z-ai/glm-5.3-flash","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":64000,"quantization":"fp8","retirement_date":null,"description":"Served by TensorX at fp8 quantization.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":5e-8},"list_pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":5e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"cloudflare/@cf/zai-org/glm-5.3-flash","object":"model","created":1787752741,"owned_by":"cloudflare","model_name":"@cf/zai-org/glm-5.3-flash","context_length":1048576,"max_input_tokens":null,"max_output_tokens":131072,"quantization":null,"retirement_date":"2098-12-31","description":"GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks.","source":null,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":3e-8},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":3e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"deepinfra/zai-org/GLM-5.3-Flash","object":"model","created":1787752741,"owned_by":"deepinfra","model_name":"zai-org/GLM-5.3-Flash","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":131072,"quantization":"fp4","retirement_date":"2098-12-31","description":"GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks.","source":null,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":3e-8},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":3e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"nebius/zai-org/GLM-5.3-Flash","object":"model","created":1787752741,"owned_by":"nebius","model_name":"zai-org/GLM-5.3-Flash","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":1024000,"quantization":"fp4","retirement_date":null,"description":"GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":1.5e-7},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":1.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"together_ai/zai-org/GLM-5.3-Flash","object":"model","created":1787752741,"owned_by":"together_ai","model_name":"zai-org/GLM-5.3-Flash","context_length":1048575,"max_input_tokens":1048575,"max_output_tokens":131072,"quantization":null,"retirement_date":"2098-12-31","description":"GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks.","source":null,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":3.0000000000000004e-8},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":3.0000000000000004e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null},{"id":"zai/glm-5.3-flash","object":"model","created":1787752741,"owned_by":"zai","model_name":"glm-5.3-flash","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":131072,"quantization":"fp8","retirement_date":"2098-12-31","description":"GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks.","source":null,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":3e-8,"cache_creation_input_token_cost":0.0},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":3e-8,"cache_creation_input_token_cost":0.0},"discount":null,"discount_ends_at":null,"regions":[{"code":"ap","name":"Asia"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":16},{"id":"gpt-oss-120b","object":"model","created":1794443601,"owned_by":"openai","mode":"chat","context_length":131072,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":3e-8,"output_cost_per_token":1.5e-7,"cache_read_input_token_cost":4.5e-9},"pricing_endpoint":"flexai/gpt-oss-120b","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"tsystems/gpt-oss-120b","object":"model","created":1794443601,"owned_by":"tsystems","model_name":"gpt-oss-120b","context_length":131072,"max_input_tokens":null,"max_output_tokens":32768,"quantization":null,"retirement_date":null,"description":"gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.2028008612951367e-7,"output_cost_per_token":7.159102799209194e-7,"cache_read_input_token_cost":3.304201291942705e-8},"list_pricing":{"input_cost_per_token":2.2028008612951367e-7,"output_cost_per_token":7.159102799209194e-7,"cache_read_input_token_cost":3.304201291942705e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"arkanecloud/openai/gpt-oss-120b","object":"model","created":1792768060,"owned_by":"arkanecloud","model_name":"openai/gpt-oss-120b","context_length":131072,"max_input_tokens":null,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":1e-7},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":1e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"},{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"greenpt/gpt-oss-120b","object":"model","created":1791839241,"owned_by":"greenpt","model_name":"gpt-oss-120b","context_length":128000,"max_input_tokens":null,"max_output_tokens":32000,"quantization":null,"retirement_date":null,"description":"gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.2028008612951367e-7,"output_cost_per_token":7.709803014532979e-7},"list_pricing":{"input_cost_per_token":2.2028008612951367e-7,"output_cost_per_token":7.709803014532979e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"ionos/openai/gpt-oss-120b","object":"model","created":1786647205,"owned_by":"ionos","model_name":"openai/gpt-oss-120b","context_length":128000,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.6521006459713525e-7,"output_cost_per_token":7.159102799209195e-7},"list_pricing":{"input_cost_per_token":1.6521006459713525e-7,"output_cost_per_token":7.159102799209195e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"flexai/gpt-oss-120b","object":"model","created":1786610410,"owned_by":"flexai","model_name":"gpt-oss-120b","context_length":131072,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-8,"output_cost_per_token":1.5e-7,"cache_read_input_token_cost":4.5e-9},"list_pricing":{"input_cost_per_token":3e-8,"output_cost_per_token":1.5e-7,"cache_read_input_token_cost":4.5e-9},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"cloudflare/@cf/openai/gpt-oss-120b","object":"model","created":1782119040,"owned_by":"cloudflare","model_name":"@cf/openai/gpt-oss-120b","context_length":128000,"max_input_tokens":128000,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.5e-7,"output_cost_per_token":7.5e-7},"list_pricing":{"input_cost_per_token":3.5e-7,"output_cost_per_token":7.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"databricks/databricks-gpt-oss-120b@eu","object":"model","created":1769507058,"owned_by":"databricks","model_name":"databricks-gpt-oss-120b","context_length":131072,"max_input_tokens":131072,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"GPT OSS 120B is a state-of-the-art, reasoning model with chain-of-thought and adjustable reasoning effort levels built and trained by OpenAI. It is OpenAI's flagship open-weight model that features a 128K token context window. The model is built for high-quality reasoning tasks.","source":"https://www.databricks.com/product/pricing/foundation-model-serving","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"input_dbu_cost_per_token":2.1429999999999996e-6,"output_dbu_cost_per_token":8.571e-6,"cache_read_input_token_cost":1.5e-8,"cache_creation_input_token_cost":1.5e-7},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"input_dbu_cost_per_token":2.1429999999999996e-6,"output_dbu_cost_per_token":8.571e-6,"cache_read_input_token_cost":1.5e-8,"cache_creation_input_token_cost":1.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"databricks/databricks-gpt-oss-120b","object":"model","created":1769507058,"owned_by":"databricks","model_name":"databricks-gpt-oss-120b","context_length":131072,"max_input_tokens":131072,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"GPT OSS 120B is a state-of-the-art, reasoning model with chain-of-thought and adjustable reasoning effort levels built and trained by OpenAI. It is OpenAI's flagship open-weight model that features a 128K token context window. The model is built for high-quality reasoning tasks.","source":"https://www.databricks.com/product/pricing/foundation-model-serving","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"input_dbu_cost_per_token":2.1429999999999996e-6,"output_dbu_cost_per_token":8.571e-6,"cache_read_input_token_cost":1.5e-8,"cache_creation_input_token_cost":1.5e-7},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"input_dbu_cost_per_token":2.1429999999999996e-6,"output_dbu_cost_per_token":8.571e-6,"cache_read_input_token_cost":1.5e-8,"cache_creation_input_token_cost":1.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"fireworks_ai/accounts/fireworks/models/gpt-oss-120b","object":"model","created":1769507058,"owned_by":"fireworks_ai","model_name":"accounts/fireworks/models/gpt-oss-120b","context_length":131072,"max_input_tokens":131072,"max_output_tokens":32768,"quantization":null,"retirement_date":null,"description":"gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases.","source":"https://fireworks.ai/pricing","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":1.5e-8,"input_cost_per_token_priority":1.8e-7,"output_cost_per_token_priority":7.2e-7,"cache_read_input_token_cost_priority":1.8e-8},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":1.5e-8,"input_cost_per_token_priority":1.8e-7,"output_cost_per_token_priority":7.2e-7,"cache_read_input_token_cost_priority":1.8e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"ovhcloud/gpt-oss-120b","object":"model","created":1769507058,"owned_by":"ovhcloud","model_name":"gpt-oss-120b","context_length":131072,"max_input_tokens":131000,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases.","source":"https://endpoints.ai.cloud.ovh.net/models/gpt-oss-120b","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":9e-8,"output_cost_per_token":4.7e-7},"list_pricing":{"input_cost_per_token":9e-8,"output_cost_per_token":4.7e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/openai.gpt-oss-120b-1:0","object":"model","created":1767692616,"owned_by":"amazon","model_name":"openai.gpt-oss-120b-1:0","context_length":128000,"max_input_tokens":128000,"max_output_tokens":16384,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"input_cost_per_token_flex":7.5e-8,"output_cost_per_token_flex":3e-7,"input_cost_per_token_priority":2.625e-7,"output_cost_per_token_priority":1.05e-6},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"input_cost_per_token_flex":7.5e-8,"output_cost_per_token_flex":3e-7,"input_cost_per_token_priority":2.625e-7,"output_cost_per_token_priority":1.05e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/openai.gpt-oss-120b-1:0@us","object":"model","created":1767692616,"owned_by":"amazon","model_name":"openai.gpt-oss-120b-1:0","context_length":128000,"max_input_tokens":128000,"max_output_tokens":16384,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"input_cost_per_token_flex":7.5e-8,"output_cost_per_token_flex":3e-7,"input_cost_per_token_priority":2.625e-7,"output_cost_per_token_priority":1.05e-6},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"input_cost_per_token_flex":7.5e-8,"output_cost_per_token_flex":3e-7,"input_cost_per_token_priority":2.625e-7,"output_cost_per_token_priority":1.05e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"scaleway/gpt-oss-120b","object":"model","created":1755093042,"owned_by":"scaleway","model_name":"gpt-oss-120b","context_length":128000,"max_input_tokens":null,"max_output_tokens":32768,"quantization":null,"retirement_date":null,"description":"gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.6521006459713525e-7,"output_cost_per_token":6.60840258388541e-7},"list_pricing":{"input_cost_per_token":1.6521006459713525e-7,"output_cost_per_token":6.60840258388541e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"cerebras/gpt-oss-120b","object":"model","created":1754414231,"owned_by":"cerebras","model_name":"gpt-oss-120b","context_length":131072,"max_input_tokens":131072,"max_output_tokens":40960,"quantization":"fp16","retirement_date":null,"description":"gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases.","source":"https://www.cerebras.ai/blog/openai-gpt-oss-120b-runs-fastest-on-cerebras","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":3.5e-7,"output_cost_per_token":7.5e-7,"cache_read_input_token_cost":3.5e-7},"list_pricing":{"input_cost_per_token":3.5e-7,"output_cost_per_token":7.5e-7,"cache_read_input_token_cost":3.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"deepinfra/openai/gpt-oss-120b","object":"model","created":1754414231,"owned_by":"deepinfra","model_name":"openai/gpt-oss-120b","context_length":131072,"max_input_tokens":131072,"max_output_tokens":null,"quantization":"bf16","retirement_date":null,"description":"gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.7e-8,"output_cost_per_token":1.7e-7,"cache_read_input_token_cost":1.85e-8},"list_pricing":{"input_cost_per_token":3.7e-8,"output_cost_per_token":1.7e-7,"cache_read_input_token_cost":1.85e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"fireworks_ai/gpt-oss-120b","object":"model","created":1754414231,"owned_by":"fireworks_ai","model_name":"gpt-oss-120b","context_length":131072,"max_input_tokens":131072,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized...","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":1.4e-8},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":1.4e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"groq/openai/gpt-oss-120b","object":"model","created":1754414231,"owned_by":"groq","model_name":"openai/gpt-oss-120b","context_length":131072,"max_input_tokens":131072,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":7.5e-8,"search_context_cost_per_query":{"search_context_size_low":0.005,"search_context_size_high":0.005,"search_context_size_medium":0.005}},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":7.5e-8,"search_context_cost_per_query":{"search_context_size_low":0.005,"search_context_size_high":0.005,"search_context_size_medium":0.005}},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":null,"alias_of":null},{"id":"nebius/openai/gpt-oss-120b","object":"model","created":1754414231,"owned_by":"nebius","model_name":"openai/gpt-oss-120b","context_length":131072,"max_input_tokens":131072,"max_output_tokens":null,"quantization":"fp4","retirement_date":null,"description":"gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":1.5e-7},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":1.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"together_ai/openai/gpt-oss-120b","object":"model","created":1754414231,"owned_by":"together_ai","model_name":"openai/gpt-oss-120b","context_length":131072,"max_input_tokens":131072,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases.","source":"https://www.together.ai/models/gpt-oss-120b","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null},{"id":"vertex/openai/gpt-oss-120b-maas","object":"model","created":1754414231,"owned_by":"vertex","model_name":"openai/gpt-oss-120b-maas","context_length":131072,"max_input_tokens":131072,"max_output_tokens":32768,"quantization":null,"retirement_date":null,"description":"gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":9e-8,"output_cost_per_token":3.6e-7},"list_pricing":{"input_cost_per_token":9e-8,"output_cost_per_token":3.6e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":20},{"id":"mistral-small-4-119b-2603","object":"model","created":1794443601,"owned_by":"mistral","mode":"chat","context_length":262144,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":1.5e-8},"pricing_endpoint":"arkanecloud/mistralai/Mistral-Small-4-119B-2603","regions":[{"code":"ch","name":"Switzerland"},{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"tsystems/Mistral-Small-4-119B-2603","object":"model","created":1794443601,"owned_by":"tsystems","model_name":"Mistral-Small-4-119B-2603","context_length":262144,"max_input_tokens":null,"max_output_tokens":32768,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6.60840258388541e-7,"output_cost_per_token":1.321680516777082e-6,"cache_read_input_token_cost":9.912603875828116e-8},"list_pricing":{"input_cost_per_token":6.60840258388541e-7,"output_cost_per_token":1.321680516777082e-6,"cache_read_input_token_cost":9.912603875828116e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"arkanecloud/mistralai/Mistral-Small-4-119B-2603","object":"model","created":1792768060,"owned_by":"arkanecloud","model_name":"mistralai/Mistral-Small-4-119B-2603","context_length":262144,"max_input_tokens":null,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":1.5e-8},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":1.5e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"},{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"infomaniak/mistralai/Mistral-Small-4-119B-2603","object":"model","created":1792029544,"owned_by":"infomaniak","model_name":"mistralai/Mistral-Small-4-119B-2603","context_length":256000,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.2028008612951367e-7,"output_cost_per_token":8.260503229856763e-7},"list_pricing":{"input_cost_per_token":2.2028008612951367e-7,"output_cost_per_token":8.260503229856763e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"ch","name":"Switzerland"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":3},{"id":"nemotron-3-super-120b-a12b-fp8","object":"model","created":1794443601,"owned_by":"nvidia","mode":"chat","context_length":1000000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6.60840258388541e-7,"output_cost_per_token":1.321680516777082e-6,"cache_read_input_token_cost":9.912603875828116e-8},"pricing_endpoint":"tsystems/NVIDIA-Nemotron-3-Super-120B-A12B-FP8","regions":[{"code":"eu","name":"Europe"}],"alias_of":null,"endpoints":[{"id":"tsystems/NVIDIA-Nemotron-3-Super-120B-A12B-FP8","object":"model","created":1794443601,"owned_by":"tsystems","model_name":"NVIDIA-Nemotron-3-Super-120B-A12B-FP8","context_length":1000000,"max_input_tokens":null,"max_output_tokens":32768,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6.60840258388541e-7,"output_cost_per_token":1.321680516777082e-6,"cache_read_input_token_cost":9.912603875828116e-8},"list_pricing":{"input_cost_per_token":6.60840258388541e-7,"output_cost_per_token":1.321680516777082e-6,"cache_read_input_token_cost":9.912603875828116e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":1},{"id":"qwen3.6-35b-a3b-fp8","object":"model","created":1794443601,"owned_by":"qwen","mode":"chat","context_length":262144,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6.60840258388541e-7,"output_cost_per_token":1.321680516777082e-6,"cache_read_input_token_cost":9.912603875828116e-8},"pricing_endpoint":"tsystems/Qwen3.6-35B-A3B-FP8","regions":[{"code":"eu","name":"Europe"}],"alias_of":null,"endpoints":[{"id":"tsystems/Qwen3.6-35B-A3B-FP8","object":"model","created":1794443601,"owned_by":"tsystems","model_name":"Qwen3.6-35B-A3B-FP8","context_length":262144,"max_input_tokens":null,"max_output_tokens":32768,"quantization":null,"retirement_date":null,"description":"Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6.60840258388541e-7,"output_cost_per_token":1.321680516777082e-6,"cache_read_input_token_cost":9.912603875828116e-8},"list_pricing":{"input_cost_per_token":6.60840258388541e-7,"output_cost_per_token":1.321680516777082e-6,"cache_read_input_token_cost":9.912603875828116e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":1},{"id":"~glm-flash-latest","object":"model","created":1794443601,"owned_by":"zai","mode":"chat","context_length":1048576,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":8.8e-8,"output_cost_per_token":2.5e-7,"cache_read_input_token_cost":1.32e-8},"pricing_endpoint":"flexai/GLM-5.3-Flash","regions":[{"code":"ap","name":"Asia"},{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":"glm-5.3-flash","endpoints":[{"id":"tsystems/GLM-5.3-Flash","object":"model","created":1794443601,"owned_by":"tsystems","model_name":"GLM-5.3-Flash","context_length":1000000,"max_input_tokens":null,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.2028008612951367e-7,"output_cost_per_token":6.60840258388541e-7,"cache_read_input_token_cost":3.304201291942705e-8},"list_pricing":{"input_cost_per_token":2.2028008612951367e-7,"output_cost_per_token":6.60840258388541e-7,"cache_read_input_token_cost":3.304201291942705e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"arkanecloud/zai-org/GLM-5.3-Flash","object":"model","created":1793900129,"owned_by":"arkanecloud","model_name":"zai-org/GLM-5.3-Flash","context_length":1000000,"max_input_tokens":null,"max_output_tokens":500000,"quantization":null,"retirement_date":null,"description":"GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":3e-8},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":3e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"},{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"mistral/zai-glm-5-3-flash@eu","object":"model","created":1792693170,"owned_by":"mistral","model_name":"zai-glm-5-3-flash","context_length":1048576,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.65e-7,"output_cost_per_token":5.5e-7,"cache_read_input_token_cost":3.3e-8},"list_pricing":{"input_cost_per_token":1.65e-7,"output_cost_per_token":5.5e-7,"cache_read_input_token_cost":3.3e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"mistral/zai-glm-5-3-flash","object":"model","created":1792693170,"owned_by":"mistral","model_name":"zai-glm-5-3-flash","context_length":1048576,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":3e-8},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":3e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"sference/zai-org/GLM-5.3-Flash","object":"model","created":1792636080,"owned_by":"sference","model_name":"zai-org/GLM-5.3-Flash","context_length":1048576,"max_input_tokens":null,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":7e-8},"list_pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":7e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"greenpt/glm-5.3-flash","object":"model","created":1791839241,"owned_by":"greenpt","model_name":"glm-5.3-flash","context_length":1000000,"max_input_tokens":null,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.2115404737123253e-7,"output_cost_per_token":4.846161894849301e-7,"cache_read_input_token_cost":2.4230809474246503e-8},"list_pricing":{"input_cost_per_token":1.2115404737123253e-7,"output_cost_per_token":4.846161894849301e-7,"cache_read_input_token_cost":2.4230809474246503e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"greenference/glm-5.3-flash","object":"model","created":1790948154,"owned_by":"greenference","model_name":"glm-5.3-flash","context_length":1048576,"max_input_tokens":null,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.3e-7,"output_cost_per_token":4.45e-7,"input_cost_per_image_token":0.0,"cache_read_input_token_cost":3e-8,"cache_creation_input_token_cost":0.0},"list_pricing":{"input_cost_per_token":1.3e-7,"output_cost_per_token":4.45e-7,"input_cost_per_image_token":0.0,"cache_read_input_token_cost":3e-8,"cache_creation_input_token_cost":0.0},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"flexai/GLM-5.3-Flash","object":"model","created":1790170741,"owned_by":"flexai","model_name":"GLM-5.3-Flash","context_length":1048576,"max_input_tokens":null,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":8.8e-8,"output_cost_per_token":2.5e-7,"cache_read_input_token_cost":1.32e-8},"list_pricing":{"input_cost_per_token":8.8e-8,"output_cost_per_token":2.5e-7,"cache_read_input_token_cost":1.32e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"databricks/databricks-glm-5-3-flash","object":"model","created":1788671370,"owned_by":"databricks","model_name":"databricks-glm-5-3-flash","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"GLM-5.3-Flash is a natively multimodal mixture-of-experts model with 320B total parameters and 18B active parameters, developed by Zhipu AI. It supports text and image input, a context length of 1,048,576 tokens, reasoning, coding, and agentic tool use.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":5e-7,"input_dbu_cost_per_token":2.143e-6,"output_dbu_cost_per_token":7.143e-6,"cache_read_input_token_cost":1.5e-8,"cache_creation_input_token_cost":1.5e-7,"cache_creation_input_token_cost_priority":2.625e-7},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":5e-7,"input_dbu_cost_per_token":2.143e-6,"output_dbu_cost_per_token":7.143e-6,"cache_read_input_token_cost":1.5e-8,"cache_creation_input_token_cost":1.5e-7,"cache_creation_input_token_cost_priority":2.625e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"fireworks_ai/accounts/fireworks/models/glm-5p3-flash","object":"model","created":1788498545,"owned_by":"fireworks_ai","model_name":"accounts/fireworks/models/glm-5p3-flash","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":3e-8,"input_cost_per_token_priority":1.875e-7,"output_cost_per_token_priority":6.25e-7,"cache_read_input_token_cost_priority":3.75e-8},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":3e-8,"input_cost_per_token_priority":1.875e-7,"output_cost_per_token_priority":6.25e-7,"cache_read_input_token_cost_priority":3.75e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"tensorx/z-ai/glm-5.3-flash","object":"model","created":1787929919,"owned_by":"tensorx","model_name":"z-ai/glm-5.3-flash","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":64000,"quantization":"fp8","retirement_date":null,"description":"Served by TensorX at fp8 quantization.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":5e-8},"list_pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":5e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"cloudflare/@cf/zai-org/glm-5.3-flash","object":"model","created":1787752741,"owned_by":"cloudflare","model_name":"@cf/zai-org/glm-5.3-flash","context_length":1048576,"max_input_tokens":null,"max_output_tokens":131072,"quantization":null,"retirement_date":"2098-12-31","description":"GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks.","source":null,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":3e-8},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":3e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"deepinfra/zai-org/GLM-5.3-Flash","object":"model","created":1787752741,"owned_by":"deepinfra","model_name":"zai-org/GLM-5.3-Flash","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":131072,"quantization":"fp4","retirement_date":"2098-12-31","description":"GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks.","source":null,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":3e-8},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":3e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"nebius/zai-org/GLM-5.3-Flash","object":"model","created":1787752741,"owned_by":"nebius","model_name":"zai-org/GLM-5.3-Flash","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":1024000,"quantization":"fp4","retirement_date":null,"description":"GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":1.5e-7},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":1.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"together_ai/zai-org/GLM-5.3-Flash","object":"model","created":1787752741,"owned_by":"together_ai","model_name":"zai-org/GLM-5.3-Flash","context_length":1048575,"max_input_tokens":1048575,"max_output_tokens":131072,"quantization":null,"retirement_date":"2098-12-31","description":"GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks.","source":null,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":3.0000000000000004e-8},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":3.0000000000000004e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null},{"id":"zai/glm-5.3-flash","object":"model","created":1787752741,"owned_by":"zai","model_name":"glm-5.3-flash","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":131072,"quantization":"fp8","retirement_date":"2098-12-31","description":"GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks.","source":null,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":3e-8,"cache_creation_input_token_cost":0.0},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":3e-8,"cache_creation_input_token_cost":0.0},"discount":null,"discount_ends_at":null,"regions":[{"code":"ap","name":"Asia"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":16},{"id":"mimo-v2.6-flash-rl","object":"model","created":1794410001,"owned_by":"xiaomi","mode":"chat","context_length":1048576,"capabilities":{"input_modalities":["text","image","audio","video"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.4e-7,"output_cost_per_token":2.8e-7,"cache_read_input_token_cost":3.7e-9},"pricing_endpoint":"flexai/MiMo-V2.6-Flash-RL","regions":[{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"flexai/MiMo-V2.6-Flash-RL","object":"model","created":1794410001,"owned_by":"flexai","model_name":"MiMo-V2.6-Flash-RL","context_length":1048576,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image","audio","video"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.4e-7,"output_cost_per_token":2.8e-7,"cache_read_input_token_cost":3.7e-9},"list_pricing":{"input_cost_per_token":1.4e-7,"output_cost_per_token":2.8e-7,"cache_read_input_token_cost":3.7e-9},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"minimax-m3.1-flash","object":"model","created":1794410001,"owned_by":"minimax","mode":"chat","context_length":1048576,"capabilities":{"input_modalities":["text","image","video","audio"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":7.5e-8,"output_cost_per_token":3e-7,"cache_read_input_token_cost":7.5e-9},"pricing_endpoint":"minimax/MiniMax-M3.1-Flash","regions":[{"code":"ap","name":"Asia"},{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"flexai/MiniMax-M3.1-Flash","object":"model","created":1794410001,"owned_by":"flexai","model_name":"MiniMax-M3.1-Flash","context_length":1048576,"max_input_tokens":null,"max_output_tokens":524288,"quantization":null,"retirement_date":null,"description":"MiniMax-M3.1-Flash is a multimodal model from MiniMax. Compared with M3, it delivers significant improvements across multiple benchmarks, particularly in complex agentic tasks, coding, and cybersecurity.","source":null,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":1.5e-8},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":1.5e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"arkanecloud/MiniMaxAI/MiniMax-M3.1-Flash","object":"model","created":1794257614,"owned_by":"arkanecloud","model_name":"MiniMaxAI/MiniMax-M3.1-Flash","context_length":1000000,"max_input_tokens":null,"max_output_tokens":500000,"quantization":null,"retirement_date":null,"description":"MiniMax-M3.1-Flash is a multimodal model from MiniMax. Compared with M3, it delivers significant improvements across multiple benchmarks, particularly in complex agentic tasks, coding, and cybersecurity.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":1.5e-8},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":1.5e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"},{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"tencent/minimax-m3.1-flash","object":"model","created":1793077988,"owned_by":"tencent","model_name":"minimax-m3.1-flash","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":512000,"quantization":null,"retirement_date":null,"description":"MiniMax-M3.1-Flash is a multimodal model from MiniMax. Compared with M3, it delivers significant improvements across multiple benchmarks, particularly in complex agentic tasks, coding, and cybersecurity.","source":null,"capabilities":{"input_modalities":["text","image","video","audio"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":1.5e-8},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":1.5e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"ap","name":"Asia"}],"zero_data_retention":true,"alias_of":null},{"id":"tensorx/minimax/minimax-m3.1-flash","object":"model","created":1792854448,"owned_by":"tensorx","model_name":"minimax/minimax-m3.1-flash","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":64000,"quantization":"fp8","retirement_date":null,"description":"Served by TensorX at fp8 quantization.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1.2e-6,"cache_read_input_token_cost":7.5e-8},"list_pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1.2e-6,"cache_read_input_token_cost":7.5e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"fireworks_ai/accounts/fireworks/models/minimax-m3p1-flash","object":"model","created":1792473255,"owned_by":"fireworks_ai","model_name":"accounts/fireworks/models/minimax-m3p1-flash","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":524288,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":1.5e-8,"input_cost_per_token_priority":2.25e-7,"output_cost_per_token_priority":9e-7,"cache_read_input_token_cost_priority":2.25e-8},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":1.5e-8,"input_cost_per_token_priority":2.25e-7,"output_cost_per_token_priority":9e-7,"cache_read_input_token_cost_priority":2.25e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"minimax/MiniMax-M3.1-Flash","object":"model","created":1792379569,"owned_by":"minimax","model_name":"MiniMax-M3.1-Flash","context_length":1048576,"max_input_tokens":null,"max_output_tokens":524288,"quantization":null,"retirement_date":null,"description":"MiniMax-M3.1-Flash is a multimodal model from MiniMax. Compared with M3, it delivers significant improvements across multiple benchmarks, particularly in complex agentic tasks, coding, and cybersecurity.","source":null,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":7.5e-8,"output_cost_per_token":3e-7,"cache_read_input_token_cost":7.5e-9},"list_pricing":{"input_cost_per_token":7.5e-8,"output_cost_per_token":3e-7,"cache_read_input_token_cost":7.5e-9},"discount":null,"discount_ends_at":null,"regions":[{"code":"ap","name":"Asia"}],"zero_data_retention":false,"alias_of":null},{"id":"nebius/MiniMaxAI/MiniMax-M3.1-Flash","object":"model","created":1792379569,"owned_by":"nebius","model_name":"MiniMaxAI/MiniMax-M3.1-Flash","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":524288,"quantization":"fp4","retirement_date":null,"description":"MiniMax-M3.1-Flash is a multimodal model from MiniMax. Compared with M3, it delivers significant improvements across multiple benchmarks, particularly in complex agentic tasks, coding, and cybersecurity.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":1.5e-7},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":1.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"together_ai/MiniMaxAI/MiniMax-M3.1-Flash","object":"model","created":1792379569,"owned_by":"together_ai","model_name":"MiniMaxAI/MiniMax-M3.1-Flash","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":524288,"quantization":null,"retirement_date":null,"description":"MiniMax-M3.1-Flash is a multimodal model from MiniMax. Compared with M3, it delivers significant improvements across multiple benchmarks, particularly in complex agentic tasks, coding, and cybersecurity.","source":null,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":1.5000000000000002e-8},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":1.5000000000000002e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":8},{"id":"gemini-4-carbon","object":"model","created":1794364821,"owned_by":"google","mode":"chat","context_length":1048576,"capabilities":{"input_modalities":["audio","file","image","text","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"input_cost_per_audio_token":2e-6,"input_cost_per_image_token":2e-6,"cache_read_input_token_cost":1e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"cache_creation_input_token_cost":1.875e-7,"output_cost_per_reasoning_token":0.00001,"cache_read_input_audio_token_cost":1e-7,"google_maps_grounding_cost_per_query":0.007},"pricing_endpoint":"google/gemini-4-carbon","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"databricks/databricks-gemini-4-carbon","object":"model","created":1794364821,"owned_by":"databricks","model_name":"databricks-gemini-4-carbon","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":32768,"quantization":null,"retirement_date":null,"description":"Gemini 4 Carbon is Google's frontier model for complex reasoning, coding, and multimodal tasks. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["audio","file","image","text","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"cache_read_input_token_cost":2e-6,"cache_creation_input_token_cost":2e-6},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"cache_read_input_token_cost":2e-6,"cache_creation_input_token_cost":2e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"google/gemini-4-carbon","object":"model","created":1794326871,"owned_by":"google","model_name":"gemini-4-carbon","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":32768,"quantization":null,"retirement_date":null,"description":"Gemini 4 Carbon is a frontier Gemini 4 model from Google for coding, agentic and complex reasoning work.","source":null,"capabilities":{"input_modalities":["audio","file","image","text","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"input_cost_per_audio_token":2e-6,"input_cost_per_image_token":2e-6,"cache_read_input_token_cost":1e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"cache_creation_input_token_cost":1.875e-7,"output_cost_per_reasoning_token":0.00001,"cache_read_input_audio_token_cost":1e-7,"google_maps_grounding_cost_per_query":0.007},"list_pricing":{"input_cost_per_token":4e-6,"output_cost_per_token":0.00002,"input_cost_per_audio_token":4e-6,"input_cost_per_image_token":4e-6,"cache_read_input_token_cost":2e-7,"search_context_cost_per_query":{"search_context_size_low":0.028,"search_context_size_high":0.028,"search_context_size_medium":0.028},"cache_creation_input_token_cost":3.75e-7,"output_cost_per_reasoning_token":0.00002,"cache_read_input_audio_token_cost":2e-7,"google_maps_grounding_cost_per_query":0.014},"discount":0.5,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"vertex/gemini-4-carbon@eu","object":"model","created":1794326871,"owned_by":"vertex","model_name":"gemini-4-carbon","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":32768,"quantization":null,"retirement_date":null,"description":"Gemini 4 Carbon is a frontier Gemini 4 model from Google for coding, agentic and complex reasoning work.","source":null,"capabilities":{"input_modalities":["audio","file","image","text","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2.2e-6,"output_cost_per_token":0.000011000000000000001,"input_cost_per_audio_token":2.2e-6,"input_cost_per_image_token":2.2e-6,"cache_read_input_token_cost":1.1e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"cache_creation_input_token_cost":2.0625e-7,"output_cost_per_reasoning_token":0.000011000000000000001,"cache_read_input_audio_token_cost":1.1e-7,"google_maps_grounding_cost_per_query":0.007700000000000001},"list_pricing":{"input_cost_per_token":4.4e-6,"output_cost_per_token":0.000022000000000000003,"input_cost_per_audio_token":4.4e-6,"input_cost_per_image_token":4.4e-6,"cache_read_input_token_cost":2.2e-7,"search_context_cost_per_query":{"search_context_size_low":0.028,"search_context_size_high":0.028,"search_context_size_medium":0.028},"cache_creation_input_token_cost":4.125e-7,"output_cost_per_reasoning_token":0.000022000000000000003,"cache_read_input_audio_token_cost":2.2e-7,"google_maps_grounding_cost_per_query":0.015400000000000002},"discount":0.5,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"vertex/gemini-4-carbon","object":"model","created":1794326871,"owned_by":"vertex","model_name":"gemini-4-carbon","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":32768,"quantization":null,"retirement_date":null,"description":"Gemini 4 Carbon is a frontier Gemini 4 model from Google for coding, agentic and complex reasoning work.","source":null,"capabilities":{"input_modalities":["audio","file","image","text","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"input_cost_per_audio_token":2e-6,"input_cost_per_image_token":2e-6,"cache_read_input_token_cost":1e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"cache_creation_input_token_cost":1.875e-7,"output_cost_per_reasoning_token":0.00001,"cache_read_input_audio_token_cost":1e-7,"google_maps_grounding_cost_per_query":0.007},"list_pricing":{"input_cost_per_token":4e-6,"output_cost_per_token":0.00002,"input_cost_per_audio_token":4e-6,"input_cost_per_image_token":4e-6,"cache_read_input_token_cost":2e-7,"search_context_cost_per_query":{"search_context_size_low":0.028,"search_context_size_high":0.028,"search_context_size_medium":0.028},"cache_creation_input_token_cost":3.75e-7,"output_cost_per_reasoning_token":0.00002,"cache_read_input_audio_token_cost":2e-7,"google_maps_grounding_cost_per_query":0.014},"discount":0.5,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"vertex/gemini-4-carbon@us","object":"model","created":1794326871,"owned_by":"vertex","model_name":"gemini-4-carbon","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":32768,"quantization":null,"retirement_date":null,"description":"Gemini 4 Carbon is a frontier Gemini 4 model from Google for coding, agentic and complex reasoning work.","source":null,"capabilities":{"input_modalities":["audio","file","image","text","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2.2e-6,"output_cost_per_token":0.000011000000000000001,"input_cost_per_audio_token":2.2e-6,"input_cost_per_image_token":2.2e-6,"cache_read_input_token_cost":1.1e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"cache_creation_input_token_cost":2.0625e-7,"output_cost_per_reasoning_token":0.000011000000000000001,"cache_read_input_audio_token_cost":1.1e-7,"google_maps_grounding_cost_per_query":0.007700000000000001},"list_pricing":{"input_cost_per_token":4.4e-6,"output_cost_per_token":0.000022000000000000003,"input_cost_per_audio_token":4.4e-6,"input_cost_per_image_token":4.4e-6,"cache_read_input_token_cost":2.2e-7,"search_context_cost_per_query":{"search_context_size_low":0.028,"search_context_size_high":0.028,"search_context_size_medium":0.028},"cache_creation_input_token_cost":4.125e-7,"output_cost_per_reasoning_token":0.000022000000000000003,"cache_read_input_audio_token_cost":2.2e-7,"google_maps_grounding_cost_per_query":0.015400000000000002},"discount":0.5,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":5},{"id":"~gemini-pro-latest","object":"model","created":1794364821,"owned_by":"google","mode":"chat","context_length":1048576,"capabilities":{"input_modalities":["audio","file","image","text","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"input_cost_per_audio_token":2e-6,"input_cost_per_image_token":2e-6,"cache_read_input_token_cost":1e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"cache_creation_input_token_cost":1.875e-7,"output_cost_per_reasoning_token":0.00001,"cache_read_input_audio_token_cost":1e-7,"google_maps_grounding_cost_per_query":0.007},"pricing_endpoint":"google/gemini-4-carbon","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":"gemini-4-carbon","endpoints":[{"id":"databricks/databricks-gemini-4-carbon","object":"model","created":1794364821,"owned_by":"databricks","model_name":"databricks-gemini-4-carbon","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":32768,"quantization":null,"retirement_date":null,"description":"Gemini 4 Carbon is Google's frontier model for complex reasoning, coding, and multimodal tasks. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["audio","file","image","text","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"cache_read_input_token_cost":2e-6,"cache_creation_input_token_cost":2e-6},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"cache_read_input_token_cost":2e-6,"cache_creation_input_token_cost":2e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"google/gemini-4-carbon","object":"model","created":1794326871,"owned_by":"google","model_name":"gemini-4-carbon","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":32768,"quantization":null,"retirement_date":null,"description":"Gemini 4 Carbon is a frontier Gemini 4 model from Google for coding, agentic and complex reasoning work.","source":null,"capabilities":{"input_modalities":["audio","file","image","text","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"input_cost_per_audio_token":2e-6,"input_cost_per_image_token":2e-6,"cache_read_input_token_cost":1e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"cache_creation_input_token_cost":1.875e-7,"output_cost_per_reasoning_token":0.00001,"cache_read_input_audio_token_cost":1e-7,"google_maps_grounding_cost_per_query":0.007},"list_pricing":{"input_cost_per_token":4e-6,"output_cost_per_token":0.00002,"input_cost_per_audio_token":4e-6,"input_cost_per_image_token":4e-6,"cache_read_input_token_cost":2e-7,"search_context_cost_per_query":{"search_context_size_low":0.028,"search_context_size_high":0.028,"search_context_size_medium":0.028},"cache_creation_input_token_cost":3.75e-7,"output_cost_per_reasoning_token":0.00002,"cache_read_input_audio_token_cost":2e-7,"google_maps_grounding_cost_per_query":0.014},"discount":0.5,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"vertex/gemini-4-carbon@eu","object":"model","created":1794326871,"owned_by":"vertex","model_name":"gemini-4-carbon","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":32768,"quantization":null,"retirement_date":null,"description":"Gemini 4 Carbon is a frontier Gemini 4 model from Google for coding, agentic and complex reasoning work.","source":null,"capabilities":{"input_modalities":["audio","file","image","text","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2.2e-6,"output_cost_per_token":0.000011000000000000001,"input_cost_per_audio_token":2.2e-6,"input_cost_per_image_token":2.2e-6,"cache_read_input_token_cost":1.1e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"cache_creation_input_token_cost":2.0625e-7,"output_cost_per_reasoning_token":0.000011000000000000001,"cache_read_input_audio_token_cost":1.1e-7,"google_maps_grounding_cost_per_query":0.007700000000000001},"list_pricing":{"input_cost_per_token":4.4e-6,"output_cost_per_token":0.000022000000000000003,"input_cost_per_audio_token":4.4e-6,"input_cost_per_image_token":4.4e-6,"cache_read_input_token_cost":2.2e-7,"search_context_cost_per_query":{"search_context_size_low":0.028,"search_context_size_high":0.028,"search_context_size_medium":0.028},"cache_creation_input_token_cost":4.125e-7,"output_cost_per_reasoning_token":0.000022000000000000003,"cache_read_input_audio_token_cost":2.2e-7,"google_maps_grounding_cost_per_query":0.015400000000000002},"discount":0.5,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"vertex/gemini-4-carbon","object":"model","created":1794326871,"owned_by":"vertex","model_name":"gemini-4-carbon","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":32768,"quantization":null,"retirement_date":null,"description":"Gemini 4 Carbon is a frontier Gemini 4 model from Google for coding, agentic and complex reasoning work.","source":null,"capabilities":{"input_modalities":["audio","file","image","text","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"input_cost_per_audio_token":2e-6,"input_cost_per_image_token":2e-6,"cache_read_input_token_cost":1e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"cache_creation_input_token_cost":1.875e-7,"output_cost_per_reasoning_token":0.00001,"cache_read_input_audio_token_cost":1e-7,"google_maps_grounding_cost_per_query":0.007},"list_pricing":{"input_cost_per_token":4e-6,"output_cost_per_token":0.00002,"input_cost_per_audio_token":4e-6,"input_cost_per_image_token":4e-6,"cache_read_input_token_cost":2e-7,"search_context_cost_per_query":{"search_context_size_low":0.028,"search_context_size_high":0.028,"search_context_size_medium":0.028},"cache_creation_input_token_cost":3.75e-7,"output_cost_per_reasoning_token":0.00002,"cache_read_input_audio_token_cost":2e-7,"google_maps_grounding_cost_per_query":0.014},"discount":0.5,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"vertex/gemini-4-carbon@us","object":"model","created":1794326871,"owned_by":"vertex","model_name":"gemini-4-carbon","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":32768,"quantization":null,"retirement_date":null,"description":"Gemini 4 Carbon is a frontier Gemini 4 model from Google for coding, agentic and complex reasoning work.","source":null,"capabilities":{"input_modalities":["audio","file","image","text","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2.2e-6,"output_cost_per_token":0.000011000000000000001,"input_cost_per_audio_token":2.2e-6,"input_cost_per_image_token":2.2e-6,"cache_read_input_token_cost":1.1e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"cache_creation_input_token_cost":2.0625e-7,"output_cost_per_reasoning_token":0.000011000000000000001,"cache_read_input_audio_token_cost":1.1e-7,"google_maps_grounding_cost_per_query":0.007700000000000001},"list_pricing":{"input_cost_per_token":4.4e-6,"output_cost_per_token":0.000022000000000000003,"input_cost_per_audio_token":4.4e-6,"input_cost_per_image_token":4.4e-6,"cache_read_input_token_cost":2.2e-7,"search_context_cost_per_query":{"search_context_size_low":0.028,"search_context_size_high":0.028,"search_context_size_medium":0.028},"cache_creation_input_token_cost":4.125e-7,"output_cost_per_reasoning_token":0.000022000000000000003,"cache_read_input_audio_token_cost":2.2e-7,"google_maps_grounding_cost_per_query":0.015400000000000002},"discount":0.5,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":5},{"id":"glimpse-1.0","object":"model","created":1794287531,"owned_by":"","mode":"chat","context_length":262144,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6e-7,"output_cost_per_token":3e-6,"cache_read_input_token_cost":6.000000000000001e-8},"pricing_endpoint":"together_ai/elorian-labs/glimpse-1.0","regions":[{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"together_ai/elorian-labs/glimpse-1.0","object":"model","created":1794287531,"owned_by":"together_ai","model_name":"elorian-labs/glimpse-1.0","context_length":262144,"max_input_tokens":262144,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6e-7,"output_cost_per_token":3e-6,"cache_read_input_token_cost":6.000000000000001e-8},"list_pricing":{"input_cost_per_token":6e-7,"output_cost_per_token":3e-6,"cache_read_input_token_cost":6.000000000000001e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":1},{"id":"inkling-2-small","object":"model","created":1794261847,"owned_by":"thinkingmachines","mode":"chat","context_length":1048576,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1e-6,"cache_read_input_token_cost":3e-8},"pricing_endpoint":"deepinfra/thinkingmachines/Inkling-2-Small","regions":[{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"cloudflare/@cf/thinkingmachines/inkling-2-small","object":"model","created":1794261847,"owned_by":"cloudflare","model_name":"@cf/thinkingmachines/inkling-2-small","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"Inkling 2 Small is an open-weight multimodal mixture-of-experts reasoning model from Thinking Machines Lab, with 17B active parameters out of 594B total.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1e-6,"cache_read_input_token_cost":1.0000000000000001e-7},"list_pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1e-6,"cache_read_input_token_cost":1.0000000000000001e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"deepinfra/thinkingmachines/Inkling-2-Small","object":"model","created":1794261847,"owned_by":"deepinfra","model_name":"thinkingmachines/Inkling-2-Small","context_length":1048576,"max_input_tokens":null,"max_output_tokens":null,"quantization":"fp4","retirement_date":null,"description":"Inkling 2 Small is an open-weight multimodal mixture-of-experts reasoning model from Thinking Machines Lab, with 17B active parameters out of 594B total.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1e-6,"cache_read_input_token_cost":3e-8},"list_pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1e-6,"cache_read_input_token_cost":3e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"nebius/thinkingmachines/Inkling-2-Small","object":"model","created":1794261847,"owned_by":"nebius","model_name":"thinkingmachines/Inkling-2-Small","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":null,"quantization":"fp4","retirement_date":null,"description":"Inkling 2 Small is an open-weight multimodal mixture-of-experts reasoning model from Thinking Machines Lab, with 17B active parameters out of 594B total.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1e-6,"cache_read_input_token_cost":3e-7},"list_pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1e-6,"cache_read_input_token_cost":3e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"together_ai/thinkingmachines/Inkling-2-Small","object":"model","created":1794261847,"owned_by":"together_ai","model_name":"thinkingmachines/Inkling-2-Small","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"Inkling 2 Small is an open-weight multimodal mixture-of-experts reasoning model from Thinking Machines Lab, with 17B active parameters out of 594B total.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1e-6,"cache_read_input_token_cost":3.0000000000000004e-8},"list_pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1e-6,"cache_read_input_token_cost":3.0000000000000004e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":4},{"id":"claude-fable-5-2","object":"model","created":1794253781,"owned_by":"anthropic","mode":"chat","context_length":1000000,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":8e-6,"output_cost_per_token":0.00004,"provider_specific_entry":{"us":1.1,"fast":2.0},"cache_read_input_token_cost":2e-7,"input_cost_per_token_batches":4e-6,"output_cost_per_token_batches":0.00002,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":0.00001,"cache_read_input_token_cost_batches":1e-7,"cache_creation_input_token_cost_above_1hr":0.000016},"pricing_endpoint":"anthropic/claude-fable-5-2","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"anthropic/claude-fable-5-2","object":"model","created":1794253781,"owned_by":"anthropic","model_name":"claude-fable-5-2","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Fable 5.2 is Anthropic's most capable model for the most demanding technical work, with gains over Fable 5.1 in coding, reasoning, and vision.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":8e-6,"output_cost_per_token":0.00004,"provider_specific_entry":{"us":1.1,"fast":2.0},"cache_read_input_token_cost":2e-7,"input_cost_per_token_batches":4e-6,"output_cost_per_token_batches":0.00002,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":0.00001,"cache_read_input_token_cost_batches":1e-7,"cache_creation_input_token_cost_above_1hr":0.000016},"list_pricing":{"input_cost_per_token":8e-6,"output_cost_per_token":0.00004,"provider_specific_entry":{"us":1.1,"fast":2.0},"cache_read_input_token_cost":2e-7,"input_cost_per_token_batches":4e-6,"output_cost_per_token_batches":0.00002,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":0.00001,"cache_read_input_token_cost_batches":1e-7,"cache_creation_input_token_cost_above_1hr":0.000016},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null},{"id":"vertex/claude-fable-5-2@eu","object":"model","created":1794253204,"owned_by":"vertex","model_name":"claude-fable-5-2","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":8.8e-6,"output_cost_per_token":0.000044000000000000006,"cache_read_input_token_cost":2.2e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":0.000011000000000000001,"cache_creation_input_token_cost_above_1hr":0.0000176},"list_pricing":{"input_cost_per_token":8.8e-6,"output_cost_per_token":0.000044000000000000006,"cache_read_input_token_cost":2.2e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":0.000011000000000000001,"cache_creation_input_token_cost_above_1hr":0.0000176},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"vertex/claude-fable-5-2","object":"model","created":1794253204,"owned_by":"vertex","model_name":"claude-fable-5-2","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":8e-6,"output_cost_per_token":0.00004,"cache_read_input_token_cost":2e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":0.00001,"cache_creation_input_token_cost_above_1hr":0.000016},"list_pricing":{"input_cost_per_token":8e-6,"output_cost_per_token":0.00004,"cache_read_input_token_cost":2e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":0.00001,"cache_creation_input_token_cost_above_1hr":0.000016},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"vertex/claude-fable-5-2@us","object":"model","created":1794253204,"owned_by":"vertex","model_name":"claude-fable-5-2","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":8.8e-6,"output_cost_per_token":0.000044000000000000006,"cache_read_input_token_cost":2.2e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":0.000011000000000000001,"cache_creation_input_token_cost_above_1hr":0.0000176},"list_pricing":{"input_cost_per_token":8.8e-6,"output_cost_per_token":0.000044000000000000006,"cache_read_input_token_cost":2.2e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":0.000011000000000000001,"cache_creation_input_token_cost_above_1hr":0.0000176},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":4},{"id":"~claude-fable-latest","object":"model","created":1794253781,"owned_by":"anthropic","mode":"chat","context_length":1000000,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":8e-6,"output_cost_per_token":0.00004,"provider_specific_entry":{"us":1.1,"fast":2.0},"cache_read_input_token_cost":2e-7,"input_cost_per_token_batches":4e-6,"output_cost_per_token_batches":0.00002,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":0.00001,"cache_read_input_token_cost_batches":1e-7,"cache_creation_input_token_cost_above_1hr":0.000016},"pricing_endpoint":"anthropic/claude-fable-5-2","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":"claude-fable-5-2","endpoints":[{"id":"anthropic/claude-fable-5-2","object":"model","created":1794253781,"owned_by":"anthropic","model_name":"claude-fable-5-2","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Fable 5.2 is Anthropic's most capable model for the most demanding technical work, with gains over Fable 5.1 in coding, reasoning, and vision.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":8e-6,"output_cost_per_token":0.00004,"provider_specific_entry":{"us":1.1,"fast":2.0},"cache_read_input_token_cost":2e-7,"input_cost_per_token_batches":4e-6,"output_cost_per_token_batches":0.00002,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":0.00001,"cache_read_input_token_cost_batches":1e-7,"cache_creation_input_token_cost_above_1hr":0.000016},"list_pricing":{"input_cost_per_token":8e-6,"output_cost_per_token":0.00004,"provider_specific_entry":{"us":1.1,"fast":2.0},"cache_read_input_token_cost":2e-7,"input_cost_per_token_batches":4e-6,"output_cost_per_token_batches":0.00002,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":0.00001,"cache_read_input_token_cost_batches":1e-7,"cache_creation_input_token_cost_above_1hr":0.000016},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null},{"id":"vertex/claude-fable-5-2@eu","object":"model","created":1794253204,"owned_by":"vertex","model_name":"claude-fable-5-2","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":8.8e-6,"output_cost_per_token":0.000044000000000000006,"cache_read_input_token_cost":2.2e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":0.000011000000000000001,"cache_creation_input_token_cost_above_1hr":0.0000176},"list_pricing":{"input_cost_per_token":8.8e-6,"output_cost_per_token":0.000044000000000000006,"cache_read_input_token_cost":2.2e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":0.000011000000000000001,"cache_creation_input_token_cost_above_1hr":0.0000176},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"vertex/claude-fable-5-2","object":"model","created":1794253204,"owned_by":"vertex","model_name":"claude-fable-5-2","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":8e-6,"output_cost_per_token":0.00004,"cache_read_input_token_cost":2e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":0.00001,"cache_creation_input_token_cost_above_1hr":0.000016},"list_pricing":{"input_cost_per_token":8e-6,"output_cost_per_token":0.00004,"cache_read_input_token_cost":2e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":0.00001,"cache_creation_input_token_cost_above_1hr":0.000016},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"vertex/claude-fable-5-2@us","object":"model","created":1794253204,"owned_by":"vertex","model_name":"claude-fable-5-2","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":8.8e-6,"output_cost_per_token":0.000044000000000000006,"cache_read_input_token_cost":2.2e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":0.000011000000000000001,"cache_creation_input_token_cost_above_1hr":0.0000176},"list_pricing":{"input_cost_per_token":8.8e-6,"output_cost_per_token":0.000044000000000000006,"cache_read_input_token_cost":2.2e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":0.000011000000000000001,"cache_creation_input_token_cost_above_1hr":0.0000176},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":4},{"id":"kimi-k3.1","object":"model","created":1794011533,"owned_by":"moonshot","mode":"chat","context_length":868928,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4.4e-6,"output_cost_per_token":0.000022,"input_cost_per_token_flex":2.2e-6,"output_cost_per_token_flex":0.000011,"cache_read_input_token_cost":2.2e-7,"input_cost_per_token_priority":7.7e-6,"output_cost_per_token_priority":0.0000385,"cache_creation_input_token_cost":5.5e-6,"cache_read_input_token_cost_flex":1.1e-7,"cache_creation_input_token_cost_flex":2.75e-6,"cache_read_input_token_cost_priority":3.85e-7,"cache_creation_input_token_cost_priority":9.625e-6},"pricing_endpoint":"amazon/moonshotai.kimi-k3.1","regions":[{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"amazon/moonshotai.kimi-k3.1","object":"model","created":1794011533,"owned_by":"amazon","model_name":"moonshotai.kimi-k3.1","context_length":868928,"max_input_tokens":868928,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4.4e-6,"output_cost_per_token":0.000022,"input_cost_per_token_flex":2.2e-6,"output_cost_per_token_flex":0.000011,"cache_read_input_token_cost":2.2e-7,"input_cost_per_token_priority":7.7e-6,"output_cost_per_token_priority":0.0000385,"cache_creation_input_token_cost":5.5e-6,"cache_read_input_token_cost_flex":1.1e-7,"cache_creation_input_token_cost_flex":2.75e-6,"cache_read_input_token_cost_priority":3.85e-7,"cache_creation_input_token_cost_priority":9.625e-6},"list_pricing":{"input_cost_per_token":4.4e-6,"output_cost_per_token":0.000022,"input_cost_per_token_flex":2.2e-6,"output_cost_per_token_flex":0.000011,"cache_read_input_token_cost":2.2e-7,"input_cost_per_token_priority":7.7e-6,"output_cost_per_token_priority":0.0000385,"cache_creation_input_token_cost":5.5e-6,"cache_read_input_token_cost_flex":1.1e-7,"cache_creation_input_token_cost_flex":2.75e-6,"cache_read_input_token_cost_priority":3.85e-7,"cache_creation_input_token_cost_priority":9.625e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/moonshotai.kimi-k3.1@us","object":"model","created":1794011533,"owned_by":"amazon","model_name":"moonshotai.kimi-k3.1","context_length":868928,"max_input_tokens":868928,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4.4e-6,"output_cost_per_token":0.000022,"input_cost_per_token_flex":2.2e-6,"output_cost_per_token_flex":0.000011,"cache_read_input_token_cost":2.2e-7,"input_cost_per_token_priority":7.7e-6,"output_cost_per_token_priority":0.0000385,"cache_creation_input_token_cost":5.5e-6,"cache_read_input_token_cost_flex":1.1e-7,"cache_creation_input_token_cost_flex":2.75e-6,"cache_read_input_token_cost_priority":3.85e-7,"cache_creation_input_token_cost_priority":9.625e-6},"list_pricing":{"input_cost_per_token":4.4e-6,"output_cost_per_token":0.000022,"input_cost_per_token_flex":2.2e-6,"output_cost_per_token_flex":0.000011,"cache_read_input_token_cost":2.2e-7,"input_cost_per_token_priority":7.7e-6,"output_cost_per_token_priority":0.0000385,"cache_creation_input_token_cost":5.5e-6,"cache_read_input_token_cost_flex":1.1e-7,"cache_creation_input_token_cost_flex":2.75e-6,"cache_read_input_token_cost_priority":3.85e-7,"cache_creation_input_token_cost_priority":9.625e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"kimi-k3.1-pro","object":"model","created":1793988020,"owned_by":"moonshot","mode":"chat","context_length":1048576,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.3e-6,"output_cost_per_token":6.5000000000000004e-6,"cache_read_input_token_cost":1.3000000000000003e-7},"pricing_endpoint":"qwen/kimi-k3.1-pro","regions":[{"code":"ap","name":"Asia"},{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"databricks/databricks-kimi-k3-1-pro","object":"model","created":1793988020,"owned_by":"databricks","model_name":"databricks-kimi-k3-1-pro","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"Kimi K3.1 Pro is a 3T-class open-weight model in the Kimi K3.1 series developed by Moonshot AI with native vision capabilities and a 1M-token context window, with substantial improvements in coding, 3D creation, financial research, and other agentic capabilities.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"input_dbu_cost_per_token":0.000028571,"output_dbu_cost_per_token":0.000142857,"cache_read_input_token_cost":2e-7,"cache_creation_input_token_cost":2e-6},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"input_dbu_cost_per_token":0.000028571,"output_dbu_cost_per_token":0.000142857,"cache_read_input_token_cost":2e-7,"cache_creation_input_token_cost":2e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"arkanecloud/moonshotai/Kimi-K3.1-Pro","object":"model","created":1793900129,"owned_by":"arkanecloud","model_name":"moonshotai/Kimi-K3.1-Pro","context_length":1000000,"max_input_tokens":null,"max_output_tokens":500000,"quantization":null,"retirement_date":null,"description":"Kimi K3.1 Pro is Moonshot AI's flagship open-weight multimodal reasoning model and a post-trained successor to Kimi K3, with a 1M-token context window.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"cache_read_input_token_cost":2e-7},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"cache_read_input_token_cost":2e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"},{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"tensorx/moonshotai/kimi-k3.1-pro","object":"model","created":1793855556,"owned_by":"tensorx","model_name":"moonshotai/kimi-k3.1-pro","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":64000,"quantization":"fp4","retirement_date":null,"description":"Served by TensorX at mxfp4 quantization.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"cache_read_input_token_cost":7.5e-7},"list_pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"cache_read_input_token_cost":7.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"deepinfra/moonshotai/Kimi-K3.1-Pro","object":"model","created":1792778188,"owned_by":"deepinfra","model_name":"moonshotai/Kimi-K3.1-Pro","context_length":1048576,"max_input_tokens":null,"max_output_tokens":null,"quantization":"bf16","retirement_date":null,"description":"Kimi K3.1 Pro is Moonshot AI's flagship open-weight multimodal reasoning model and a post-trained successor to Kimi K3, with a 1M-token context window.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"cache_read_input_token_cost":2.0000000000000002e-7},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"cache_read_input_token_cost":2.0000000000000002e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"moonshot/kimi-k3.1-pro","object":"model","created":1792778188,"owned_by":"moonshot","model_name":"kimi-k3.1-pro","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":null,"quantization":"fp4","retirement_date":null,"description":"Kimi K3.1 Pro is Moonshot AI's flagship open-weight multimodal reasoning model and a post-trained successor to Kimi K3, with a 1M-token context window.","source":null,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"cache_read_input_token_cost":2e-7,"cache_creation_input_token_cost":2e-6,"cache_creation_input_token_cost_above_1hr":4e-6},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"cache_read_input_token_cost":2e-7,"cache_creation_input_token_cost":2e-6,"cache_creation_input_token_cost_above_1hr":4e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"ap","name":"Asia"}],"zero_data_retention":false,"alias_of":null},{"id":"nebius/moonshotai/Kimi-K3.1-Pro","object":"model","created":1792778188,"owned_by":"nebius","model_name":"moonshotai/Kimi-K3.1-Pro","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":null,"quantization":"fp4","retirement_date":null,"description":"Kimi K3.1 Pro is Moonshot AI's flagship open-weight multimodal reasoning model and a post-trained successor to Kimi K3, with a 1M-token context window.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"cache_read_input_token_cost":2e-6},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"cache_read_input_token_cost":2e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"qwen/kimi-k3.1-pro","object":"model","created":1792778188,"owned_by":"qwen","model_name":"kimi-k3.1-pro","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"Kimi-K3.1-Pro is the first model in Moonshot AI's new K3.1 series and its most capable 3T-class open-weight model to date. It is a post-trained version of Kimi K3 with substantially larger post-training compute, featuring a 1-million-token context window and native visual understanding (text and image input, text output). Through large-scale joint reinforcement learning across hundreds of downstream domains, it delivers significant gains in coding, 3D creation, financial research, and other long-horizon agentic tasks: scoring 65.7% on Terminal-Bench 4.0, achieving a state-of-the-art 64.4 on OfficeQA Pro v2, and reducing claim-level hallucination rate from 23.4% (K3) to 8.3%. Its overall intelligence approaches leading closed-source frontier models.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.3e-6,"output_cost_per_token":6.5000000000000004e-6,"cache_read_input_token_cost":1.3000000000000003e-7},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"cache_read_input_token_cost":2.0000000000000002e-7},"discount":0.35,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null},{"id":"together_ai/moonshotai/Kimi-K3.1-Pro","object":"model","created":1792778188,"owned_by":"together_ai","model_name":"moonshotai/Kimi-K3.1-Pro","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"Kimi K3.1 Pro is Moonshot AI's flagship open-weight multimodal reasoning model and a post-trained successor to Kimi K3, with a 1M-token context window.","source":null,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"cache_read_input_token_cost":2.0000000000000002e-7},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"cache_read_input_token_cost":2.0000000000000002e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":8},{"id":"deepseek-v4.1-flash-1017-ultrafast","object":"model","created":1793855556,"owned_by":"deepseek","mode":"chat","context_length":1048576,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.4e-6,"output_cost_per_token":9.6e-6,"cache_read_input_token_cost":4.8e-8},"pricing_endpoint":"fireworks_ai/accounts/fireworks/routers/deepseek-v4p1-flash-1017-ultrafast","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"fireworks_ai/accounts/fireworks/routers/deepseek-v4p1-flash-1017-ultrafast","object":"model","created":1793855556,"owned_by":"fireworks_ai","model_name":"accounts/fireworks/routers/deepseek-v4p1-flash-1017-ultrafast","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":393216,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.4e-6,"output_cost_per_token":9.6e-6,"cache_read_input_token_cost":4.8e-8},"list_pricing":{"input_cost_per_token":2.4e-6,"output_cost_per_token":9.6e-6,"cache_read_input_token_cost":4.8e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"ripple-65b-preview","object":"model","created":1793818990,"owned_by":"","mode":"chat","context_length":131072,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.0000000000000002e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":2e-8},"pricing_endpoint":"together_ai/ricursive-ai/Ripple-65B-Preview","regions":[{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"together_ai/ricursive-ai/Ripple-65B-Preview","object":"model","created":1793818990,"owned_by":"together_ai","model_name":"ricursive-ai/Ripple-65B-Preview","context_length":131072,"max_input_tokens":131072,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"Ripple-65B-Preview by ricursiveAI, a 65B model with native tool calling, served in BF16.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.0000000000000002e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":2e-8},"list_pricing":{"input_cost_per_token":2.0000000000000002e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":2e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":1},{"id":"hy4","object":"model","created":1793769145,"owned_by":"tencent","mode":"chat","context_length":1000000,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":8.34e-7,"output_cost_per_token":2.501e-6,"cache_read_input_token_cost":4.2e-8,"input_cost_per_token_cache_hit":4.2e-8},"pricing_endpoint":"tencent/hy4","regions":[{"code":"ap","name":"Asia"}],"alias_of":null,"endpoints":[{"id":"tencent/hy4","object":"model","created":1793769145,"owned_by":"tencent","model_name":"hy4","context_length":1000000,"max_input_tokens":960000,"max_output_tokens":64000,"quantization":null,"retirement_date":null,"description":"The official release of Hy4 delivers comprehensive and substantial improvements over Hy4 Preview, with particularly strong gains in agentic capabilities and performance across a wide range of long-horizon, real-world productivity...","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":8.34e-7,"output_cost_per_token":2.501e-6,"cache_read_input_token_cost":4.2e-8,"input_cost_per_token_cache_hit":4.2e-8},"list_pricing":{"input_cost_per_token":8.34e-7,"output_cost_per_token":2.501e-6,"cache_read_input_token_cost":4.2e-8,"input_cost_per_token_cache_hit":4.2e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"ap","name":"Asia"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"gemini-3.6-flash","object":"model","created":1793739015,"owned_by":"google","mode":"chat","context_length":1048576,"capabilities":{"input_modalities":["text","image","video","audio","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":7.5e-7,"output_cost_per_token":3.75e-6,"input_cost_per_token_flex":3.75e-7,"input_cost_per_audio_token":7.5e-7,"input_cost_per_image_token":7.5e-7,"output_cost_per_token_flex":1.875e-6,"cache_read_input_token_cost":7.5e-8,"input_cost_per_token_priority":1.35e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":6.75e-6,"cache_creation_input_token_cost":4.16666666666667e-8,"output_cost_per_reasoning_token":3.75e-6,"cache_read_input_token_cost_flex":3.75e-8,"cache_read_input_audio_token_cost":7.5e-8,"cache_read_input_token_cost_priority":1.35e-7,"google_maps_grounding_cost_per_query":0.014},"pricing_endpoint":"google/gemini-3.6-flash","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"databricks/databricks-gemini-3-6-flash@eu","object":"model","created":1793739015,"owned_by":"databricks","model_name":"databricks-gemini-3-6-flash","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"Gemini 3.6 Flash is Google's next generation fast and efficient model. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["text","image","video","audio","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":7.5e-7,"output_cost_per_token":3.75e-6,"input_dbu_cost_per_token":0.000010714,"output_dbu_cost_per_token":0.000053571,"cache_read_input_token_cost":7.5e-8,"cache_creation_input_token_cost":7.5e-7,"cache_creation_input_token_cost_priority":1.35e-6},"list_pricing":{"input_cost_per_token":7.5e-7,"output_cost_per_token":3.75e-6,"input_dbu_cost_per_token":0.000010714,"output_dbu_cost_per_token":0.000053571,"cache_read_input_token_cost":7.5e-8,"cache_creation_input_token_cost":7.5e-7,"cache_creation_input_token_cost_priority":1.35e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"databricks/databricks-gemini-3-6-flash","object":"model","created":1793739015,"owned_by":"databricks","model_name":"databricks-gemini-3-6-flash","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"Gemini 3.6 Flash is Google's next generation fast and efficient model. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["text","image","video","audio","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":7.5e-7,"output_cost_per_token":3.75e-6,"input_dbu_cost_per_token":0.000010714,"output_dbu_cost_per_token":0.000053571,"cache_read_input_token_cost":7.5e-8,"cache_creation_input_token_cost":7.5e-7,"cache_creation_input_token_cost_priority":1.35e-6},"list_pricing":{"input_cost_per_token":7.5e-7,"output_cost_per_token":3.75e-6,"input_dbu_cost_per_token":0.000010714,"output_dbu_cost_per_token":0.000053571,"cache_read_input_token_cost":7.5e-8,"cache_creation_input_token_cost":7.5e-7,"cache_creation_input_token_cost_priority":1.35e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"google/gemini-3.6-flash","object":"model","created":1784646733,"owned_by":"google","model_name":"gemini-3.6-flash","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development.","source":null,"capabilities":{"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":7.5e-7,"output_cost_per_token":3.75e-6,"input_cost_per_token_flex":3.75e-7,"input_cost_per_audio_token":7.5e-7,"input_cost_per_image_token":7.5e-7,"output_cost_per_token_flex":1.875e-6,"cache_read_input_token_cost":7.5e-8,"input_cost_per_token_priority":1.35e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":6.75e-6,"cache_creation_input_token_cost":4.16666666666667e-8,"output_cost_per_reasoning_token":3.75e-6,"cache_read_input_token_cost_flex":3.75e-8,"cache_read_input_audio_token_cost":7.5e-8,"cache_read_input_token_cost_priority":1.35e-7,"google_maps_grounding_cost_per_query":0.014},"list_pricing":{"input_cost_per_token":7.5e-7,"output_cost_per_token":3.75e-6,"input_cost_per_token_flex":3.75e-7,"input_cost_per_audio_token":7.5e-7,"input_cost_per_image_token":7.5e-7,"output_cost_per_token_flex":1.875e-6,"cache_read_input_token_cost":7.5e-8,"input_cost_per_token_priority":1.35e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":6.75e-6,"cache_creation_input_token_cost":4.16666666666667e-8,"output_cost_per_reasoning_token":3.75e-6,"cache_read_input_token_cost_flex":3.75e-8,"cache_read_input_audio_token_cost":7.5e-8,"cache_read_input_token_cost_priority":1.35e-7,"google_maps_grounding_cost_per_query":0.014},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"vertex/gemini-3.6-flash@eu","object":"model","created":1784646733,"owned_by":"vertex","model_name":"gemini-3.6-flash","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development.","source":null,"capabilities":{"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":8.25e-7,"output_cost_per_token":4.125e-6,"input_cost_per_token_flex":4.125e-7,"input_cost_per_audio_token":8.25e-7,"input_cost_per_image_token":8.25e-7,"output_cost_per_token_flex":2.0625e-6,"cache_read_input_token_cost":8.25e-8,"input_cost_per_token_priority":1.4850000000000002e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":7.425e-6,"cache_creation_input_token_cost":4.583333333333337e-8,"output_cost_per_reasoning_token":4.125e-6,"cache_read_input_token_cost_flex":4.125e-8,"cache_read_input_audio_token_cost":8.25e-8,"cache_read_input_token_cost_priority":1.485e-7,"google_maps_grounding_cost_per_query":0.015400000000000002},"list_pricing":{"input_cost_per_token":8.25e-7,"output_cost_per_token":4.125e-6,"input_cost_per_token_flex":4.125e-7,"input_cost_per_audio_token":8.25e-7,"input_cost_per_image_token":8.25e-7,"output_cost_per_token_flex":2.0625e-6,"cache_read_input_token_cost":8.25e-8,"input_cost_per_token_priority":1.4850000000000002e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":7.425e-6,"cache_creation_input_token_cost":4.583333333333337e-8,"output_cost_per_reasoning_token":4.125e-6,"cache_read_input_token_cost_flex":4.125e-8,"cache_read_input_audio_token_cost":8.25e-8,"cache_read_input_token_cost_priority":1.485e-7,"google_maps_grounding_cost_per_query":0.015400000000000002},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"vertex/gemini-3.6-flash","object":"model","created":1784646733,"owned_by":"vertex","model_name":"gemini-3.6-flash","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development.","source":null,"capabilities":{"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":7.5e-7,"output_cost_per_token":3.75e-6,"input_cost_per_token_flex":3.75e-7,"input_cost_per_audio_token":7.5e-7,"input_cost_per_image_token":7.5e-7,"output_cost_per_token_flex":1.875e-6,"cache_read_input_token_cost":7.5e-8,"input_cost_per_token_priority":1.35e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":6.75e-6,"cache_creation_input_token_cost":4.16666666666667e-8,"output_cost_per_reasoning_token":3.75e-6,"cache_read_input_token_cost_flex":3.75e-8,"cache_read_input_audio_token_cost":7.5e-8,"cache_read_input_token_cost_priority":1.35e-7,"google_maps_grounding_cost_per_query":0.014},"list_pricing":{"input_cost_per_token":7.5e-7,"output_cost_per_token":3.75e-6,"input_cost_per_token_flex":3.75e-7,"input_cost_per_audio_token":7.5e-7,"input_cost_per_image_token":7.5e-7,"output_cost_per_token_flex":1.875e-6,"cache_read_input_token_cost":7.5e-8,"input_cost_per_token_priority":1.35e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":6.75e-6,"cache_creation_input_token_cost":4.16666666666667e-8,"output_cost_per_reasoning_token":3.75e-6,"cache_read_input_token_cost_flex":3.75e-8,"cache_read_input_audio_token_cost":7.5e-8,"cache_read_input_token_cost_priority":1.35e-7,"google_maps_grounding_cost_per_query":0.014},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"vertex/gemini-3.6-flash@us","object":"model","created":1784646733,"owned_by":"vertex","model_name":"gemini-3.6-flash","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development.","source":null,"capabilities":{"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":8.25e-7,"output_cost_per_token":4.125e-6,"input_cost_per_token_flex":4.125e-7,"input_cost_per_audio_token":8.25e-7,"input_cost_per_image_token":8.25e-7,"output_cost_per_token_flex":2.0625e-6,"cache_read_input_token_cost":8.25e-8,"input_cost_per_token_priority":1.4850000000000002e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":7.425e-6,"cache_creation_input_token_cost":4.583333333333337e-8,"output_cost_per_reasoning_token":4.125e-6,"cache_read_input_token_cost_flex":4.125e-8,"cache_read_input_audio_token_cost":8.25e-8,"cache_read_input_token_cost_priority":1.485e-7,"google_maps_grounding_cost_per_query":0.015400000000000002},"list_pricing":{"input_cost_per_token":8.25e-7,"output_cost_per_token":4.125e-6,"input_cost_per_token_flex":4.125e-7,"input_cost_per_audio_token":8.25e-7,"input_cost_per_image_token":8.25e-7,"output_cost_per_token_flex":2.0625e-6,"cache_read_input_token_cost":8.25e-8,"input_cost_per_token_priority":1.4850000000000002e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":7.425e-6,"cache_creation_input_token_cost":4.583333333333337e-8,"output_cost_per_reasoning_token":4.125e-6,"cache_read_input_token_cost_flex":4.125e-8,"cache_read_input_audio_token_cost":8.25e-8,"cache_read_input_token_cost_priority":1.485e-7,"google_maps_grounding_cost_per_query":0.015400000000000002},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":6},{"id":"glm-5.3-flashx-legal","object":"model","created":1793626154,"owned_by":"zai","mode":"chat","context_length":1048576,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.7e-7,"output_cost_per_token":1.25e-6,"cache_read_input_token_cost":7.5e-8},"pricing_endpoint":"zai/glm-5.3-flashx-legal","regions":[{"code":"ap","name":"Asia"}],"alias_of":null,"endpoints":[{"id":"zai/glm-5.3-flashx-legal","object":"model","created":1793626154,"owned_by":"zai","model_name":"glm-5.3-flashx-legal","context_length":1048576,"max_input_tokens":null,"max_output_tokens":131072,"quantization":"fp8","retirement_date":null,"description":"GLM-5.3-FlashX-Legal (GLM-Legal) is Z.ai's legal-domain variant of GLM-5.3-FlashX, a native multimodal model that accepts text, image, and video input and produces text.","source":null,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.7e-7,"output_cost_per_token":1.25e-6,"cache_read_input_token_cost":7.5e-8},"list_pricing":{"input_cost_per_token":3.7e-7,"output_cost_per_token":1.25e-6,"cache_read_input_token_cost":7.5e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"ap","name":"Asia"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"deepseek-v4-flash-0731","object":"model","created":1793250768,"owned_by":"deepseek","mode":"chat","context_length":1048576,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6.000000000000001e-8,"output_cost_per_token":1.8e-7,"cache_read_input_token_cost":1.5000000000000002e-8},"pricing_endpoint":"deepinfra/deepseek-ai/DeepSeek-V4-Flash-0731","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"arkanecloud/deepseek-ai/DeepSeek-V4-Flash-0731","object":"model","created":1793250768,"owned_by":"arkanecloud","model_name":"deepseek-ai/DeepSeek-V4-Flash-0731","context_length":1048576,"max_input_tokens":null,"max_output_tokens":393216,"quantization":null,"retirement_date":null,"description":"DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":4e-7,"cache_read_input_token_cost":5e-8},"list_pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":4e-7,"cache_read_input_token_cost":5e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null},{"id":"sference/deepseek-ai/DeepSeek-V4-Flash-0731","object":"model","created":1792636080,"owned_by":"sference","model_name":"deepseek-ai/DeepSeek-V4-Flash-0731","context_length":1048576,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.8e-7,"output_cost_per_token":5.6e-7,"cache_read_input_token_cost":7e-8},"list_pricing":{"input_cost_per_token":2.8e-7,"output_cost_per_token":5.6e-7,"cache_read_input_token_cost":7e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"greenpt/deepseek-v4-flash-0731","object":"model","created":1791839241,"owned_by":"greenpt","model_name":"deepseek-v4-flash-0731","context_length":1000000,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5419606029065959e-7,"output_cost_per_token":3.8549015072664893e-7,"cache_read_input_token_cost":4.405601722590274e-8},"list_pricing":{"input_cost_per_token":1.5419606029065959e-7,"output_cost_per_token":3.8549015072664893e-7,"cache_read_input_token_cost":4.405601722590274e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"tensorx/deepseek/deepseek-v4-flash-0731","object":"model","created":1787003349,"owned_by":"tensorx","model_name":"deepseek/deepseek-v4-flash-0731","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":64000,"quantization":"fp4","retirement_date":null,"description":"Served by TensorX at fp4 quantization.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.5e-7,"output_cost_per_token":3e-7,"cache_read_input_token_cost":6.25e-8},"list_pricing":{"input_cost_per_token":2.5e-7,"output_cost_per_token":3e-7,"cache_read_input_token_cost":6.25e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"flexai/DeepSeek-V4-Flash-0731@eu","object":"model","created":1786684194,"owned_by":"flexai","model_name":"DeepSeek-V4-Flash-0731","context_length":1048576,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.3e-7,"output_cost_per_token":2.6e-7,"cache_read_input_token_cost":1.95e-8},"list_pricing":{"input_cost_per_token":1.3e-7,"output_cost_per_token":2.6e-7,"cache_read_input_token_cost":1.95e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"flexai/DeepSeek-V4-Flash-0731","object":"model","created":1786684194,"owned_by":"flexai","model_name":"DeepSeek-V4-Flash-0731","context_length":1048576,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.3e-7,"output_cost_per_token":2.6e-7,"cache_read_input_token_cost":1.95e-8},"list_pricing":{"input_cost_per_token":1.3e-7,"output_cost_per_token":2.6e-7,"cache_read_input_token_cost":1.95e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"scaleway/deepseek-v4-flash-0731","object":"model","created":1786376637,"owned_by":"scaleway","model_name":"deepseek-v4-flash-0731","context_length":256000,"max_input_tokens":null,"max_output_tokens":32768,"quantization":null,"retirement_date":null,"description":"DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4.405601722590274e-7,"output_cost_per_token":8.811203445180548e-7,"cache_read_input_token_cost":8.811203445180547e-8},"list_pricing":{"input_cost_per_token":4.405601722590274e-7,"output_cost_per_token":8.811203445180548e-7,"cache_read_input_token_cost":8.811203445180547e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"cloudflare/@cf/deepseek-ai/deepseek-v4-flash-0731","object":"model","created":1785478908,"owned_by":"cloudflare","model_name":"@cf/deepseek-ai/deepseek-v4-flash-0731","context_length":1048576,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4.4e-7,"output_cost_per_token":1.32e-6,"cache_read_input_token_cost":1.4e-8},"list_pricing":{"input_cost_per_token":4.4e-7,"output_cost_per_token":1.32e-6,"cache_read_input_token_cost":1.4e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"deepinfra/deepseek-ai/DeepSeek-V4-Flash-0731","object":"model","created":1785478908,"owned_by":"deepinfra","model_name":"deepseek-ai/DeepSeek-V4-Flash-0731","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":384000,"quantization":"fp8","retirement_date":null,"description":"DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6.000000000000001e-8,"output_cost_per_token":1.8e-7,"cache_read_input_token_cost":1.5000000000000002e-8},"list_pricing":{"input_cost_per_token":6.000000000000001e-8,"output_cost_per_token":1.8e-7,"cache_read_input_token_cost":1.5000000000000002e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"qwen/deepseek-v4-flash-0731","object":"model","created":1785478908,"owned_by":"qwen","model_name":"deepseek-v4-flash-0731","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":393216,"quantization":null,"retirement_date":null,"description":"A highly efficient, lightweight MoE model with 284 billion parameters in total and 13 billion activated parameters, natively supporting context windows of up to one million tokens. It offers fast inference speed, low latency, and cost-effective invocation, delivering well-balanced overall performance. Designed for high-concurrency, lightweight workloads, it is ideally suited for common, essential use cases such as everyday dialogue, content creation, basic RAG applications, and batch text processing.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.4300000000000002e-7,"output_cost_per_token":4.2900000000000004e-7,"cache_read_input_token_cost":1.4299999999999999e-8},"list_pricing":{"input_cost_per_token":2.2e-7,"output_cost_per_token":6.6e-7,"cache_read_input_token_cost":2.2e-8},"discount":0.35,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":10},{"id":"deepseek-v4.1-flash-1017","object":"model","created":1793250768,"owned_by":"deepseek","mode":"chat","context_length":1048576,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":9.749999999999999e-8,"output_cost_per_token":3.8999999999999997e-7,"web_search_cost_per_call":0.00037271715,"cache_read_input_token_cost":1.95e-9},"pricing_endpoint":"qwen/deepseek-v4.1-flash-1017","regions":[{"code":"ap","name":"Asia"},{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"arkanecloud/deepseek-ai/DeepSeek-V4.1-Flash-1017","object":"model","created":1793250768,"owned_by":"arkanecloud","model_name":"deepseek-ai/DeepSeek-V4.1-Flash-1017","context_length":1048576,"max_input_tokens":null,"max_output_tokens":393216,"quantization":null,"retirement_date":null,"description":"DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the deepseek-flash API model name.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1.2e-6,"cache_read_input_token_cost":7.5e-8},"list_pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1.2e-6,"cache_read_input_token_cost":7.5e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null},{"id":"tencent/deepseek-v4.1-flash-1017","object":"model","created":1793077988,"owned_by":"tencent","model_name":"deepseek-v4.1-flash-1017","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":384000,"quantization":null,"retirement_date":null,"description":"DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the deepseek-flash API model name.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":3e-9},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":3e-9},"discount":null,"discount_ends_at":null,"regions":[{"code":"ap","name":"Asia"}],"zero_data_retention":true,"alias_of":null},{"id":"flexai/DeepSeek-V4.1-Flash-1017","object":"model","created":1792681596,"owned_by":"flexai","model_name":"DeepSeek-V4.1-Flash-1017","context_length":1048576,"max_input_tokens":null,"max_output_tokens":393216,"quantization":null,"retirement_date":null,"description":"DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the deepseek-flash API model name.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":8e-8,"output_cost_per_token":6.05e-7,"cache_read_input_token_cost":5.5e-9},"list_pricing":{"input_cost_per_token":8e-8,"output_cost_per_token":6.05e-7,"cache_read_input_token_cost":5.5e-9},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"sference/deepseek-ai/DeepSeek-V4.1-Flash-1017","object":"model","created":1792636080,"owned_by":"sference","model_name":"deepseek-ai/DeepSeek-V4.1-Flash-1017","context_length":1048576,"max_input_tokens":null,"max_output_tokens":393216,"quantization":null,"retirement_date":null,"description":"DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the deepseek-flash API model name.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.5e-7,"output_cost_per_token":1.32e-6,"cache_read_input_token_cost":3e-8},"list_pricing":{"input_cost_per_token":3.5e-7,"output_cost_per_token":1.32e-6,"cache_read_input_token_cost":3e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"fireworks_ai/accounts/fireworks/models/deepseek-v4p1-flash-1017","object":"model","created":1792336066,"owned_by":"fireworks_ai","model_name":"accounts/fireworks/models/deepseek-v4p1-flash-1017","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":393216,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1.2e-6,"cache_read_input_token_cost":6e-9,"input_cost_per_token_priority":3.75e-7,"output_cost_per_token_priority":1.5e-6,"cache_read_input_token_cost_priority":7.5e-9},"list_pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1.2e-6,"cache_read_input_token_cost":6e-9,"input_cost_per_token_priority":3.75e-7,"output_cost_per_token_priority":1.5e-6,"cache_read_input_token_cost_priority":7.5e-9},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"tensorx/deepseek/deepseek-v4.1-flash-1017","object":"model","created":1792300420,"owned_by":"tensorx","model_name":"deepseek/deepseek-v4.1-flash-1017","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":64000,"quantization":"fp8","retirement_date":null,"description":"Served by TensorX at fp8 quantization.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":1.5e-6,"cache_read_input_token_cost":1.25e-7},"list_pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":1.5e-6,"cache_read_input_token_cost":1.25e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"cloudflare/@cf/deepseek-ai/deepseek-v4.1-flash-1017","object":"model","created":1792225624,"owned_by":"cloudflare","model_name":"@cf/deepseek-ai/deepseek-v4.1-flash-1017","context_length":1048576,"max_input_tokens":null,"max_output_tokens":393216,"quantization":null,"retirement_date":null,"description":"DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the deepseek-flash API model name.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1.2e-6,"cache_read_input_token_cost":6e-9},"list_pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1.2e-6,"cache_read_input_token_cost":6e-9},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"deepinfra/deepseek-ai/DeepSeek-V4.1-Flash-1017","object":"model","created":1792225624,"owned_by":"deepinfra","model_name":"deepseek-ai/DeepSeek-V4.1-Flash-1017","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":393216,"quantization":"fp8","retirement_date":null,"description":"DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the deepseek-flash API model name.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.0000000000000002e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":6e-9},"list_pricing":{"input_cost_per_token":2.0000000000000002e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":6e-9},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"mistral/deepseek-v4-1-flash-1017@eu","object":"model","created":1792225624,"owned_by":"mistral","model_name":"deepseek-v4-1-flash-1017","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":393216,"quantization":"fp8","retirement_date":null,"description":"DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the deepseek-flash API model name.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.3e-7,"output_cost_per_token":1.32e-6,"cache_read_input_token_cost":7.700000000000001e-9,"input_cost_per_token_batches":1.65e-7,"output_cost_per_token_batches":6.6e-7,"cache_read_input_token_cost_batches":3.8500000000000006e-9},"list_pricing":{"input_cost_per_token":3.3e-7,"output_cost_per_token":1.32e-6,"cache_read_input_token_cost":7.700000000000001e-9,"input_cost_per_token_batches":1.65e-7,"output_cost_per_token_batches":6.6e-7,"cache_read_input_token_cost_batches":3.8500000000000006e-9},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"mistral/deepseek-v4-1-flash-1017","object":"model","created":1792225624,"owned_by":"mistral","model_name":"deepseek-v4-1-flash-1017","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":393216,"quantization":"fp8","retirement_date":null,"description":"DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the deepseek-flash API model name.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1.2e-6,"cache_read_input_token_cost":7e-9,"input_cost_per_token_batches":1.5e-7,"output_cost_per_token_batches":6e-7,"cache_read_input_token_cost_batches":3.5e-9},"list_pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1.2e-6,"cache_read_input_token_cost":7e-9,"input_cost_per_token_batches":1.5e-7,"output_cost_per_token_batches":6e-7,"cache_read_input_token_cost_batches":3.5e-9},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"nebius/deepseek-ai/DeepSeek-V4.1-Flash-1017","object":"model","created":1792225624,"owned_by":"nebius","model_name":"deepseek-ai/DeepSeek-V4.1-Flash-1017","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":393216,"quantization":"fp8","retirement_date":null,"description":"DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the deepseek-flash API model name.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1.2e-6,"cache_read_input_token_cost":3e-7},"list_pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1.2e-6,"cache_read_input_token_cost":3e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"qwen/deepseek-v4.1-flash-1017","object":"model","created":1792225624,"owned_by":"qwen","model_name":"deepseek-v4.1-flash-1017","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":393216,"quantization":null,"retirement_date":null,"description":"DeepSeek-V4.1-Flash-1017 is the latest iteration of V4.1-Flash, trained with self-feedback-based reinforcement learning to deliver substantial gains over its predecessor across benchmarks such as Terminal-Bench 4.0, DeepSWE v1.1, and ProgramBench, while shortening task runtime and output length to reach a new performance–cost Pareto optimum across multiple harnesses. Its ability to build complete projects from scratch is further strengthened, enabling \"wish-based\" programming tasks such as game development and 3D modeling, while retaining the same 552B-parameter MoE, native multimodal visual understanding, 1M-token context window, and 384K-token maximum output.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":9.749999999999999e-8,"output_cost_per_token":3.8999999999999997e-7,"web_search_cost_per_call":0.00037271715,"cache_read_input_token_cost":1.95e-9},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"web_search_cost_per_call":0.000573411,"cache_read_input_token_cost":3e-9},"discount":0.35,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null},{"id":"together_ai/deepseek-ai/DeepSeek-V4.1-Flash-1017","object":"model","created":1792225624,"owned_by":"together_ai","model_name":"deepseek-ai/DeepSeek-V4.1-Flash-1017","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":393216,"quantization":null,"retirement_date":null,"description":"DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the deepseek-flash API model name.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1.2e-6,"cache_read_input_token_cost":6e-9},"list_pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1.2e-6,"cache_read_input_token_cost":6e-9},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null},{"id":"scaleway/deepseek-v4.1-flash-1017","object":"model","created":1791211484,"owned_by":"scaleway","model_name":"deepseek-v4.1-flash-1017","context_length":256000,"max_input_tokens":null,"max_output_tokens":32768,"quantization":null,"retirement_date":null,"description":"DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the deepseek-flash API model name.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6.60840258388541e-7,"output_cost_per_token":1.982520775165623e-6,"cache_read_input_token_cost":1.3216805167770822e-7},"list_pricing":{"input_cost_per_token":6.60840258388541e-7,"output_cost_per_token":1.982520775165623e-6,"cache_read_input_token_cost":1.3216805167770822e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":14},{"id":"deepseek-v4.1-flash-1017-spot","object":"model","created":1793250768,"owned_by":"deepseek","mode":"chat","context_length":1048576,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.1e-7,"output_cost_per_token":8.4e-7,"cache_read_input_token_cost":4.2e-9},"pricing_endpoint":"fireworks_ai/accounts/fireworks/routers/deepseek-v4p1-flash-1017-spot","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"fireworks_ai/accounts/fireworks/routers/deepseek-v4p1-flash-1017-spot","object":"model","created":1793250768,"owned_by":"fireworks_ai","model_name":"accounts/fireworks/routers/deepseek-v4p1-flash-1017-spot","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":393216,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.1e-7,"output_cost_per_token":8.4e-7,"cache_read_input_token_cost":4.2e-9},"list_pricing":{"input_cost_per_token":2.1e-7,"output_cost_per_token":8.4e-7,"cache_read_input_token_cost":4.2e-9},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"deepseek-v4.1-flash-spot","object":"model","created":1793250768,"owned_by":"deepseek","mode":"chat","context_length":1048576,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.1e-7,"output_cost_per_token":8.4e-7,"cache_read_input_token_cost":4.2e-9},"pricing_endpoint":"fireworks_ai/accounts/fireworks/routers/deepseek-v4p1-flash-spot","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"fireworks_ai/accounts/fireworks/routers/deepseek-v4p1-flash-spot","object":"model","created":1793250768,"owned_by":"fireworks_ai","model_name":"accounts/fireworks/routers/deepseek-v4p1-flash-spot","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":393216,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.1e-7,"output_cost_per_token":8.4e-7,"cache_read_input_token_cost":4.2e-9},"list_pricing":{"input_cost_per_token":2.1e-7,"output_cost_per_token":8.4e-7,"cache_read_input_token_cost":4.2e-9},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"glm-5.3-spot","object":"model","created":1793250768,"owned_by":"zai","mode":"chat","context_length":1048576,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":9.8e-7,"output_cost_per_token":3.08e-6,"cache_read_input_token_cost":1.82e-7},"pricing_endpoint":"fireworks_ai/accounts/fireworks/routers/glm-5p3-spot","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"fireworks_ai/accounts/fireworks/routers/glm-5p3-spot","object":"model","created":1793250768,"owned_by":"fireworks_ai","model_name":"accounts/fireworks/routers/glm-5p3-spot","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":9.8e-7,"output_cost_per_token":3.08e-6,"cache_read_input_token_cost":1.82e-7},"list_pricing":{"input_cost_per_token":9.8e-7,"output_cost_per_token":3.08e-6,"cache_read_input_token_cost":1.82e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"spot-deepseek-v4-flash","object":"model","created":1793250768,"owned_by":"deepseek","mode":"chat","context_length":1048576,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.05e-7,"output_cost_per_token":2.1e-7,"cache_read_input_token_cost":2.1e-8},"pricing_endpoint":"fireworks_ai/accounts/fireworks/routers/spot-deepseek-v4-flash","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"fireworks_ai/accounts/fireworks/routers/spot-deepseek-v4-flash","object":"model","created":1793250768,"owned_by":"fireworks_ai","model_name":"accounts/fireworks/routers/spot-deepseek-v4-flash","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":384000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.05e-7,"output_cost_per_token":2.1e-7,"cache_read_input_token_cost":2.1e-8},"list_pricing":{"input_cost_per_token":1.05e-7,"output_cost_per_token":2.1e-7,"cache_read_input_token_cost":2.1e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"~deepseek-flash-latest","object":"model","created":1793250768,"owned_by":"deepseek","mode":"chat","context_length":1048576,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":9.749999999999999e-8,"output_cost_per_token":3.8999999999999997e-7,"web_search_cost_per_call":0.00037271715,"cache_read_input_token_cost":1.95e-9},"pricing_endpoint":"qwen/deepseek-v4.1-flash-1017","regions":[{"code":"ap","name":"Asia"},{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":"deepseek-v4.1-flash-1017","endpoints":[{"id":"arkanecloud/deepseek-ai/DeepSeek-V4.1-Flash-1017","object":"model","created":1793250768,"owned_by":"arkanecloud","model_name":"deepseek-ai/DeepSeek-V4.1-Flash-1017","context_length":1048576,"max_input_tokens":null,"max_output_tokens":393216,"quantization":null,"retirement_date":null,"description":"DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the deepseek-flash API model name.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1.2e-6,"cache_read_input_token_cost":7.5e-8},"list_pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1.2e-6,"cache_read_input_token_cost":7.5e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null},{"id":"tencent/deepseek-v4.1-flash-1017","object":"model","created":1793077988,"owned_by":"tencent","model_name":"deepseek-v4.1-flash-1017","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":384000,"quantization":null,"retirement_date":null,"description":"DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the deepseek-flash API model name.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":3e-9},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":3e-9},"discount":null,"discount_ends_at":null,"regions":[{"code":"ap","name":"Asia"}],"zero_data_retention":true,"alias_of":null},{"id":"flexai/DeepSeek-V4.1-Flash-1017","object":"model","created":1792681596,"owned_by":"flexai","model_name":"DeepSeek-V4.1-Flash-1017","context_length":1048576,"max_input_tokens":null,"max_output_tokens":393216,"quantization":null,"retirement_date":null,"description":"DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the deepseek-flash API model name.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":8e-8,"output_cost_per_token":6.05e-7,"cache_read_input_token_cost":5.5e-9},"list_pricing":{"input_cost_per_token":8e-8,"output_cost_per_token":6.05e-7,"cache_read_input_token_cost":5.5e-9},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"sference/deepseek-ai/DeepSeek-V4.1-Flash-1017","object":"model","created":1792636080,"owned_by":"sference","model_name":"deepseek-ai/DeepSeek-V4.1-Flash-1017","context_length":1048576,"max_input_tokens":null,"max_output_tokens":393216,"quantization":null,"retirement_date":null,"description":"DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the deepseek-flash API model name.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.5e-7,"output_cost_per_token":1.32e-6,"cache_read_input_token_cost":3e-8},"list_pricing":{"input_cost_per_token":3.5e-7,"output_cost_per_token":1.32e-6,"cache_read_input_token_cost":3e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"fireworks_ai/accounts/fireworks/models/deepseek-v4p1-flash-1017","object":"model","created":1792336066,"owned_by":"fireworks_ai","model_name":"accounts/fireworks/models/deepseek-v4p1-flash-1017","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":393216,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1.2e-6,"cache_read_input_token_cost":6e-9,"input_cost_per_token_priority":3.75e-7,"output_cost_per_token_priority":1.5e-6,"cache_read_input_token_cost_priority":7.5e-9},"list_pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1.2e-6,"cache_read_input_token_cost":6e-9,"input_cost_per_token_priority":3.75e-7,"output_cost_per_token_priority":1.5e-6,"cache_read_input_token_cost_priority":7.5e-9},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"tensorx/deepseek/deepseek-v4.1-flash-1017","object":"model","created":1792300420,"owned_by":"tensorx","model_name":"deepseek/deepseek-v4.1-flash-1017","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":64000,"quantization":"fp8","retirement_date":null,"description":"Served by TensorX at fp8 quantization.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":1.5e-6,"cache_read_input_token_cost":1.25e-7},"list_pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":1.5e-6,"cache_read_input_token_cost":1.25e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"cloudflare/@cf/deepseek-ai/deepseek-v4.1-flash-1017","object":"model","created":1792225624,"owned_by":"cloudflare","model_name":"@cf/deepseek-ai/deepseek-v4.1-flash-1017","context_length":1048576,"max_input_tokens":null,"max_output_tokens":393216,"quantization":null,"retirement_date":null,"description":"DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the deepseek-flash API model name.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1.2e-6,"cache_read_input_token_cost":6e-9},"list_pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1.2e-6,"cache_read_input_token_cost":6e-9},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"deepinfra/deepseek-ai/DeepSeek-V4.1-Flash-1017","object":"model","created":1792225624,"owned_by":"deepinfra","model_name":"deepseek-ai/DeepSeek-V4.1-Flash-1017","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":393216,"quantization":"fp8","retirement_date":null,"description":"DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the deepseek-flash API model name.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.0000000000000002e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":6e-9},"list_pricing":{"input_cost_per_token":2.0000000000000002e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":6e-9},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"mistral/deepseek-v4-1-flash-1017@eu","object":"model","created":1792225624,"owned_by":"mistral","model_name":"deepseek-v4-1-flash-1017","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":393216,"quantization":"fp8","retirement_date":null,"description":"DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the deepseek-flash API model name.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.3e-7,"output_cost_per_token":1.32e-6,"cache_read_input_token_cost":7.700000000000001e-9,"input_cost_per_token_batches":1.65e-7,"output_cost_per_token_batches":6.6e-7,"cache_read_input_token_cost_batches":3.8500000000000006e-9},"list_pricing":{"input_cost_per_token":3.3e-7,"output_cost_per_token":1.32e-6,"cache_read_input_token_cost":7.700000000000001e-9,"input_cost_per_token_batches":1.65e-7,"output_cost_per_token_batches":6.6e-7,"cache_read_input_token_cost_batches":3.8500000000000006e-9},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"mistral/deepseek-v4-1-flash-1017","object":"model","created":1792225624,"owned_by":"mistral","model_name":"deepseek-v4-1-flash-1017","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":393216,"quantization":"fp8","retirement_date":null,"description":"DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the deepseek-flash API model name.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1.2e-6,"cache_read_input_token_cost":7e-9,"input_cost_per_token_batches":1.5e-7,"output_cost_per_token_batches":6e-7,"cache_read_input_token_cost_batches":3.5e-9},"list_pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1.2e-6,"cache_read_input_token_cost":7e-9,"input_cost_per_token_batches":1.5e-7,"output_cost_per_token_batches":6e-7,"cache_read_input_token_cost_batches":3.5e-9},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"nebius/deepseek-ai/DeepSeek-V4.1-Flash-1017","object":"model","created":1792225624,"owned_by":"nebius","model_name":"deepseek-ai/DeepSeek-V4.1-Flash-1017","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":393216,"quantization":"fp8","retirement_date":null,"description":"DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the deepseek-flash API model name.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1.2e-6,"cache_read_input_token_cost":3e-7},"list_pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1.2e-6,"cache_read_input_token_cost":3e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"qwen/deepseek-v4.1-flash-1017","object":"model","created":1792225624,"owned_by":"qwen","model_name":"deepseek-v4.1-flash-1017","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":393216,"quantization":null,"retirement_date":null,"description":"DeepSeek-V4.1-Flash-1017 is the latest iteration of V4.1-Flash, trained with self-feedback-based reinforcement learning to deliver substantial gains over its predecessor across benchmarks such as Terminal-Bench 4.0, DeepSWE v1.1, and ProgramBench, while shortening task runtime and output length to reach a new performance–cost Pareto optimum across multiple harnesses. Its ability to build complete projects from scratch is further strengthened, enabling \"wish-based\" programming tasks such as game development and 3D modeling, while retaining the same 552B-parameter MoE, native multimodal visual understanding, 1M-token context window, and 384K-token maximum output.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":9.749999999999999e-8,"output_cost_per_token":3.8999999999999997e-7,"web_search_cost_per_call":0.00037271715,"cache_read_input_token_cost":1.95e-9},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"web_search_cost_per_call":0.000573411,"cache_read_input_token_cost":3e-9},"discount":0.35,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null},{"id":"together_ai/deepseek-ai/DeepSeek-V4.1-Flash-1017","object":"model","created":1792225624,"owned_by":"together_ai","model_name":"deepseek-ai/DeepSeek-V4.1-Flash-1017","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":393216,"quantization":null,"retirement_date":null,"description":"DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the deepseek-flash API model name.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1.2e-6,"cache_read_input_token_cost":6e-9},"list_pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1.2e-6,"cache_read_input_token_cost":6e-9},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null},{"id":"scaleway/deepseek-v4.1-flash-1017","object":"model","created":1791211484,"owned_by":"scaleway","model_name":"deepseek-v4.1-flash-1017","context_length":256000,"max_input_tokens":null,"max_output_tokens":32768,"quantization":null,"retirement_date":null,"description":"DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the deepseek-flash API model name.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6.60840258388541e-7,"output_cost_per_token":1.982520775165623e-6,"cache_read_input_token_cost":1.3216805167770822e-7},"list_pricing":{"input_cost_per_token":6.60840258388541e-7,"output_cost_per_token":1.982520775165623e-6,"cache_read_input_token_cost":1.3216805167770822e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":14},{"id":"~deepseek-v4-flash-latest","object":"model","created":1793250768,"owned_by":"deepseek","mode":"chat","context_length":1048576,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6.000000000000001e-8,"output_cost_per_token":1.8e-7,"cache_read_input_token_cost":1.5000000000000002e-8},"pricing_endpoint":"deepinfra/deepseek-ai/DeepSeek-V4-Flash-0731","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":"deepseek-v4-flash-0731","endpoints":[{"id":"arkanecloud/deepseek-ai/DeepSeek-V4-Flash-0731","object":"model","created":1793250768,"owned_by":"arkanecloud","model_name":"deepseek-ai/DeepSeek-V4-Flash-0731","context_length":1048576,"max_input_tokens":null,"max_output_tokens":393216,"quantization":null,"retirement_date":null,"description":"DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":4e-7,"cache_read_input_token_cost":5e-8},"list_pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":4e-7,"cache_read_input_token_cost":5e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null},{"id":"sference/deepseek-ai/DeepSeek-V4-Flash-0731","object":"model","created":1792636080,"owned_by":"sference","model_name":"deepseek-ai/DeepSeek-V4-Flash-0731","context_length":1048576,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.8e-7,"output_cost_per_token":5.6e-7,"cache_read_input_token_cost":7e-8},"list_pricing":{"input_cost_per_token":2.8e-7,"output_cost_per_token":5.6e-7,"cache_read_input_token_cost":7e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"greenpt/deepseek-v4-flash-0731","object":"model","created":1791839241,"owned_by":"greenpt","model_name":"deepseek-v4-flash-0731","context_length":1000000,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5419606029065959e-7,"output_cost_per_token":3.8549015072664893e-7,"cache_read_input_token_cost":4.405601722590274e-8},"list_pricing":{"input_cost_per_token":1.5419606029065959e-7,"output_cost_per_token":3.8549015072664893e-7,"cache_read_input_token_cost":4.405601722590274e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"tensorx/deepseek/deepseek-v4-flash-0731","object":"model","created":1787003349,"owned_by":"tensorx","model_name":"deepseek/deepseek-v4-flash-0731","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":64000,"quantization":"fp4","retirement_date":null,"description":"Served by TensorX at fp4 quantization.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.5e-7,"output_cost_per_token":3e-7,"cache_read_input_token_cost":6.25e-8},"list_pricing":{"input_cost_per_token":2.5e-7,"output_cost_per_token":3e-7,"cache_read_input_token_cost":6.25e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"flexai/DeepSeek-V4-Flash-0731@eu","object":"model","created":1786684194,"owned_by":"flexai","model_name":"DeepSeek-V4-Flash-0731","context_length":1048576,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.3e-7,"output_cost_per_token":2.6e-7,"cache_read_input_token_cost":1.95e-8},"list_pricing":{"input_cost_per_token":1.3e-7,"output_cost_per_token":2.6e-7,"cache_read_input_token_cost":1.95e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"flexai/DeepSeek-V4-Flash-0731","object":"model","created":1786684194,"owned_by":"flexai","model_name":"DeepSeek-V4-Flash-0731","context_length":1048576,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.3e-7,"output_cost_per_token":2.6e-7,"cache_read_input_token_cost":1.95e-8},"list_pricing":{"input_cost_per_token":1.3e-7,"output_cost_per_token":2.6e-7,"cache_read_input_token_cost":1.95e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"scaleway/deepseek-v4-flash-0731","object":"model","created":1786376637,"owned_by":"scaleway","model_name":"deepseek-v4-flash-0731","context_length":256000,"max_input_tokens":null,"max_output_tokens":32768,"quantization":null,"retirement_date":null,"description":"DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4.405601722590274e-7,"output_cost_per_token":8.811203445180548e-7,"cache_read_input_token_cost":8.811203445180547e-8},"list_pricing":{"input_cost_per_token":4.405601722590274e-7,"output_cost_per_token":8.811203445180548e-7,"cache_read_input_token_cost":8.811203445180547e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"cloudflare/@cf/deepseek-ai/deepseek-v4-flash-0731","object":"model","created":1785478908,"owned_by":"cloudflare","model_name":"@cf/deepseek-ai/deepseek-v4-flash-0731","context_length":1048576,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4.4e-7,"output_cost_per_token":1.32e-6,"cache_read_input_token_cost":1.4e-8},"list_pricing":{"input_cost_per_token":4.4e-7,"output_cost_per_token":1.32e-6,"cache_read_input_token_cost":1.4e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"deepinfra/deepseek-ai/DeepSeek-V4-Flash-0731","object":"model","created":1785478908,"owned_by":"deepinfra","model_name":"deepseek-ai/DeepSeek-V4-Flash-0731","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":384000,"quantization":"fp8","retirement_date":null,"description":"DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6.000000000000001e-8,"output_cost_per_token":1.8e-7,"cache_read_input_token_cost":1.5000000000000002e-8},"list_pricing":{"input_cost_per_token":6.000000000000001e-8,"output_cost_per_token":1.8e-7,"cache_read_input_token_cost":1.5000000000000002e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"qwen/deepseek-v4-flash-0731","object":"model","created":1785478908,"owned_by":"qwen","model_name":"deepseek-v4-flash-0731","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":393216,"quantization":null,"retirement_date":null,"description":"A highly efficient, lightweight MoE model with 284 billion parameters in total and 13 billion activated parameters, natively supporting context windows of up to one million tokens. It offers fast inference speed, low latency, and cost-effective invocation, delivering well-balanced overall performance. Designed for high-concurrency, lightweight workloads, it is ideally suited for common, essential use cases such as everyday dialogue, content creation, basic RAG applications, and batch text processing.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.4300000000000002e-7,"output_cost_per_token":4.2900000000000004e-7,"cache_read_input_token_cost":1.4299999999999999e-8},"list_pricing":{"input_cost_per_token":2.2e-7,"output_cost_per_token":6.6e-7,"cache_read_input_token_cost":2.2e-8},"discount":0.35,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":10},{"id":"gpt-6.1-terra","object":"model","created":1793060038,"owned_by":"openai","mode":"chat","context_length":1050000,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":5e-6,"input_cost_per_token_flex":5e-7,"output_cost_per_token_flex":2.5e-6,"cache_read_input_token_cost":5e-8,"input_cost_per_token_batches":5e-7,"input_cost_per_token_priority":2e-6,"output_cost_per_token_batches":2.5e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"output_cost_per_token_priority":0.00001,"cache_creation_input_token_cost":1.25e-6,"cache_read_input_token_cost_flex":2.5e-8,"cache_read_input_token_cost_batches":2.5e-8,"cache_creation_input_token_cost_flex":6.25e-7,"cache_read_input_token_cost_priority":1e-7,"input_cost_per_token_above_272k_tokens":2e-6,"output_cost_per_token_above_272k_tokens":7.5e-6,"cache_creation_input_token_cost_priority":2.5e-6,"cache_creation_input_token_cost_above_12hr":2.5e-6,"input_cost_per_token_above_272k_tokens_flex":1e-6,"output_cost_per_token_above_272k_tokens_flex":3.75e-6,"cache_read_input_token_cost_above_272k_tokens":1e-7,"cache_creation_input_token_cost_above_12hr_flex":1.25e-6,"input_cost_per_token_above_272k_tokens_priority":4e-6,"output_cost_per_token_above_272k_tokens_priority":0.000015,"cache_creation_input_token_cost_above_272k_tokens":2.5e-6,"cache_read_input_token_cost_above_272k_tokens_flex":5e-8,"cache_creation_input_token_cost_above_12hr_priority":5e-6,"cache_creation_input_token_cost_above_272k_tokens_flex":1.25e-6,"cache_read_input_token_cost_above_272k_tokens_priority":2e-7,"cache_creation_input_token_cost_above_272k_tokens_priority":5e-6,"cache_creation_input_token_cost_above_12hr_above_272k_tokens":5e-6,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_flex":2.5e-6,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_priority":0.00001},"pricing_endpoint":"openai/gpt-6.1-terra","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"databricks/databricks-gpt-6-1-terra@eu","object":"model","created":1793060038,"owned_by":"databricks","model_name":"databricks-gpt-6-1-terra","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-6.1 Terra is an OpenAI model that advances the cost-intelligence frontier. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":5e-6,"input_dbu_cost_per_token":0.000014286,"output_dbu_cost_per_token":0.000071429,"cache_read_input_token_cost":1e-7,"cache_creation_input_token_cost":1.25e-6,"input_cost_per_token_above_272k_tokens":2e-6,"output_cost_per_token_above_272k_tokens":7.5e-6,"cache_creation_input_token_cost_priority":2.5e-6,"cache_read_input_token_cost_above_272k_tokens":1e-7,"input_cost_per_token_above_272k_tokens_priority":4e-6,"output_cost_per_token_above_272k_tokens_priority":0.000015,"cache_creation_input_token_cost_above_272k_tokens":2.5e-6,"cache_read_input_token_cost_above_272k_tokens_priority":2e-7,"cache_creation_input_token_cost_above_272k_tokens_priority":5e-6},"list_pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":5e-6,"input_dbu_cost_per_token":0.000014286,"output_dbu_cost_per_token":0.000071429,"cache_read_input_token_cost":1e-7,"cache_creation_input_token_cost":1.25e-6,"input_cost_per_token_above_272k_tokens":2e-6,"output_cost_per_token_above_272k_tokens":7.5e-6,"cache_creation_input_token_cost_priority":2.5e-6,"cache_read_input_token_cost_above_272k_tokens":1e-7,"input_cost_per_token_above_272k_tokens_priority":4e-6,"output_cost_per_token_above_272k_tokens_priority":0.000015,"cache_creation_input_token_cost_above_272k_tokens":2.5e-6,"cache_read_input_token_cost_above_272k_tokens_priority":2e-7,"cache_creation_input_token_cost_above_272k_tokens_priority":5e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"databricks/databricks-gpt-6-1-terra","object":"model","created":1793060038,"owned_by":"databricks","model_name":"databricks-gpt-6-1-terra","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-6.1 Terra is an OpenAI model that advances the cost-intelligence frontier. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":5e-6,"input_dbu_cost_per_token":0.000014286,"output_dbu_cost_per_token":0.000071429,"cache_read_input_token_cost":1e-7,"cache_creation_input_token_cost":1.25e-6,"input_cost_per_token_above_272k_tokens":2e-6,"output_cost_per_token_above_272k_tokens":7.5e-6,"cache_creation_input_token_cost_priority":2.5e-6,"cache_read_input_token_cost_above_272k_tokens":1e-7,"input_cost_per_token_above_272k_tokens_priority":4e-6,"output_cost_per_token_above_272k_tokens_priority":0.000015,"cache_creation_input_token_cost_above_272k_tokens":2.5e-6,"cache_read_input_token_cost_above_272k_tokens_priority":2e-7,"cache_creation_input_token_cost_above_272k_tokens_priority":5e-6},"list_pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":5e-6,"input_dbu_cost_per_token":0.000014286,"output_dbu_cost_per_token":0.000071429,"cache_read_input_token_cost":1e-7,"cache_creation_input_token_cost":1.25e-6,"input_cost_per_token_above_272k_tokens":2e-6,"output_cost_per_token_above_272k_tokens":7.5e-6,"cache_creation_input_token_cost_priority":2.5e-6,"cache_read_input_token_cost_above_272k_tokens":1e-7,"input_cost_per_token_above_272k_tokens_priority":4e-6,"output_cost_per_token_above_272k_tokens_priority":0.000015,"cache_creation_input_token_cost_above_272k_tokens":2.5e-6,"cache_read_input_token_cost_above_272k_tokens_priority":2e-7,"cache_creation_input_token_cost_above_272k_tokens_priority":5e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"azure/gpt-6.1-terra@eu","object":"model","created":1793045891,"owned_by":"azure","model_name":"gpt-6.1-terra","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-6.1 Terra is the mid-tier model in OpenAI's GPT-6.1 series, priced below GPT-6.1 Sol.","source":null,"capabilities":{"input_modalities":["text","file","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.2e-6,"output_cost_per_token":6e-6,"cache_read_input_token_cost":6e-8,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"cache_creation_input_token_cost":1.5e-6,"input_cost_per_token_above_272k_tokens":2.4e-6,"output_cost_per_token_above_272k_tokens":9e-6,"cache_read_input_token_cost_above_272k_tokens":1.2e-7,"cache_creation_input_token_cost_above_272k_tokens":3e-6},"list_pricing":{"input_cost_per_token":1.2e-6,"output_cost_per_token":6e-6,"cache_read_input_token_cost":6e-8,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"cache_creation_input_token_cost":1.5e-6,"input_cost_per_token_above_272k_tokens":2.4e-6,"output_cost_per_token_above_272k_tokens":9e-6,"cache_read_input_token_cost_above_272k_tokens":1.2e-7,"cache_creation_input_token_cost_above_272k_tokens":3e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"azure/gpt-6.1-terra","object":"model","created":1793045891,"owned_by":"azure","model_name":"gpt-6.1-terra","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-6.1 Terra is the mid-tier model in OpenAI's GPT-6.1 series, priced below GPT-6.1 Sol.","source":null,"capabilities":{"input_modalities":["text","file","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":5e-6,"cache_read_input_token_cost":5e-8,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"cache_creation_input_token_cost":1.25e-6,"input_cost_per_token_above_272k_tokens":2e-6,"output_cost_per_token_above_272k_tokens":7.5e-6,"cache_read_input_token_cost_above_272k_tokens":1e-7,"cache_creation_input_token_cost_above_272k_tokens":2.5e-6},"list_pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":5e-6,"cache_read_input_token_cost":5e-8,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"cache_creation_input_token_cost":1.25e-6,"input_cost_per_token_above_272k_tokens":2e-6,"output_cost_per_token_above_272k_tokens":7.5e-6,"cache_read_input_token_cost_above_272k_tokens":1e-7,"cache_creation_input_token_cost_above_272k_tokens":2.5e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"azure/gpt-6.1-terra@us","object":"model","created":1793045891,"owned_by":"azure","model_name":"gpt-6.1-terra","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-6.1 Terra is the mid-tier model in OpenAI's GPT-6.1 series, priced below GPT-6.1 Sol.","source":null,"capabilities":{"input_modalities":["text","file","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.1e-6,"output_cost_per_token":5.500000000000001e-6,"cache_read_input_token_cost":5.5e-8,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"cache_creation_input_token_cost":1.3750000000000002e-6,"input_cost_per_token_above_272k_tokens":2.2e-6,"output_cost_per_token_above_272k_tokens":8.25e-6,"cache_read_input_token_cost_above_272k_tokens":1.1e-7,"cache_creation_input_token_cost_above_272k_tokens":2.7500000000000004e-6},"list_pricing":{"input_cost_per_token":1.1e-6,"output_cost_per_token":5.500000000000001e-6,"cache_read_input_token_cost":5.5e-8,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"cache_creation_input_token_cost":1.3750000000000002e-6,"input_cost_per_token_above_272k_tokens":2.2e-6,"output_cost_per_token_above_272k_tokens":8.25e-6,"cache_read_input_token_cost_above_272k_tokens":1.1e-7,"cache_creation_input_token_cost_above_272k_tokens":2.7500000000000004e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"openai/gpt-6.1-terra","object":"model","created":1793038409,"owned_by":"openai","model_name":"gpt-6.1-terra","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-6.1 Terra is the mid-tier model in OpenAI's GPT-6.1 series, priced below GPT-6.1 Sol.","source":null,"capabilities":{"input_modalities":["file","image","text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":5e-6,"input_cost_per_token_flex":5e-7,"output_cost_per_token_flex":2.5e-6,"cache_read_input_token_cost":5e-8,"input_cost_per_token_batches":5e-7,"input_cost_per_token_priority":2e-6,"output_cost_per_token_batches":2.5e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"output_cost_per_token_priority":0.00001,"cache_creation_input_token_cost":1.25e-6,"cache_read_input_token_cost_flex":2.5e-8,"cache_read_input_token_cost_batches":2.5e-8,"cache_creation_input_token_cost_flex":6.25e-7,"cache_read_input_token_cost_priority":1e-7,"input_cost_per_token_above_272k_tokens":2e-6,"output_cost_per_token_above_272k_tokens":7.5e-6,"cache_creation_input_token_cost_priority":2.5e-6,"cache_creation_input_token_cost_above_12hr":2.5e-6,"input_cost_per_token_above_272k_tokens_flex":1e-6,"output_cost_per_token_above_272k_tokens_flex":3.75e-6,"cache_read_input_token_cost_above_272k_tokens":1e-7,"cache_creation_input_token_cost_above_12hr_flex":1.25e-6,"input_cost_per_token_above_272k_tokens_priority":4e-6,"output_cost_per_token_above_272k_tokens_priority":0.000015,"cache_creation_input_token_cost_above_272k_tokens":2.5e-6,"cache_read_input_token_cost_above_272k_tokens_flex":5e-8,"cache_creation_input_token_cost_above_12hr_priority":5e-6,"cache_creation_input_token_cost_above_272k_tokens_flex":1.25e-6,"cache_read_input_token_cost_above_272k_tokens_priority":2e-7,"cache_creation_input_token_cost_above_272k_tokens_priority":5e-6,"cache_creation_input_token_cost_above_12hr_above_272k_tokens":5e-6,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_flex":2.5e-6,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_priority":0.00001},"list_pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":5e-6,"input_cost_per_token_flex":5e-7,"output_cost_per_token_flex":2.5e-6,"cache_read_input_token_cost":5e-8,"input_cost_per_token_batches":5e-7,"input_cost_per_token_priority":2e-6,"output_cost_per_token_batches":2.5e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"output_cost_per_token_priority":0.00001,"cache_creation_input_token_cost":1.25e-6,"cache_read_input_token_cost_flex":2.5e-8,"cache_read_input_token_cost_batches":2.5e-8,"cache_creation_input_token_cost_flex":6.25e-7,"cache_read_input_token_cost_priority":1e-7,"input_cost_per_token_above_272k_tokens":2e-6,"output_cost_per_token_above_272k_tokens":7.5e-6,"cache_creation_input_token_cost_priority":2.5e-6,"cache_creation_input_token_cost_above_12hr":2.5e-6,"input_cost_per_token_above_272k_tokens_flex":1e-6,"output_cost_per_token_above_272k_tokens_flex":3.75e-6,"cache_read_input_token_cost_above_272k_tokens":1e-7,"cache_creation_input_token_cost_above_12hr_flex":1.25e-6,"input_cost_per_token_above_272k_tokens_priority":4e-6,"output_cost_per_token_above_272k_tokens_priority":0.000015,"cache_creation_input_token_cost_above_272k_tokens":2.5e-6,"cache_read_input_token_cost_above_272k_tokens_flex":5e-8,"cache_creation_input_token_cost_above_12hr_priority":5e-6,"cache_creation_input_token_cost_above_272k_tokens_flex":1.25e-6,"cache_read_input_token_cost_above_272k_tokens_priority":2e-7,"cache_creation_input_token_cost_above_272k_tokens_priority":5e-6,"cache_creation_input_token_cost_above_12hr_above_272k_tokens":5e-6,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_flex":2.5e-6,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_priority":0.00001},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":6},{"id":"~gpt-terra-latest","object":"model","created":1793060038,"owned_by":"openai","mode":"chat","context_length":1050000,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":5e-6,"input_cost_per_token_flex":5e-7,"output_cost_per_token_flex":2.5e-6,"cache_read_input_token_cost":5e-8,"input_cost_per_token_batches":5e-7,"input_cost_per_token_priority":2e-6,"output_cost_per_token_batches":2.5e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"output_cost_per_token_priority":0.00001,"cache_creation_input_token_cost":1.25e-6,"cache_read_input_token_cost_flex":2.5e-8,"cache_read_input_token_cost_batches":2.5e-8,"cache_creation_input_token_cost_flex":6.25e-7,"cache_read_input_token_cost_priority":1e-7,"input_cost_per_token_above_272k_tokens":2e-6,"output_cost_per_token_above_272k_tokens":7.5e-6,"cache_creation_input_token_cost_priority":2.5e-6,"cache_creation_input_token_cost_above_12hr":2.5e-6,"input_cost_per_token_above_272k_tokens_flex":1e-6,"output_cost_per_token_above_272k_tokens_flex":3.75e-6,"cache_read_input_token_cost_above_272k_tokens":1e-7,"cache_creation_input_token_cost_above_12hr_flex":1.25e-6,"input_cost_per_token_above_272k_tokens_priority":4e-6,"output_cost_per_token_above_272k_tokens_priority":0.000015,"cache_creation_input_token_cost_above_272k_tokens":2.5e-6,"cache_read_input_token_cost_above_272k_tokens_flex":5e-8,"cache_creation_input_token_cost_above_12hr_priority":5e-6,"cache_creation_input_token_cost_above_272k_tokens_flex":1.25e-6,"cache_read_input_token_cost_above_272k_tokens_priority":2e-7,"cache_creation_input_token_cost_above_272k_tokens_priority":5e-6,"cache_creation_input_token_cost_above_12hr_above_272k_tokens":5e-6,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_flex":2.5e-6,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_priority":0.00001},"pricing_endpoint":"openai/gpt-6.1-terra","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":"gpt-6.1-terra","endpoints":[{"id":"databricks/databricks-gpt-6-1-terra@eu","object":"model","created":1793060038,"owned_by":"databricks","model_name":"databricks-gpt-6-1-terra","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-6.1 Terra is an OpenAI model that advances the cost-intelligence frontier. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":5e-6,"input_dbu_cost_per_token":0.000014286,"output_dbu_cost_per_token":0.000071429,"cache_read_input_token_cost":1e-7,"cache_creation_input_token_cost":1.25e-6,"input_cost_per_token_above_272k_tokens":2e-6,"output_cost_per_token_above_272k_tokens":7.5e-6,"cache_creation_input_token_cost_priority":2.5e-6,"cache_read_input_token_cost_above_272k_tokens":1e-7,"input_cost_per_token_above_272k_tokens_priority":4e-6,"output_cost_per_token_above_272k_tokens_priority":0.000015,"cache_creation_input_token_cost_above_272k_tokens":2.5e-6,"cache_read_input_token_cost_above_272k_tokens_priority":2e-7,"cache_creation_input_token_cost_above_272k_tokens_priority":5e-6},"list_pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":5e-6,"input_dbu_cost_per_token":0.000014286,"output_dbu_cost_per_token":0.000071429,"cache_read_input_token_cost":1e-7,"cache_creation_input_token_cost":1.25e-6,"input_cost_per_token_above_272k_tokens":2e-6,"output_cost_per_token_above_272k_tokens":7.5e-6,"cache_creation_input_token_cost_priority":2.5e-6,"cache_read_input_token_cost_above_272k_tokens":1e-7,"input_cost_per_token_above_272k_tokens_priority":4e-6,"output_cost_per_token_above_272k_tokens_priority":0.000015,"cache_creation_input_token_cost_above_272k_tokens":2.5e-6,"cache_read_input_token_cost_above_272k_tokens_priority":2e-7,"cache_creation_input_token_cost_above_272k_tokens_priority":5e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"databricks/databricks-gpt-6-1-terra","object":"model","created":1793060038,"owned_by":"databricks","model_name":"databricks-gpt-6-1-terra","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-6.1 Terra is an OpenAI model that advances the cost-intelligence frontier. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":5e-6,"input_dbu_cost_per_token":0.000014286,"output_dbu_cost_per_token":0.000071429,"cache_read_input_token_cost":1e-7,"cache_creation_input_token_cost":1.25e-6,"input_cost_per_token_above_272k_tokens":2e-6,"output_cost_per_token_above_272k_tokens":7.5e-6,"cache_creation_input_token_cost_priority":2.5e-6,"cache_read_input_token_cost_above_272k_tokens":1e-7,"input_cost_per_token_above_272k_tokens_priority":4e-6,"output_cost_per_token_above_272k_tokens_priority":0.000015,"cache_creation_input_token_cost_above_272k_tokens":2.5e-6,"cache_read_input_token_cost_above_272k_tokens_priority":2e-7,"cache_creation_input_token_cost_above_272k_tokens_priority":5e-6},"list_pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":5e-6,"input_dbu_cost_per_token":0.000014286,"output_dbu_cost_per_token":0.000071429,"cache_read_input_token_cost":1e-7,"cache_creation_input_token_cost":1.25e-6,"input_cost_per_token_above_272k_tokens":2e-6,"output_cost_per_token_above_272k_tokens":7.5e-6,"cache_creation_input_token_cost_priority":2.5e-6,"cache_read_input_token_cost_above_272k_tokens":1e-7,"input_cost_per_token_above_272k_tokens_priority":4e-6,"output_cost_per_token_above_272k_tokens_priority":0.000015,"cache_creation_input_token_cost_above_272k_tokens":2.5e-6,"cache_read_input_token_cost_above_272k_tokens_priority":2e-7,"cache_creation_input_token_cost_above_272k_tokens_priority":5e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"azure/gpt-6.1-terra@eu","object":"model","created":1793045891,"owned_by":"azure","model_name":"gpt-6.1-terra","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-6.1 Terra is the mid-tier model in OpenAI's GPT-6.1 series, priced below GPT-6.1 Sol.","source":null,"capabilities":{"input_modalities":["text","file","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.2e-6,"output_cost_per_token":6e-6,"cache_read_input_token_cost":6e-8,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"cache_creation_input_token_cost":1.5e-6,"input_cost_per_token_above_272k_tokens":2.4e-6,"output_cost_per_token_above_272k_tokens":9e-6,"cache_read_input_token_cost_above_272k_tokens":1.2e-7,"cache_creation_input_token_cost_above_272k_tokens":3e-6},"list_pricing":{"input_cost_per_token":1.2e-6,"output_cost_per_token":6e-6,"cache_read_input_token_cost":6e-8,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"cache_creation_input_token_cost":1.5e-6,"input_cost_per_token_above_272k_tokens":2.4e-6,"output_cost_per_token_above_272k_tokens":9e-6,"cache_read_input_token_cost_above_272k_tokens":1.2e-7,"cache_creation_input_token_cost_above_272k_tokens":3e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"azure/gpt-6.1-terra","object":"model","created":1793045891,"owned_by":"azure","model_name":"gpt-6.1-terra","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-6.1 Terra is the mid-tier model in OpenAI's GPT-6.1 series, priced below GPT-6.1 Sol.","source":null,"capabilities":{"input_modalities":["text","file","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":5e-6,"cache_read_input_token_cost":5e-8,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"cache_creation_input_token_cost":1.25e-6,"input_cost_per_token_above_272k_tokens":2e-6,"output_cost_per_token_above_272k_tokens":7.5e-6,"cache_read_input_token_cost_above_272k_tokens":1e-7,"cache_creation_input_token_cost_above_272k_tokens":2.5e-6},"list_pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":5e-6,"cache_read_input_token_cost":5e-8,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"cache_creation_input_token_cost":1.25e-6,"input_cost_per_token_above_272k_tokens":2e-6,"output_cost_per_token_above_272k_tokens":7.5e-6,"cache_read_input_token_cost_above_272k_tokens":1e-7,"cache_creation_input_token_cost_above_272k_tokens":2.5e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"azure/gpt-6.1-terra@us","object":"model","created":1793045891,"owned_by":"azure","model_name":"gpt-6.1-terra","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-6.1 Terra is the mid-tier model in OpenAI's GPT-6.1 series, priced below GPT-6.1 Sol.","source":null,"capabilities":{"input_modalities":["text","file","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.1e-6,"output_cost_per_token":5.500000000000001e-6,"cache_read_input_token_cost":5.5e-8,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"cache_creation_input_token_cost":1.3750000000000002e-6,"input_cost_per_token_above_272k_tokens":2.2e-6,"output_cost_per_token_above_272k_tokens":8.25e-6,"cache_read_input_token_cost_above_272k_tokens":1.1e-7,"cache_creation_input_token_cost_above_272k_tokens":2.7500000000000004e-6},"list_pricing":{"input_cost_per_token":1.1e-6,"output_cost_per_token":5.500000000000001e-6,"cache_read_input_token_cost":5.5e-8,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"cache_creation_input_token_cost":1.3750000000000002e-6,"input_cost_per_token_above_272k_tokens":2.2e-6,"output_cost_per_token_above_272k_tokens":8.25e-6,"cache_read_input_token_cost_above_272k_tokens":1.1e-7,"cache_creation_input_token_cost_above_272k_tokens":2.7500000000000004e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"openai/gpt-6.1-terra","object":"model","created":1793038409,"owned_by":"openai","model_name":"gpt-6.1-terra","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-6.1 Terra is the mid-tier model in OpenAI's GPT-6.1 series, priced below GPT-6.1 Sol.","source":null,"capabilities":{"input_modalities":["file","image","text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":5e-6,"input_cost_per_token_flex":5e-7,"output_cost_per_token_flex":2.5e-6,"cache_read_input_token_cost":5e-8,"input_cost_per_token_batches":5e-7,"input_cost_per_token_priority":2e-6,"output_cost_per_token_batches":2.5e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"output_cost_per_token_priority":0.00001,"cache_creation_input_token_cost":1.25e-6,"cache_read_input_token_cost_flex":2.5e-8,"cache_read_input_token_cost_batches":2.5e-8,"cache_creation_input_token_cost_flex":6.25e-7,"cache_read_input_token_cost_priority":1e-7,"input_cost_per_token_above_272k_tokens":2e-6,"output_cost_per_token_above_272k_tokens":7.5e-6,"cache_creation_input_token_cost_priority":2.5e-6,"cache_creation_input_token_cost_above_12hr":2.5e-6,"input_cost_per_token_above_272k_tokens_flex":1e-6,"output_cost_per_token_above_272k_tokens_flex":3.75e-6,"cache_read_input_token_cost_above_272k_tokens":1e-7,"cache_creation_input_token_cost_above_12hr_flex":1.25e-6,"input_cost_per_token_above_272k_tokens_priority":4e-6,"output_cost_per_token_above_272k_tokens_priority":0.000015,"cache_creation_input_token_cost_above_272k_tokens":2.5e-6,"cache_read_input_token_cost_above_272k_tokens_flex":5e-8,"cache_creation_input_token_cost_above_12hr_priority":5e-6,"cache_creation_input_token_cost_above_272k_tokens_flex":1.25e-6,"cache_read_input_token_cost_above_272k_tokens_priority":2e-7,"cache_creation_input_token_cost_above_272k_tokens_priority":5e-6,"cache_creation_input_token_cost_above_12hr_above_272k_tokens":5e-6,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_flex":2.5e-6,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_priority":0.00001},"list_pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":5e-6,"input_cost_per_token_flex":5e-7,"output_cost_per_token_flex":2.5e-6,"cache_read_input_token_cost":5e-8,"input_cost_per_token_batches":5e-7,"input_cost_per_token_priority":2e-6,"output_cost_per_token_batches":2.5e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"output_cost_per_token_priority":0.00001,"cache_creation_input_token_cost":1.25e-6,"cache_read_input_token_cost_flex":2.5e-8,"cache_read_input_token_cost_batches":2.5e-8,"cache_creation_input_token_cost_flex":6.25e-7,"cache_read_input_token_cost_priority":1e-7,"input_cost_per_token_above_272k_tokens":2e-6,"output_cost_per_token_above_272k_tokens":7.5e-6,"cache_creation_input_token_cost_priority":2.5e-6,"cache_creation_input_token_cost_above_12hr":2.5e-6,"input_cost_per_token_above_272k_tokens_flex":1e-6,"output_cost_per_token_above_272k_tokens_flex":3.75e-6,"cache_read_input_token_cost_above_272k_tokens":1e-7,"cache_creation_input_token_cost_above_12hr_flex":1.25e-6,"input_cost_per_token_above_272k_tokens_priority":4e-6,"output_cost_per_token_above_272k_tokens_priority":0.000015,"cache_creation_input_token_cost_above_272k_tokens":2.5e-6,"cache_read_input_token_cost_above_272k_tokens_flex":5e-8,"cache_creation_input_token_cost_above_12hr_priority":5e-6,"cache_creation_input_token_cost_above_272k_tokens_flex":1.25e-6,"cache_read_input_token_cost_above_272k_tokens_priority":2e-7,"cache_creation_input_token_cost_above_272k_tokens_priority":5e-6,"cache_creation_input_token_cost_above_12hr_above_272k_tokens":5e-6,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_flex":2.5e-6,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_priority":0.00001},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":6},{"id":"kimi-k3.1-pro-highspeed","object":"model","created":1792782618,"owned_by":"moonshot","mode":"chat","context_length":1048576,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4e-6,"output_cost_per_token":0.00002,"cache_read_input_token_cost":2e-7,"cache_creation_input_token_cost":4e-6,"cache_creation_input_token_cost_above_1hr":8e-6},"pricing_endpoint":"moonshot/kimi-k3.1-pro-highspeed","regions":[{"code":"ap","name":"Asia"}],"alias_of":null,"endpoints":[{"id":"moonshot/kimi-k3.1-pro-highspeed","object":"model","created":1792782618,"owned_by":"moonshot","model_name":"kimi-k3.1-pro-highspeed","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4e-6,"output_cost_per_token":0.00002,"cache_read_input_token_cost":2e-7,"cache_creation_input_token_cost":4e-6,"cache_creation_input_token_cost_above_1hr":8e-6},"list_pricing":{"input_cost_per_token":4e-6,"output_cost_per_token":0.00002,"cache_read_input_token_cost":2e-7,"cache_creation_input_token_cost":4e-6,"cache_creation_input_token_cost_above_1hr":8e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"ap","name":"Asia"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":1},{"id":"deepseek-v3.2","object":"model","created":1792768060,"owned_by":"deepseek","mode":"chat","context_length":163840,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.6e-7,"output_cost_per_token":3.8e-7,"cache_read_input_token_cost":1.3e-7},"pricing_endpoint":"deepinfra/deepseek-ai/DeepSeek-V3.2","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"arkanecloud/deepseek-ai/DeepSeek-V3.2","object":"model","created":1792768060,"owned_by":"arkanecloud","model_name":"deepseek-ai/DeepSeek-V3.2","context_length":163840,"max_input_tokens":null,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":1.5e-6,"cache_read_input_token_cost":1.5e-7},"list_pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":1.5e-6,"cache_read_input_token_cost":1.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"},{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"tensorx/deepseek/deepseek-v3.2","object":"model","created":1787003349,"owned_by":"tensorx","model_name":"deepseek/deepseek-v3.2","context_length":163840,"max_input_tokens":163840,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"Served by TensorX at fp8 quantization.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":7.5e-8},"list_pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":7.5e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/deepseek.v3.2","object":"model","created":1770991619,"owned_by":"amazon","model_name":"deepseek.v3.2","context_length":156000,"max_input_tokens":156000,"max_output_tokens":8000,"quantization":null,"retirement_date":null,"description":null,"source":"https://aws.amazon.com/bedrock/pricing/","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":7.4e-7,"output_cost_per_token":2.22e-6,"input_cost_per_token_flex":3.7e-7,"output_cost_per_token_flex":1.11e-6,"input_cost_per_token_priority":1.295e-6,"output_cost_per_token_priority":3.885e-6},"list_pricing":{"input_cost_per_token":7.4e-7,"output_cost_per_token":2.22e-6,"input_cost_per_token_flex":3.7e-7,"output_cost_per_token_flex":1.11e-6,"input_cost_per_token_priority":1.295e-6,"output_cost_per_token_priority":3.885e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/deepseek.v3.2@us","object":"model","created":1770991619,"owned_by":"amazon","model_name":"deepseek.v3.2","context_length":156000,"max_input_tokens":156000,"max_output_tokens":8000,"quantization":null,"retirement_date":null,"description":null,"source":"https://aws.amazon.com/bedrock/pricing/","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":7.4e-7,"output_cost_per_token":2.22e-6,"input_cost_per_token_flex":3.7e-7,"output_cost_per_token_flex":1.11e-6,"input_cost_per_token_priority":1.295e-6,"output_cost_per_token_priority":3.885e-6},"list_pricing":{"input_cost_per_token":7.4e-7,"output_cost_per_token":2.22e-6,"input_cost_per_token_flex":3.7e-7,"output_cost_per_token_flex":1.11e-6,"input_cost_per_token_priority":1.295e-6,"output_cost_per_token_priority":3.885e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"deepinfra/deepseek-ai/DeepSeek-V3.2","object":"model","created":1764594642,"owned_by":"deepinfra","model_name":"deepseek-ai/DeepSeek-V3.2","context_length":163840,"max_input_tokens":163840,"max_output_tokens":null,"quantization":"fp4","retirement_date":"2026-09-28","description":"DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.6e-7,"output_cost_per_token":3.8e-7,"cache_read_input_token_cost":1.3e-7},"list_pricing":{"input_cost_per_token":2.6e-7,"output_cost_per_token":3.8e-7,"cache_read_input_token_cost":1.3e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":5},{"id":"deepseek-v4-flash","object":"model","created":1792768060,"owned_by":"deepseek","mode":"chat","context_length":1048576,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":9e-8,"output_cost_per_token":1.8e-7,"cache_read_input_token_cost":1.8e-8},"pricing_endpoint":"deepinfra/deepseek-ai/DeepSeek-V4-Flash","regions":[{"code":"ap","name":"Asia"},{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"arkanecloud/deepseek-ai/DeepSeek-V4-Flash","object":"model","created":1792768060,"owned_by":"arkanecloud","model_name":"deepseek-ai/DeepSeek-V4-Flash","context_length":1048576,"max_input_tokens":null,"max_output_tokens":393216,"quantization":null,"retirement_date":null,"description":"DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":4e-7,"cache_read_input_token_cost":5e-8},"list_pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":4e-7,"cache_read_input_token_cost":5e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"},{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"tencent/deepseek-v4-flash-202605","object":"model","created":1790867221,"owned_by":"tencent","model_name":"deepseek-v4-flash-202605","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":384000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":3e-9},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":3e-9},"discount":null,"discount_ends_at":null,"regions":[{"code":"ap","name":"Asia"}],"zero_data_retention":true,"alias_of":null},{"id":"azure/deepseek-v4-flash@eu","object":"model","created":1786613111,"owned_by":"azure","model_name":"deepseek-v4-flash","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":384000,"quantization":null,"retirement_date":null,"description":"DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.0900000000000003e-7,"output_cost_per_token":5.61e-7,"cache_read_input_token_cost":3.0800000000000004e-8},"list_pricing":{"input_cost_per_token":2.0900000000000003e-7,"output_cost_per_token":5.61e-7,"cache_read_input_token_cost":3.0800000000000004e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"azure/deepseek-v4-flash","object":"model","created":1786613111,"owned_by":"azure","model_name":"deepseek-v4-flash","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":384000,"quantization":null,"retirement_date":null,"description":"DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.9e-7,"output_cost_per_token":5.1e-7,"cache_read_input_token_cost":2.8e-8},"list_pricing":{"input_cost_per_token":1.9e-7,"output_cost_per_token":5.1e-7,"cache_read_input_token_cost":2.8e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"azure/deepseek-v4-flash@us","object":"model","created":1786613111,"owned_by":"azure","model_name":"deepseek-v4-flash","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":384000,"quantization":null,"retirement_date":null,"description":"DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.0900000000000003e-7,"output_cost_per_token":5.61e-7,"cache_read_input_token_cost":3.0800000000000004e-8},"list_pricing":{"input_cost_per_token":2.0900000000000003e-7,"output_cost_per_token":5.61e-7,"cache_read_input_token_cost":3.0800000000000004e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"deepinfra/deepseek-ai/DeepSeek-V4-Flash","object":"model","created":1777000666,"owned_by":"deepinfra","model_name":"deepseek-ai/DeepSeek-V4-Flash","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":393216,"quantization":"fp8","retirement_date":null,"description":"DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":9e-8,"output_cost_per_token":1.8e-7,"cache_read_input_token_cost":1.8e-8},"list_pricing":{"input_cost_per_token":9e-8,"output_cost_per_token":1.8e-7,"cache_read_input_token_cost":1.8e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":6},{"id":"deepseek-v4-pro","object":"model","created":1792768060,"owned_by":"deepseek","mode":"chat","context_length":1048576,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":6.6e-7,"output_cost_per_token":1.98e-6,"web_search_cost_per_call":0.00075,"cache_read_input_token_cost":2.2e-8,"input_cost_per_token_cache_hit":4.4e-8,"cache_creation_input_token_cost":0.0},"pricing_endpoint":"deepseek/deepseek-v4-pro","regions":[{"code":"ap","name":"Asia"},{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"arkanecloud/deepseek-ai/DeepSeek-V4-Pro","object":"model","created":1792768060,"owned_by":"arkanecloud","model_name":"deepseek-ai/DeepSeek-V4-Pro","context_length":1000000,"max_input_tokens":null,"max_output_tokens":384000,"quantization":null,"retirement_date":null,"description":"DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.7e-6,"output_cost_per_token":3.4e-6,"cache_read_input_token_cost":1.5e-7},"list_pricing":{"input_cost_per_token":1.7e-6,"output_cost_per_token":3.4e-6,"cache_read_input_token_cost":1.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"},{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"tencent/deepseek-v4-pro-202606","object":"model","created":1790867221,"owned_by":"tencent","model_name":"deepseek-v4-pro-202606","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":384000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6.6e-7,"output_cost_per_token":1.98e-6,"cache_read_input_token_cost":2.2e-8},"list_pricing":{"input_cost_per_token":6.6e-7,"output_cost_per_token":1.98e-6,"cache_read_input_token_cost":2.2e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"ap","name":"Asia"}],"zero_data_retention":true,"alias_of":null},{"id":"tensorx/deepseek/deepseek-v4-pro","object":"model","created":1787003349,"owned_by":"tensorx","model_name":"deepseek/deepseek-v4-pro","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":64000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.75e-6,"output_cost_per_token":3.5e-6,"cache_read_input_token_cost":4.375e-7},"list_pricing":{"input_cost_per_token":1.75e-6,"output_cost_per_token":3.5e-6,"cache_read_input_token_cost":4.375e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"deepinfra/deepseek-ai/DeepSeek-V4-Pro","object":"model","created":1777000679,"owned_by":"deepinfra","model_name":"deepseek-ai/DeepSeek-V4-Pro","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":393216,"quantization":"fp8","retirement_date":null,"description":"DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.2999999999999998e-6,"output_cost_per_token":2.5999999999999997e-6,"cache_read_input_token_cost":1.0000000399999998e-7},"list_pricing":{"input_cost_per_token":1.2999999999999998e-6,"output_cost_per_token":2.5999999999999997e-6,"cache_read_input_token_cost":1.0000000399999998e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"deepseek/deepseek-v4-pro","object":"model","created":1777000679,"owned_by":"deepseek","model_name":"deepseek-v4-pro","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":393216,"quantization":null,"retirement_date":null,"description":"DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":6.6e-7,"output_cost_per_token":1.98e-6,"web_search_cost_per_call":0.00075,"cache_read_input_token_cost":2.2e-8,"input_cost_per_token_cache_hit":4.4e-8,"cache_creation_input_token_cost":0.0},"list_pricing":{"input_cost_per_token":6.6e-7,"output_cost_per_token":1.98e-6,"web_search_cost_per_call":0.00075,"cache_read_input_token_cost":2.2e-8,"input_cost_per_token_cache_hit":4.4e-8,"cache_creation_input_token_cost":0.0},"discount":null,"discount_ends_at":null,"regions":[{"code":"ap","name":"Asia"}],"zero_data_retention":false,"alias_of":null},{"id":"qwen/deepseek-v4-pro","object":"model","created":1777000679,"owned_by":"qwen","model_name":"deepseek-v4-pro","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":393216,"quantization":"fp8","retirement_date":null,"description":"A flagship MoE large model with 1.6 trillion parameters and 49 billion activated parameters, natively supporting context lengths of up to one million tokens. Trained on a vast corpus of high-quality data, it excels in advanced mathematical reasoning, complex logical inference, specialized coding, and deep analysis of long-form text, making it well-suited for demanding applications such as cutting-edge research, sophisticated office workflows, and advanced AI agents.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5599999999999999e-6,"output_cost_per_token":3.1199999999999998e-6,"cache_read_input_token_cost":1.3000000000000003e-7},"list_pricing":{"input_cost_per_token":2.4e-6,"output_cost_per_token":4.8e-6,"cache_read_input_token_cost":2.0000000000000002e-7},"discount":0.35,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":6},{"id":"deepseek-v4.1-flash","object":"model","created":1792768060,"owned_by":"deepseek","mode":"chat","context_length":1048576,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":9.749999999999999e-8,"output_cost_per_token":3.8999999999999997e-7,"cache_read_input_token_cost":1.95e-9},"pricing_endpoint":"qwen/deepseek-v4.1-flash","regions":[{"code":"ap","name":"Asia"},{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"arkanecloud/deepseek-ai/DeepSeek-V4.1-Flash","object":"model","created":1792768060,"owned_by":"arkanecloud","model_name":"deepseek-ai/DeepSeek-V4.1-Flash","context_length":1048576,"max_input_tokens":null,"max_output_tokens":393216,"quantization":null,"retirement_date":null,"description":"DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1.2e-6,"cache_read_input_token_cost":7.5e-8},"list_pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1.2e-6,"cache_read_input_token_cost":7.5e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"},{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"vertex/deepseek-ai/deepseek-v4.1-flash-maas@eu","object":"model","created":1792186462,"owned_by":"vertex","model_name":"deepseek-ai/deepseek-v4.1-flash-maas","context_length":null,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.3e-7,"output_cost_per_token":1.32e-6,"cache_read_input_token_cost":3.3e-8},"list_pricing":{"input_cost_per_token":3.3e-7,"output_cost_per_token":1.32e-6,"cache_read_input_token_cost":3.3e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"vertex/deepseek-ai/deepseek-v4.1-flash-maas","object":"model","created":1792186462,"owned_by":"vertex","model_name":"deepseek-ai/deepseek-v4.1-flash-maas","context_length":null,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1.2e-6,"cache_read_input_token_cost":3e-8},"list_pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1.2e-6,"cache_read_input_token_cost":3e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"vertex/deepseek-ai/deepseek-v4.1-flash-maas@us","object":"model","created":1792186462,"owned_by":"vertex","model_name":"deepseek-ai/deepseek-v4.1-flash-maas","context_length":null,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.3e-7,"output_cost_per_token":1.32e-6,"cache_read_input_token_cost":3.3e-8},"list_pricing":{"input_cost_per_token":3.3e-7,"output_cost_per_token":1.32e-6,"cache_read_input_token_cost":3.3e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"greenpt/deepseek-v4.1-flash","object":"model","created":1791839241,"owned_by":"greenpt","model_name":"deepseek-v4.1-flash","context_length":1000000,"max_input_tokens":null,"max_output_tokens":393216,"quantization":null,"retirement_date":null,"description":"DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.4230809474246506e-7,"output_cost_per_token":1.2115404737123252e-6,"cache_read_input_token_cost":1.2115404737123252e-8},"list_pricing":{"input_cost_per_token":2.4230809474246506e-7,"output_cost_per_token":1.2115404737123252e-6,"cache_read_input_token_cost":1.2115404737123252e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"scaleway/deepseek-v4.1-flash","object":"model","created":1791211484,"owned_by":"scaleway","model_name":"deepseek-v4.1-flash","context_length":256000,"max_input_tokens":null,"max_output_tokens":32768,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6.689999899650001e-7,"output_cost_per_token":2.0069999698950002e-6,"cache_read_input_token_cost":1.3379999799300003e-7},"list_pricing":{"input_cost_per_token":6.689999899650001e-7,"output_cost_per_token":2.0069999698950002e-6,"cache_read_input_token_cost":1.3379999799300003e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"tencent/deepseek-v4.1-flash","object":"model","created":1790867221,"owned_by":"tencent","model_name":"deepseek-v4.1-flash","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":384000,"quantization":null,"retirement_date":null,"description":"DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":3e-9,"input_cost_per_token_cache_hit":6e-9,"cache_creation_input_token_cost":0.0},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":3e-9,"input_cost_per_token_cache_hit":6e-9,"cache_creation_input_token_cost":0.0},"discount":null,"discount_ends_at":null,"regions":[{"code":"ap","name":"Asia"}],"zero_data_retention":true,"alias_of":null},{"id":"databricks/databricks-deepseek-v4-1-flash","object":"model","created":1790399645,"owned_by":"databricks","model_name":"databricks-deepseek-v4-1-flash","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":393216,"quantization":null,"retirement_date":null,"description":"DeepSeek V4.1 Flash is a multimodal mixture-of-experts model with 552B backbone parameters developed by DeepSeek. It supports text and image input, reasoning, coding, and agentic tool use.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1.2e-6,"input_dbu_cost_per_token":4.286e-6,"output_dbu_cost_per_token":0.000017143,"cache_read_input_token_cost":3e-8,"cache_creation_input_token_cost":3e-7,"cache_creation_input_token_cost_priority":5.25e-7},"list_pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1.2e-6,"input_dbu_cost_per_token":4.286e-6,"output_dbu_cost_per_token":0.000017143,"cache_read_input_token_cost":3e-8,"cache_creation_input_token_cost":3e-7,"cache_creation_input_token_cost_priority":5.25e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"tensorx/deepseek/deepseek-v4.1-flash","object":"model","created":1789362586,"owned_by":"tensorx","model_name":"deepseek/deepseek-v4.1-flash","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":64000,"quantization":"fp8","retirement_date":null,"description":"Served by TensorX at fp8 quantization.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":1.5e-6,"cache_read_input_token_cost":1.25e-7},"list_pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":1.5e-6,"cache_read_input_token_cost":1.25e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"deepseek/deepseek-flash","object":"model","created":1789276218,"owned_by":"deepseek","model_name":"deepseek-flash","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":393216,"quantization":null,"retirement_date":null,"description":"This model always redirects to the latest model in the DeepSeek Flash family.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":3e-9,"input_cost_per_token_cache_hit":6e-9,"cache_creation_input_token_cost":0.0},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":3e-9,"input_cost_per_token_cache_hit":6e-9,"cache_creation_input_token_cost":0.0},"discount":null,"discount_ends_at":null,"regions":[{"code":"ap","name":"Asia"}],"zero_data_retention":false,"alias_of":null},{"id":"fireworks_ai/accounts/fireworks/models/deepseek-v4p1-flash","object":"model","created":1789276218,"owned_by":"fireworks_ai","model_name":"accounts/fireworks/models/deepseek-v4p1-flash","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":393216,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1.2e-6,"cache_read_input_token_cost":6e-9,"input_cost_per_token_priority":3.75e-7,"output_cost_per_token_priority":1.5e-6,"cache_read_input_token_cost_priority":7.5e-9},"list_pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1.2e-6,"cache_read_input_token_cost":6e-9,"input_cost_per_token_priority":3.75e-7,"output_cost_per_token_priority":1.5e-6,"cache_read_input_token_cost_priority":7.5e-9},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"deepinfra/deepseek-ai/DeepSeek-V4.1-Flash","object":"model","created":1789021285,"owned_by":"deepinfra","model_name":"deepseek-ai/DeepSeek-V4.1-Flash","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":393216,"quantization":"fp8","retirement_date":null,"description":"DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.0000000000000002e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":6e-9},"list_pricing":{"input_cost_per_token":2.0000000000000002e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":6e-9},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"qwen/deepseek-v4.1-flash","object":"model","created":1789021285,"owned_by":"qwen","model_name":"deepseek-v4.1-flash","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":393216,"quantization":null,"retirement_date":null,"description":"DeepSeek-V4.1-Flash is the lightweight flagship of DeepSeek's new architecture family, packing 552B total MoE parameters to deliver flagship-surpassing intelligence across key benchmarks, including out-performing DeepSeek-V4-Pro. It adopts a Causal Encoder-Decoder asymmetric design with 8B active parameters for input and 16B for output, and offers native multimodal visual understanding. KV Cache usage is cut to one-quarter of the previous generation's HBM and one-eighth of its SSD storage, dramatically lowering costs for long-context and agentic workloads. With a 1M-token context window and up to 384K-token maximum output, it balances high throughput, low latency, and exceptional cost efficiency.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":9.749999999999999e-8,"output_cost_per_token":3.8999999999999997e-7,"cache_read_input_token_cost":1.95e-9},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":3e-9},"discount":0.35,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null},{"id":"together_ai/deepseek-ai/DeepSeek-V4.1-Flash","object":"model","created":1789021285,"owned_by":"together_ai","model_name":"deepseek-ai/DeepSeek-V4.1-Flash","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":393216,"quantization":null,"retirement_date":null,"description":"DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1.2e-6,"cache_read_input_token_cost":6e-9},"list_pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1.2e-6,"cache_read_input_token_cost":6e-9},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null},{"id":"deepseek/deepseek-v4-flash-vision-exp","object":"model","created":1787311563,"owned_by":"deepseek","model_name":"deepseek-v4-flash-vision-exp","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":393216,"quantization":null,"retirement_date":null,"description":"DeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of DeepSeek V4 Flash 0731 from DeepSeek, adding image understanding while matching the base model on text capabilities including agents,...","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":3e-9,"input_cost_per_token_cache_hit":6e-9,"cache_creation_input_token_cost":0.0},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":3e-9,"input_cost_per_token_cache_hit":6e-9,"cache_creation_input_token_cost":0.0},"discount":null,"discount_ends_at":null,"regions":[{"code":"ap","name":"Asia"}],"zero_data_retention":false,"alias_of":null},{"id":"deepseek/deepseek-v4-flash","object":"model","created":1777000666,"owned_by":"deepseek","model_name":"deepseek-v4-flash","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":393216,"quantization":null,"retirement_date":null,"description":"DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":3e-9,"input_cost_per_token_cache_hit":6e-9,"cache_creation_input_token_cost":0.0},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":3e-9,"input_cost_per_token_cache_hit":6e-9,"cache_creation_input_token_cost":0.0},"discount":null,"discount_ends_at":null,"regions":[{"code":"ap","name":"Asia"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":16},{"id":"gemma-4-26b-a4b-it","object":"model","created":1792768060,"owned_by":"google","mode":"chat","context_length":262144,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":0.0,"output_cost_per_token":0.0},"pricing_endpoint":"google/gemma-4-26b-a4b-it","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"arkanecloud/gemma4-26b","object":"model","created":1792768060,"owned_by":"arkanecloud","model_name":"gemma4-26b","context_length":262144,"max_input_tokens":null,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-8,"output_cost_per_token":1e-7,"cache_read_input_token_cost":5e-8},"list_pricing":{"input_cost_per_token":5e-8,"output_cost_per_token":1e-7,"cache_read_input_token_cost":5e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null},{"id":"flexai/gemma-4-26B-A4B-it@eu","object":"model","created":1786610410,"owned_by":"flexai","model_name":"gemma-4-26B-A4B-it","context_length":262144,"max_input_tokens":null,"max_output_tokens":32768,"quantization":null,"retirement_date":null,"description":"Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6.7e-8,"output_cost_per_token":2.9e-7,"cache_read_input_token_cost":1e-8},"list_pricing":{"input_cost_per_token":6.7e-8,"output_cost_per_token":2.9e-7,"cache_read_input_token_cost":1e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"flexai/gemma-4-26B-A4B-it","object":"model","created":1786610410,"owned_by":"flexai","model_name":"gemma-4-26B-A4B-it","context_length":262144,"max_input_tokens":null,"max_output_tokens":32768,"quantization":null,"retirement_date":null,"description":"Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6.7e-8,"output_cost_per_token":2.9e-7,"cache_read_input_token_cost":1e-8},"list_pricing":{"input_cost_per_token":6.7e-8,"output_cost_per_token":2.9e-7,"cache_read_input_token_cost":1e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"scaleway/gemma-4-26b-a4b-it","object":"model","created":1777469299,"owned_by":"scaleway","model_name":"gemma-4-26b-a4b-it","context_length":256000,"max_input_tokens":null,"max_output_tokens":32768,"quantization":null,"retirement_date":null,"description":"Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.753501076618921e-7,"output_cost_per_token":5.507002153237842e-7},"list_pricing":{"input_cost_per_token":2.753501076618921e-7,"output_cost_per_token":5.507002153237842e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"cloudflare/@cf/google/gemma-4-26b-a4b-it","object":"model","created":1775227989,"owned_by":"cloudflare","model_name":"@cf/google/gemma-4-26b-a4b-it","context_length":256000,"max_input_tokens":256000,"max_output_tokens":32768,"quantization":null,"retirement_date":null,"description":"Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind.","source":null,"capabilities":{"input_modalities":["image","text","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.0000000000000001e-7,"output_cost_per_token":3e-7,"cache_read_input_token_cost":5.0000000000000004e-8},"list_pricing":{"input_cost_per_token":1.0000000000000001e-7,"output_cost_per_token":3e-7,"cache_read_input_token_cost":5.0000000000000004e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"deepinfra/google/gemma-4-26B-A4B-it","object":"model","created":1775227989,"owned_by":"deepinfra","model_name":"google/gemma-4-26B-A4B-it","context_length":262144,"max_input_tokens":262144,"max_output_tokens":16384,"quantization":"fp8","retirement_date":null,"description":"Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind.","source":null,"capabilities":{"input_modalities":["image","text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":7e-8,"output_cost_per_token":3.4e-7},"list_pricing":{"input_cost_per_token":7e-8,"output_cost_per_token":3.4e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"google/gemma-4-26b-a4b-it","object":"model","created":1775227989,"owned_by":"google","model_name":"gemma-4-26b-a4b-it","context_length":262144,"max_input_tokens":262144,"max_output_tokens":32768,"quantization":null,"retirement_date":null,"description":"Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind.","source":null,"capabilities":{"input_modalities":["image","text","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":0.0,"output_cost_per_token":0.0},"list_pricing":{"input_cost_per_token":0.0,"output_cost_per_token":0.0},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"vertex/google/gemma-4-26b-a4b-it-maas@eu","object":"model","created":1775227989,"owned_by":"vertex","model_name":"google/gemma-4-26b-a4b-it-maas","context_length":262144,"max_input_tokens":262144,"max_output_tokens":32768,"quantization":null,"retirement_date":null,"description":"Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind.","source":null,"capabilities":{"input_modalities":["image","text","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.65e-7,"output_cost_per_token":6.6e-7,"cache_read_input_token_cost":1.65e-8},"list_pricing":{"input_cost_per_token":1.65e-7,"output_cost_per_token":6.6e-7,"cache_read_input_token_cost":1.65e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"vertex/google/gemma-4-26b-a4b-it-maas","object":"model","created":1775227989,"owned_by":"vertex","model_name":"google/gemma-4-26b-a4b-it-maas","context_length":262144,"max_input_tokens":262144,"max_output_tokens":32768,"quantization":null,"retirement_date":null,"description":"Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind.","source":null,"capabilities":{"input_modalities":["image","text","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":1.5e-8},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":1.5e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"vertex/google/gemma-4-26b-a4b-it-maas@us","object":"model","created":1775227989,"owned_by":"vertex","model_name":"google/gemma-4-26b-a4b-it-maas","context_length":262144,"max_input_tokens":262144,"max_output_tokens":32768,"quantization":null,"retirement_date":null,"description":"Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind.","source":null,"capabilities":{"input_modalities":["image","text","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.65e-7,"output_cost_per_token":6.6e-7,"cache_read_input_token_cost":1.65e-8},"list_pricing":{"input_cost_per_token":1.65e-7,"output_cost_per_token":6.6e-7,"cache_read_input_token_cost":1.65e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":10},{"id":"gemma-4-31b-it","object":"model","created":1792768060,"owned_by":"google","mode":"chat","context_length":262144,"capabilities":{"input_modalities":["text","image","video","audio"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":0.0,"output_cost_per_token":0.0},"pricing_endpoint":"google/gemma-4-31b-it","regions":[{"code":"ch","name":"Switzerland"},{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"arkanecloud/gemma4-31b","object":"model","created":1792768060,"owned_by":"arkanecloud","model_name":"gemma4-31b","context_length":131072,"max_input_tokens":null,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":2e-7,"cache_read_input_token_cost":1e-7},"list_pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":2e-7,"cache_read_input_token_cost":1e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"},{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"infomaniak/google/gemma-4-31B-it","object":"model","created":1792029544,"owned_by":"infomaniak","model_name":"google/gemma-4-31B-it","context_length":100000,"max_input_tokens":null,"max_output_tokens":32768,"quantization":null,"retirement_date":null,"description":"Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.2028008612951367e-7,"output_cost_per_token":4.4056017225902734e-7},"list_pricing":{"input_cost_per_token":2.2028008612951367e-7,"output_cost_per_token":4.4056017225902734e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"ch","name":"Switzerland"}],"zero_data_retention":true,"alias_of":null},{"id":"greenpt/gemma4","object":"model","created":1791839241,"owned_by":"greenpt","model_name":"gemma4","context_length":256000,"max_input_tokens":null,"max_output_tokens":32000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5.507002153237842e-7,"output_cost_per_token":1.6521006459713525e-6},"list_pricing":{"input_cost_per_token":5.507002153237842e-7,"output_cost_per_token":1.6521006459713525e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"greenference/gemma-4-31b-it","object":"model","created":1790948154,"owned_by":"greenference","model_name":"gemma-4-31b-it","context_length":262144,"max_input_tokens":null,"max_output_tokens":262141,"quantization":null,"retirement_date":null,"description":"Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.485e-7,"output_cost_per_token":4.2e-7,"input_cost_per_image_token":0.0,"cache_read_input_token_cost":5.775e-8,"cache_creation_input_token_cost":0.0},"list_pricing":{"input_cost_per_token":1.485e-7,"output_cost_per_token":4.2e-7,"input_cost_per_image_token":0.0,"cache_read_input_token_cost":5.775e-8,"cache_creation_input_token_cost":0.0},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"flexai/gemma-4-31b-it@eu","object":"model","created":1786610410,"owned_by":"flexai","model_name":"gemma-4-31b-it","context_length":262144,"max_input_tokens":null,"max_output_tokens":32768,"quantization":null,"retirement_date":null,"description":"Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.4e-7,"output_cost_per_token":4e-7,"cache_read_input_token_cost":2.1e-8},"list_pricing":{"input_cost_per_token":1.4e-7,"output_cost_per_token":4e-7,"cache_read_input_token_cost":2.1e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"flexai/gemma-4-31b-it","object":"model","created":1786610410,"owned_by":"flexai","model_name":"gemma-4-31b-it","context_length":262144,"max_input_tokens":null,"max_output_tokens":32768,"quantization":null,"retirement_date":null,"description":"Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.4e-7,"output_cost_per_token":4e-7,"cache_read_input_token_cost":2.1e-8},"list_pricing":{"input_cost_per_token":1.4e-7,"output_cost_per_token":4e-7,"cache_read_input_token_cost":2.1e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"deepinfra/google/gemma-4-31B-it","object":"model","created":1775148486,"owned_by":"deepinfra","model_name":"google/gemma-4-31B-it","context_length":262144,"max_input_tokens":262144,"max_output_tokens":16384,"quantization":"fp8","retirement_date":null,"description":"Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output.","source":null,"capabilities":{"input_modalities":["image","text","video","audio"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.0000000000000002e-7,"output_cost_per_token":4.0000000000000003e-7,"cache_read_input_token_cost":7.5e-8},"list_pricing":{"input_cost_per_token":2.0000000000000002e-7,"output_cost_per_token":4.0000000000000003e-7,"cache_read_input_token_cost":7.5e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"google/gemma-4-31b-it","object":"model","created":1775148486,"owned_by":"google","model_name":"gemma-4-31b-it","context_length":262144,"max_input_tokens":262144,"max_output_tokens":32768,"quantization":null,"retirement_date":null,"description":"Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output.","source":null,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":0.0,"output_cost_per_token":0.0},"list_pricing":{"input_cost_per_token":0.0,"output_cost_per_token":0.0},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":8},{"id":"gemma-4-e4b-it","object":"model","created":1792768060,"owned_by":"google","mode":"chat","context_length":131072,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-8,"output_cost_per_token":1.0000000000000001e-7},"pricing_endpoint":"deepinfra/google/gemma-4-E4B-it","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"arkanecloud/gemma4-4b","object":"model","created":1792768060,"owned_by":"arkanecloud","model_name":"gemma4-4b","context_length":131072,"max_input_tokens":null,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-8,"output_cost_per_token":5e-8,"cache_read_input_token_cost":5e-8},"list_pricing":{"input_cost_per_token":5e-8,"output_cost_per_token":5e-8,"cache_read_input_token_cost":5e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null},{"id":"deepinfra/google/gemma-4-E4B-it","object":"model","created":1784092401,"owned_by":"deepinfra","model_name":"google/gemma-4-E4B-it","context_length":131072,"max_input_tokens":null,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-8,"output_cost_per_token":1.0000000000000001e-7},"list_pricing":{"input_cost_per_token":2e-8,"output_cost_per_token":1.0000000000000001e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"glm-5.3","object":"model","created":1792768060,"owned_by":"zai","mode":"chat","context_length":1048576,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":6.4e-7,"cache_read_input_token_cost":1.8e-8},"pricing_endpoint":"compactifai/glm-5-3","regions":[{"code":"ap","name":"Asia"},{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"arkanecloud/zai-org/GLM-5.3","object":"model","created":1792768060,"owned_by":"arkanecloud","model_name":"zai-org/GLM-5.3","context_length":200000,"max_input_tokens":null,"max_output_tokens":100000,"quantization":null,"retirement_date":null,"description":"GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.4e-6,"output_cost_per_token":4.4e-6,"cache_read_input_token_cost":3e-7},"list_pricing":{"input_cost_per_token":1.4e-6,"output_cost_per_token":4.4e-6,"cache_read_input_token_cost":3e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"},{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"sference/zai-org/GLM-5.3","object":"model","created":1792636080,"owned_by":"sference","model_name":"zai-org/GLM-5.3","context_length":1048576,"max_input_tokens":null,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.2e-6,"output_cost_per_token":4.2e-6,"cache_read_input_token_cost":2.6e-7},"list_pricing":{"input_cost_per_token":1.2e-6,"output_cost_per_token":4.2e-6,"cache_read_input_token_cost":2.6e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"greenpt/glm-5.3","object":"model","created":1791839241,"owned_by":"greenpt","model_name":"glm-5.3","context_length":1000000,"max_input_tokens":null,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.2115404737123252e-6,"output_cost_per_token":4.846161894849301e-6,"cache_read_input_token_cost":3.028851184280813e-7},"list_pricing":{"input_cost_per_token":1.2115404737123252e-6,"output_cost_per_token":4.846161894849301e-6,"cache_read_input_token_cost":3.028851184280813e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"scaleway/glm-5.3","object":"model","created":1791474730,"owned_by":"scaleway","model_name":"glm-5.3","context_length":256000,"max_input_tokens":null,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.982520775165623e-6,"output_cost_per_token":6.057702368561627e-6},"list_pricing":{"input_cost_per_token":1.982520775165623e-6,"output_cost_per_token":6.057702368561627e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"tencent/glm-5.3","object":"model","created":1790867221,"owned_by":"tencent","model_name":"glm-5.3","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.4e-6,"output_cost_per_token":4.4e-6,"cache_read_input_token_cost":2.6e-7,"input_cost_per_token_cache_hit":2.6e-7,"cache_creation_input_token_cost":0.0},"list_pricing":{"input_cost_per_token":1.4e-6,"output_cost_per_token":4.4e-6,"cache_read_input_token_cost":2.6e-7,"input_cost_per_token_cache_hit":2.6e-7,"cache_creation_input_token_cost":0.0},"discount":null,"discount_ends_at":null,"regions":[{"code":"ap","name":"Asia"}],"zero_data_retention":true,"alias_of":null},{"id":"mistral/zai-glm-5-3@eu","object":"model","created":1789621775,"owned_by":"mistral","model_name":"zai-glm-5-3","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.54e-6,"output_cost_per_token":4.84e-6,"cache_read_input_token_cost":1.5400000000000003e-7,"input_cost_per_token_batches":7.7e-7,"output_cost_per_token_batches":2.42e-6,"cache_read_input_token_cost_batches":7.700000000000001e-8},"list_pricing":{"input_cost_per_token":1.54e-6,"output_cost_per_token":4.84e-6,"cache_read_input_token_cost":1.5400000000000003e-7,"input_cost_per_token_batches":7.7e-7,"output_cost_per_token_batches":2.42e-6,"cache_read_input_token_cost_batches":7.700000000000001e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"mistral/zai-glm-5-3","object":"model","created":1789621775,"owned_by":"mistral","model_name":"zai-glm-5-3","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.4e-6,"output_cost_per_token":4.4e-6,"cache_read_input_token_cost":1.4e-7,"input_cost_per_token_batches":7e-7,"output_cost_per_token_batches":2.2e-6,"cache_read_input_token_cost_batches":7e-8},"list_pricing":{"input_cost_per_token":1.4e-6,"output_cost_per_token":4.4e-6,"cache_read_input_token_cost":1.4e-7,"input_cost_per_token_batches":7e-7,"output_cost_per_token_batches":2.2e-6,"cache_read_input_token_cost_batches":7e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"databricks/databricks-glm-5-3","object":"model","created":1788671370,"owned_by":"databricks","model_name":"databricks-glm-5-3","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"GLM-5.3 is a text-only mixture-of-experts language model developed by Zhipu AI. It supports a context length of 1,048,576 tokens, function calling, structured output, coding, and agentic tool use. Reasoning is always enabled with low, high, and max effort levels; max is the default.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.4e-6,"output_cost_per_token":4.4e-6,"input_dbu_cost_per_token":0.00002,"output_dbu_cost_per_token":0.000062857,"cache_read_input_token_cost":1.4e-7,"input_cost_per_token_priority":2.45e-6,"cache_creation_input_token_cost":1.4e-6,"cache_creation_input_token_cost_priority":2.45e-6},"list_pricing":{"input_cost_per_token":1.4e-6,"output_cost_per_token":4.4e-6,"input_dbu_cost_per_token":0.00002,"output_dbu_cost_per_token":0.000062857,"cache_read_input_token_cost":1.4e-7,"input_cost_per_token_priority":2.45e-6,"cache_creation_input_token_cost":1.4e-6,"cache_creation_input_token_cost_priority":2.45e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"compactifai/glm-5-3","object":"model","created":1788457256,"owned_by":"compactifai","model_name":"glm-5-3","context_length":null,"max_input_tokens":null,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":6.4e-7,"cache_read_input_token_cost":1.8e-8},"list_pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":6.4e-7,"cache_read_input_token_cost":1.8e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null},{"id":"compactifai/glm-5-3@us","object":"model","created":1788457256,"owned_by":"compactifai","model_name":"glm-5-3","context_length":null,"max_input_tokens":null,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":6.4e-7,"cache_read_input_token_cost":1.8e-8},"list_pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":6.4e-7,"cache_read_input_token_cost":1.8e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":null,"alias_of":null},{"id":"fireworks_ai/accounts/fireworks/models/glm-5p3","object":"model","created":1788066615,"owned_by":"fireworks_ai","model_name":"accounts/fireworks/models/glm-5p3","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.4e-6,"output_cost_per_token":4.4e-6,"cache_read_input_token_cost":2.6e-7,"input_cost_per_token_priority":1.75e-6,"output_cost_per_token_priority":5.5e-6,"cache_read_input_token_cost_priority":3.25e-7},"list_pricing":{"input_cost_per_token":1.4e-6,"output_cost_per_token":4.4e-6,"cache_read_input_token_cost":2.6e-7,"input_cost_per_token_priority":1.75e-6,"output_cost_per_token_priority":5.5e-6,"cache_read_input_token_cost_priority":3.25e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"tensorx/z-ai/glm-5.3","object":"model","created":1787980172,"owned_by":"tensorx","model_name":"z-ai/glm-5.3","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":64000,"quantization":"fp8","retirement_date":null,"description":"Served by TensorX at fp8 quantization.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.75e-6,"output_cost_per_token":4.5e-6,"cache_read_input_token_cost":4.375e-7},"list_pricing":{"input_cost_per_token":1.75e-6,"output_cost_per_token":4.5e-6,"cache_read_input_token_cost":4.375e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"cloudflare/@cf/zai-org/glm-5.3","object":"model","created":1787086655,"owned_by":"cloudflare","model_name":"@cf/zai-org/glm-5.3","context_length":1048576,"max_input_tokens":null,"max_output_tokens":131072,"quantization":null,"retirement_date":"2098-12-31","description":"GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.4e-6,"output_cost_per_token":4.4e-6,"cache_read_input_token_cost":2.6e-7},"list_pricing":{"input_cost_per_token":1.4e-6,"output_cost_per_token":4.4e-6,"cache_read_input_token_cost":2.6e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"deepinfra/zai-org/GLM-5.3","object":"model","created":1787086655,"owned_by":"deepinfra","model_name":"zai-org/GLM-5.3","context_length":1048576,"max_input_tokens":null,"max_output_tokens":131072,"quantization":"fp4","retirement_date":"2098-12-31","description":"GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":9.000000000000001e-7,"output_cost_per_token":4e-6,"cache_read_input_token_cost":1.99999998e-7},"list_pricing":{"input_cost_per_token":9.000000000000001e-7,"output_cost_per_token":4e-6,"cache_read_input_token_cost":1.99999998e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"nebius/zai-org/GLM-5.3","object":"model","created":1787086655,"owned_by":"nebius","model_name":"zai-org/GLM-5.3","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":1024000,"quantization":"fp4","retirement_date":null,"description":"GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.4e-6,"output_cost_per_token":4.4e-6,"cache_read_input_token_cost":1.4e-6},"list_pricing":{"input_cost_per_token":1.4e-6,"output_cost_per_token":4.4e-6,"cache_read_input_token_cost":1.4e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"qwen/glm-5.3","object":"model","created":1787086655,"owned_by":"qwen","model_name":"glm-5.3","context_length":1000000,"max_input_tokens":1048576,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"GLM-5.3 is Z.ai's latest flagship large language model, delivering state-of-the-art coding and agentic performance among open-source models, with a 50% improvement over its predecessor on Z.ai Code Bench and end-to-end delivery of production-grade results. It demonstrates emergent cybersecurity capability, achieving the best result to date on the CyberGym vulnerability discovery benchmark. With a 1M-token context window, 128K-token maximum output, and three reasoning effort levels, GLM-5.3 excels at long-horizon, complex tasks.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":9.1e-7,"output_cost_per_token":2.86e-6,"cache_read_input_token_cost":1.8200000000000002e-7},"list_pricing":{"input_cost_per_token":1.4e-6,"output_cost_per_token":4.4e-6,"cache_read_input_token_cost":2.8e-7},"discount":0.35,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null},{"id":"together_ai/zai-org/GLM-5.3","object":"model","created":1787086655,"owned_by":"together_ai","model_name":"zai-org/GLM-5.3","context_length":1048575,"max_input_tokens":1048575,"max_output_tokens":131072,"quantization":null,"retirement_date":"2098-12-31","description":"GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.4e-6,"output_cost_per_token":4.4e-6,"cache_read_input_token_cost":2.5999999999999995e-7},"list_pricing":{"input_cost_per_token":1.4e-6,"output_cost_per_token":4.4e-6,"cache_read_input_token_cost":2.5999999999999995e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null},{"id":"zai/glm-5.3","object":"model","created":1787086655,"owned_by":"zai","model_name":"glm-5.3","context_length":1048576,"max_input_tokens":1000000,"max_output_tokens":131072,"quantization":"fp8","retirement_date":"2098-12-31","description":"GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.4e-6,"output_cost_per_token":4.4e-6,"cache_read_input_token_cost":2.6e-7,"cache_creation_input_token_cost":0.0},"list_pricing":{"input_cost_per_token":1.4e-6,"output_cost_per_token":4.4e-6,"cache_read_input_token_cost":2.6e-7,"cache_creation_input_token_cost":0.0},"discount":null,"discount_ends_at":null,"regions":[{"code":"ap","name":"Asia"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":18},{"id":"kimi-k3","object":"model","created":1792768060,"owned_by":"moonshot","mode":"chat","context_length":1048576,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.95e-6,"output_cost_per_token":9.75e-6,"cache_read_input_token_cost":1.9499999999999999e-7},"pricing_endpoint":"qwen/kimi-k3","regions":[{"code":"ap","name":"Asia"},{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"arkanecloud/moonshotai/Kimi-K3","object":"model","created":1792768060,"owned_by":"arkanecloud","model_name":"moonshotai/Kimi-K3","context_length":1000000,"max_input_tokens":null,"max_output_tokens":500000,"quantization":null,"retirement_date":null,"description":"Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"cache_read_input_token_cost":3e-7},"list_pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"cache_read_input_token_cost":3e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null},{"id":"greenpt/kimi-k3","object":"model","created":1791839241,"owned_by":"greenpt","model_name":"kimi-k3","context_length":1000000,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.634621421136976e-6,"output_cost_per_token":0.00001817310710568488,"cache_read_input_token_cost":9.08655355284244e-7},"list_pricing":{"input_cost_per_token":3.634621421136976e-6,"output_cost_per_token":0.00001817310710568488,"cache_read_input_token_cost":9.08655355284244e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"tencent/kimi-k3","object":"model","created":1790867221,"owned_by":"tencent","model_name":"kimi-k3","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"cache_read_input_token_cost":3e-7,"input_cost_per_token_cache_hit":3e-7,"cache_creation_input_token_cost":0.0},"list_pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"cache_read_input_token_cost":3e-7,"input_cost_per_token_cache_hit":3e-7,"cache_creation_input_token_cost":0.0},"discount":null,"discount_ends_at":null,"regions":[{"code":"ap","name":"Asia"}],"zero_data_retention":true,"alias_of":null},{"id":"databricks/databricks-kimi-k3","object":"model","created":1787893793,"owned_by":"databricks","model_name":"databricks-kimi-k3","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"Kimi K3 is a 2.8T-parameter model developed by Moonshot AI with native vision capabilities. The model supports a context length of 1M tokens and is designed for long-horizon coding, knowledge work, and reasoning.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"input_dbu_cost_per_token":0.000042857,"output_dbu_cost_per_token":0.000214286,"cache_read_input_token_cost":3e-7,"cache_creation_input_token_cost":3e-6,"cache_creation_input_token_cost_priority":5.25e-6},"list_pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"input_dbu_cost_per_token":0.000042857,"output_dbu_cost_per_token":0.000214286,"cache_read_input_token_cost":3e-7,"cache_creation_input_token_cost":3e-6,"cache_creation_input_token_cost_priority":5.25e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"tensorx/moonshotai/kimi-k3","object":"model","created":1787003349,"owned_by":"tensorx","model_name":"moonshotai/kimi-k3","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":64000,"quantization":"fp4","retirement_date":null,"description":"Served by TensorX at mxfp4 quantization.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"cache_read_input_token_cost":7.5e-7},"list_pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"cache_read_input_token_cost":7.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/moonshotai.kimi-k3","object":"model","created":1784215858,"owned_by":"amazon","model_name":"moonshotai.kimi-k3","context_length":1048576,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"cache_read_input_token_cost":3e-7,"cache_creation_input_token_cost":3.75e-6},"list_pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"cache_read_input_token_cost":3e-7,"cache_creation_input_token_cost":3.75e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/moonshotai.kimi-k3@us","object":"model","created":1784215858,"owned_by":"amazon","model_name":"moonshotai.kimi-k3","context_length":1048576,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"cache_read_input_token_cost":3e-7,"cache_creation_input_token_cost":3.75e-6},"list_pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"cache_read_input_token_cost":3e-7,"cache_creation_input_token_cost":3.75e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"deepinfra/moonshotai/Kimi-K3","object":"model","created":1784215858,"owned_by":"deepinfra","model_name":"moonshotai/Kimi-K3","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":16384,"quantization":"fp4","retirement_date":null,"description":"Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.85e-6,"output_cost_per_token":0.00001425,"cache_read_input_token_cost":2.8499999999999997e-7},"list_pricing":{"input_cost_per_token":2.85e-6,"output_cost_per_token":0.00001425,"cache_read_input_token_cost":2.8499999999999997e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"fireworks_ai/accounts/fireworks/models/kimi-k3","object":"model","created":1784215858,"owned_by":"fireworks_ai","model_name":"accounts/fireworks/models/kimi-k3","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI.","source":null,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"cache_read_input_token_cost":3e-7,"input_cost_per_token_priority":3.75e-6,"output_cost_per_token_priority":0.00001875,"cache_read_input_token_cost_priority":3.75e-7},"list_pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"cache_read_input_token_cost":3e-7,"input_cost_per_token_priority":3.75e-6,"output_cost_per_token_priority":0.00001875,"cache_read_input_token_cost_priority":3.75e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"fireworks_ai/kimi-k3","object":"model","created":1784215858,"owned_by":"fireworks_ai","model_name":"kimi-k3","context_length":1048576,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at...","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"cache_read_input_token_cost":3e-7},"list_pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"cache_read_input_token_cost":3e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"moonshot/kimi-k3","object":"model","created":1784215858,"owned_by":"moonshot","model_name":"kimi-k3","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI.","source":null,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"cache_read_input_token_cost":3e-7,"cache_creation_input_token_cost":3e-6,"cache_creation_input_token_cost_above_1hr":6e-6},"list_pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"cache_read_input_token_cost":3e-7,"cache_creation_input_token_cost":3e-6,"cache_creation_input_token_cost_above_1hr":6e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"ap","name":"Asia"}],"zero_data_retention":false,"alias_of":null},{"id":"nebius/moonshotai/Kimi-K3","object":"model","created":1784215858,"owned_by":"nebius","model_name":"moonshotai/Kimi-K3","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":1024000,"quantization":"fp4","retirement_date":null,"description":"Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"cache_read_input_token_cost":3e-6},"list_pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"cache_read_input_token_cost":3e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"qwen/kimi-k3","object":"model","created":1784215858,"owned_by":"qwen","model_name":"kimi-k3","context_length":1000000,"max_input_tokens":1048576,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"Kimi-K3 is Moonshot AI’s most capable flagship model to date, featuring 2.8 trillion parameters. Built on the KDA hybrid linear attention mechanism (Kimi Delta Attention) and Attention Residuals, it natively supports visual understanding and offers a 1-million-token context window. As the world's first open-source model at the 3-trillion-parameter scale, it is designed for frontier intelligence scenarios such as long-horizon programming, knowledge work, and reasoning.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.95e-6,"output_cost_per_token":9.75e-6,"cache_read_input_token_cost":1.9499999999999999e-7},"list_pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"cache_read_input_token_cost":3e-7},"discount":0.35,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null},{"id":"together_ai/moonshotai/Kimi-K3","object":"model","created":1784215858,"owned_by":"together_ai","model_name":"moonshotai/Kimi-K3","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI.","source":null,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"cache_read_input_token_cost":3e-7},"list_pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"cache_read_input_token_cost":3e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":14},{"id":"minimax-m2.5","object":"model","created":1792768060,"owned_by":"minimax","mode":"chat","context_length":1000000,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":1.15e-6,"cache_read_input_token_cost":3e-8},"pricing_endpoint":"deepinfra/MiniMaxAI/MiniMax-M2.5","regions":[{"code":"ap","name":"Asia"},{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"arkanecloud/MiniMaxAI/MiniMax-M2.5","object":"model","created":1792768060,"owned_by":"arkanecloud","model_name":"MiniMaxAI/MiniMax-M2.5","context_length":196000,"max_input_tokens":null,"max_output_tokens":98000,"quantization":null,"retirement_date":null,"description":"MiniMax-M2.5 is a SOTA large language model designed for real-world productivity.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1.2e-6,"cache_read_input_token_cost":1e-7},"list_pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1.2e-6,"cache_read_input_token_cost":1e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"},{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"greenpt/minimax-m2.5","object":"model","created":1791839241,"owned_by":"greenpt","model_name":"minimax-m2.5","context_length":1000000,"max_input_tokens":null,"max_output_tokens":64000,"quantization":null,"retirement_date":null,"description":"MiniMax-M2.5 is a SOTA large language model designed for real-world productivity.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4.846161894849301e-7,"output_cost_per_token":2.4230809474246504e-6,"cache_read_input_token_cost":1.2115404737123253e-7},"list_pricing":{"input_cost_per_token":4.846161894849301e-7,"output_cost_per_token":2.4230809474246504e-6,"cache_read_input_token_cost":1.2115404737123253e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"tensorx/minimax/minimax-m2.5","object":"model","created":1787003349,"owned_by":"tensorx","model_name":"minimax/minimax-m2.5","context_length":196608,"max_input_tokens":196608,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"Served by TensorX at fp8 quantization.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1.2e-6,"cache_read_input_token_cost":7.5e-8},"list_pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1.2e-6,"cache_read_input_token_cost":7.5e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/minimax.minimax-m2.5","object":"model","created":1775193119,"owned_by":"amazon","model_name":"minimax.minimax-m2.5","context_length":196000,"max_input_tokens":196000,"max_output_tokens":8192,"quantization":null,"retirement_date":null,"description":"MiniMax-M2.5 is a SOTA large language model designed for real-world productivity.","source":"https://aws.amazon.com/bedrock/pricing/","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.6e-7,"output_cost_per_token":1.44e-6,"input_cost_per_token_flex":1.8e-7,"output_cost_per_token_flex":7.2e-7,"input_cost_per_token_priority":6.3e-7,"output_cost_per_token_priority":2.52e-6},"list_pricing":{"input_cost_per_token":3.6e-7,"output_cost_per_token":1.44e-6,"input_cost_per_token_flex":1.8e-7,"output_cost_per_token_flex":7.2e-7,"input_cost_per_token_priority":6.3e-7,"output_cost_per_token_priority":2.52e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/minimax.minimax-m2.5@us","object":"model","created":1775193119,"owned_by":"amazon","model_name":"minimax.minimax-m2.5","context_length":196000,"max_input_tokens":196000,"max_output_tokens":8192,"quantization":null,"retirement_date":null,"description":"MiniMax-M2.5 is a SOTA large language model designed for real-world productivity.","source":"https://aws.amazon.com/bedrock/pricing/","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.6e-7,"output_cost_per_token":1.44e-6,"input_cost_per_token_flex":1.8e-7,"output_cost_per_token_flex":7.2e-7,"input_cost_per_token_priority":6.3e-7,"output_cost_per_token_priority":2.52e-6},"list_pricing":{"input_cost_per_token":3.6e-7,"output_cost_per_token":1.44e-6,"input_cost_per_token_flex":1.8e-7,"output_cost_per_token_flex":7.2e-7,"input_cost_per_token_priority":6.3e-7,"output_cost_per_token_priority":2.52e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"deepinfra/MiniMaxAI/MiniMax-M2.5","object":"model","created":1770908502,"owned_by":"deepinfra","model_name":"MiniMaxAI/MiniMax-M2.5","context_length":196608,"max_input_tokens":null,"max_output_tokens":196608,"quantization":null,"retirement_date":null,"description":"MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon the coding expertise of M2.1...","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":1.15e-6,"cache_read_input_token_cost":3e-8},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":1.15e-6,"cache_read_input_token_cost":3e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"minimax/MiniMax-M2.5","object":"model","created":1770908502,"owned_by":"minimax","model_name":"MiniMax-M2.5","context_length":204800,"max_input_tokens":null,"max_output_tokens":196000,"quantization":null,"retirement_date":null,"description":"MiniMax-M2.5 is a SOTA large language model designed for real-world productivity.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1.2e-6,"cache_read_input_token_cost":3e-8},"list_pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1.2e-6,"cache_read_input_token_cost":3e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"ap","name":"Asia"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":7},{"id":"minimax-m3","object":"model","created":1792768060,"owned_by":"minimax","mode":"chat","context_length":1048576,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.8e-7,"output_cost_per_token":1.1e-6,"cache_read_input_token_cost":5.6000000000000005e-8},"pricing_endpoint":"deepinfra/MiniMaxAI/MiniMax-M3","regions":[{"code":"ap","name":"Asia"},{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"arkanecloud/MiniMaxAI/MiniMax-M3","object":"model","created":1792768060,"owned_by":"arkanecloud","model_name":"MiniMaxAI/MiniMax-M3","context_length":1000000,"max_input_tokens":null,"max_output_tokens":500000,"quantization":null,"retirement_date":null,"description":"MiniMax-M3 is a multimodal foundation model from MiniMax.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1.2e-6,"cache_read_input_token_cost":6e-8},"list_pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1.2e-6,"cache_read_input_token_cost":6e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null},{"id":"greenpt/minimax-m3","object":"model","created":1791839241,"owned_by":"greenpt","model_name":"minimax-m3","context_length":1000000,"max_input_tokens":null,"max_output_tokens":64000,"quantization":null,"retirement_date":null,"description":"MiniMax-M3 is a multimodal foundation model from MiniMax.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4.846161894849301e-7,"output_cost_per_token":2.4230809474246504e-6,"cache_read_input_token_cost":1.2115404737123253e-7},"list_pricing":{"input_cost_per_token":4.846161894849301e-7,"output_cost_per_token":2.4230809474246504e-6,"cache_read_input_token_cost":1.2115404737123253e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"tencent/minimax-m3","object":"model","created":1790867221,"owned_by":"tencent","model_name":"minimax-m3","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":512000,"quantization":null,"retirement_date":null,"description":"MiniMax-M3 is a multimodal foundation model from MiniMax.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1.2e-6,"cache_read_input_token_cost":6e-8,"input_cost_per_token_cache_hit":6e-8,"cache_creation_input_token_cost":0.0,"input_cost_per_token_above_512k_tokens":6e-7,"output_cost_per_token_above_512k_tokens":2.4e-6,"cache_read_input_token_cost_above_512k_tokens":1.2e-7},"list_pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1.2e-6,"cache_read_input_token_cost":6e-8,"input_cost_per_token_cache_hit":6e-8,"cache_creation_input_token_cost":0.0,"input_cost_per_token_above_512k_tokens":6e-7,"output_cost_per_token_above_512k_tokens":2.4e-6,"cache_read_input_token_cost_above_512k_tokens":1.2e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"ap","name":"Asia"}],"zero_data_retention":true,"alias_of":null},{"id":"tensorx/minimax/minimax-m3","object":"model","created":1787003349,"owned_by":"tensorx","model_name":"minimax/minimax-m3","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":64000,"quantization":null,"retirement_date":null,"description":"Served by TensorX at fp8 quantization.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4e-7,"output_cost_per_token":2e-6,"cache_read_input_token_cost":1e-7},"list_pricing":{"input_cost_per_token":4e-7,"output_cost_per_token":2e-6,"cache_read_input_token_cost":1e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"fireworks_ai/accounts/fireworks/models/minimax-m3","object":"model","created":1785320305,"owned_by":"fireworks_ai","model_name":"accounts/fireworks/models/minimax-m3","context_length":512000,"max_input_tokens":512000,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"MiniMax-M3 is a multimodal foundation model from MiniMax.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1.2e-6,"cache_read_input_token_cost":6e-8,"input_cost_per_token_priority":4.5e-7,"output_cost_per_token_priority":1.8e-6,"cache_read_input_token_cost_priority":9e-8},"list_pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1.2e-6,"cache_read_input_token_cost":6e-8,"input_cost_per_token_priority":4.5e-7,"output_cost_per_token_priority":1.8e-6,"cache_read_input_token_cost_priority":9e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"nebius/MiniMaxAI/MiniMax-M3","object":"model","created":1783732576,"owned_by":"nebius","model_name":"MiniMaxAI/MiniMax-M3","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":512000,"quantization":null,"retirement_date":null,"description":"MiniMax-M3 is a multimodal foundation model from MiniMax.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1.2e-6,"cache_read_input_token_cost":3e-7},"list_pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1.2e-6,"cache_read_input_token_cost":3e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"deepinfra/MiniMaxAI/MiniMax-M3","object":"model","created":1780245374,"owned_by":"deepinfra","model_name":"MiniMaxAI/MiniMax-M3","context_length":524288,"max_input_tokens":524288,"max_output_tokens":131072,"quantization":"fp8","retirement_date":null,"description":"MiniMax-M3 is a multimodal foundation model from MiniMax.","source":null,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.8e-7,"output_cost_per_token":1.1e-6,"cache_read_input_token_cost":5.6000000000000005e-8},"list_pricing":{"input_cost_per_token":2.8e-7,"output_cost_per_token":1.1e-6,"cache_read_input_token_cost":5.6000000000000005e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"minimax/MiniMax-M3","object":"model","created":1780245374,"owned_by":"minimax","model_name":"MiniMax-M3","context_length":524288,"max_input_tokens":524288,"max_output_tokens":512000,"quantization":null,"retirement_date":null,"description":"MiniMax-M3 is a multimodal foundation model from MiniMax.","source":null,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1.2e-6,"cache_read_input_token_cost":6e-8},"list_pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1.2e-6,"cache_read_input_token_cost":6e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"ap","name":"Asia"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":8},{"id":"ministral-14b","object":"model","created":1792768060,"owned_by":"mistral","mode":"chat","context_length":32768,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":1.5e-7,"cache_read_input_token_cost":1.5e-7},"pricing_endpoint":"arkanecloud/ministral-14b","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"arkanecloud/ministral-14b","object":"model","created":1792768060,"owned_by":"arkanecloud","model_name":"ministral-14b","context_length":32768,"max_input_tokens":null,"max_output_tokens":16384,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":1.5e-7,"cache_read_input_token_cost":1.5e-7},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":1.5e-7,"cache_read_input_token_cost":1.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"},{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":1},{"id":"ministral-8b","object":"model","created":1792768060,"owned_by":"mistral","mode":"chat","context_length":131072,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":1e-7,"cache_read_input_token_cost":1e-7},"pricing_endpoint":"arkanecloud/ministral-8b","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"arkanecloud/ministral-8b","object":"model","created":1792768060,"owned_by":"arkanecloud","model_name":"ministral-8b","context_length":131072,"max_input_tokens":null,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":1e-7,"cache_read_input_token_cost":1e-7},"list_pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":1e-7,"cache_read_input_token_cost":1e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":1},{"id":"mistral-medium-3.5-128b","object":"model","created":1792768060,"owned_by":"mistral","mode":"chat","context_length":262144,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-6,"output_cost_per_token":7.5e-6,"cache_read_input_token_cost":3e-7},"pricing_endpoint":"arkanecloud/mistralai/Mistral-Medium-3.5-128B","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"arkanecloud/mistralai/Mistral-Medium-3.5-128B","object":"model","created":1792768060,"owned_by":"arkanecloud","model_name":"mistralai/Mistral-Medium-3.5-128B","context_length":262144,"max_input_tokens":null,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-6,"output_cost_per_token":7.5e-6,"cache_read_input_token_cost":3e-7},"list_pricing":{"input_cost_per_token":1.5e-6,"output_cost_per_token":7.5e-6,"cache_read_input_token_cost":3e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"},{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":1},{"id":"nemotron-3-super-120b-a12b","object":"model","created":1792768060,"owned_by":"nvidia","mode":"chat","context_length":262144,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":7.5e-8,"output_cost_per_token":4e-7},"pricing_endpoint":"deepinfra/nemotron-3-super-120b-a12b","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"arkanecloud/nvidia/nemotron-3-super-120b-a12b","object":"model","created":1792768060,"owned_by":"arkanecloud","model_name":"nvidia/nemotron-3-super-120b-a12b","context_length":256000,"max_input_tokens":null,"max_output_tokens":16384,"quantization":null,"retirement_date":null,"description":"NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4e-7,"output_cost_per_token":8e-7,"cache_read_input_token_cost":1e-7},"list_pricing":{"input_cost_per_token":4e-7,"output_cost_per_token":8e-7,"cache_read_input_token_cost":1e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"},{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"deepinfra/nemotron-3-super-120b-a12b","object":"model","created":1773245239,"owned_by":"deepinfra","model_name":"nemotron-3-super-120b-a12b","context_length":262144,"max_input_tokens":null,"max_output_tokens":16384,"quantization":"bf16","retirement_date":null,"description":"NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":7.5e-8,"output_cost_per_token":4e-7},"list_pricing":{"input_cost_per_token":7.5e-8,"output_cost_per_token":4e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"nebius/nvidia/nemotron-3-super-120b-a12b","object":"model","created":1773245239,"owned_by":"nebius","model_name":"nvidia/nemotron-3-super-120b-a12b","context_length":262144,"max_input_tokens":262144,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":9e-7,"cache_read_input_token_cost":3e-7},"list_pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":9e-7,"cache_read_input_token_cost":3e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":3},{"id":"nemotron-3-ultra-550b-a55b","object":"model","created":1792768060,"owned_by":"nvidia","mode":"chat","context_length":1048576,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":2.2e-6,"cache_read_input_token_cost":1.0000000000000001e-7},"pricing_endpoint":"deepinfra/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"arkanecloud/nvidia/nemotron-3-ultra-550b-a55b","object":"model","created":1792768060,"owned_by":"arkanecloud","model_name":"nvidia/nemotron-3-ultra-550b-a55b","context_length":512288,"max_input_tokens":null,"max_output_tokens":256144,"quantization":null,"retirement_date":null,"description":"NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE).","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6e-7,"output_cost_per_token":3.5e-6,"cache_read_input_token_cost":2e-7},"list_pricing":{"input_cost_per_token":6e-7,"output_cost_per_token":3.5e-6,"cache_read_input_token_cost":2e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"},{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"deepinfra/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B","object":"model","created":1782119040,"owned_by":"deepinfra","model_name":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B","context_length":262144,"max_input_tokens":262144,"max_output_tokens":null,"quantization":"fp4","retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":2.2e-6,"cache_read_input_token_cost":1.0000000000000001e-7},"list_pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":2.2e-6,"cache_read_input_token_cost":1.0000000000000001e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"deepinfra/nemotron-3-ultra-550b-a55b","object":"model","created":1780551208,"owned_by":"deepinfra","model_name":"nemotron-3-ultra-550b-a55b","context_length":262144,"max_input_tokens":null,"max_output_tokens":16384,"quantization":"fp4","retirement_date":null,"description":"NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE).","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":2.2e-6,"cache_read_input_token_cost":1e-7},"list_pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":2.2e-6,"cache_read_input_token_cost":1e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"nebius/nvidia/Nemotron-3-Ultra-550b-a55b","object":"model","created":1780551208,"owned_by":"nebius","model_name":"nvidia/Nemotron-3-Ultra-550b-a55b","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE).","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":3e-6,"cache_read_input_token_cost":1e-6},"list_pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":3e-6,"cache_read_input_token_cost":1e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":4},{"id":"qwen3-235b-a22b-instruct-2507","object":"model","created":1792768060,"owned_by":"qwen","mode":"chat","context_length":262144,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":9e-8,"output_cost_per_token":5.5e-7},"pricing_endpoint":"deepinfra/Qwen/Qwen3-235B-A22B-Instruct-2507","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"arkanecloud/Qwen/Qwen3-235B-A22B-Instruct-2507","object":"model","created":1792768060,"owned_by":"arkanecloud","model_name":"Qwen/Qwen3-235B-A22B-Instruct-2507","context_length":262000,"max_input_tokens":null,"max_output_tokens":16384,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.5e-7,"output_cost_per_token":1e-6,"cache_read_input_token_cost":2e-7},"list_pricing":{"input_cost_per_token":2.5e-7,"output_cost_per_token":1e-6,"cache_read_input_token_cost":2e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null},{"id":"greenpt/qwen3-235b-a22b-instruct-2507","object":"model","created":1791839241,"owned_by":"greenpt","model_name":"qwen3-235b-a22b-instruct-2507","context_length":250000,"max_input_tokens":null,"max_output_tokens":16000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":9.912603875828115e-7,"output_cost_per_token":2.973781162748435e-6},"list_pricing":{"input_cost_per_token":9.912603875828115e-7,"output_cost_per_token":2.973781162748435e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"nebius/Qwen/Qwen3-235B-A22B-Instruct-2507","object":"model","created":1782119040,"owned_by":"nebius","model_name":"Qwen/Qwen3-235B-A22B-Instruct-2507","context_length":262144,"max_input_tokens":262144,"max_output_tokens":32768,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":2e-7},"list_pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":2e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"deepinfra/Qwen/Qwen3-235B-A22B-Instruct-2507","object":"model","created":1767692616,"owned_by":"deepinfra","model_name":"Qwen/Qwen3-235B-A22B-Instruct-2507","context_length":262144,"max_input_tokens":262144,"max_output_tokens":32768,"quantization":"fp8","retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":9e-8,"output_cost_per_token":5.5e-7},"list_pricing":{"input_cost_per_token":9e-8,"output_cost_per_token":5.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"scaleway/qwen3-235b-a22b-instruct-2507","object":"model","created":1754049528,"owned_by":"scaleway","model_name":"qwen3-235b-a22b-instruct-2507","context_length":250000,"max_input_tokens":null,"max_output_tokens":16384,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":8.260503229856764e-7,"output_cost_per_token":2.4781509689570285e-6},"list_pricing":{"input_cost_per_token":8.260503229856764e-7,"output_cost_per_token":2.4781509689570285e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":5},{"id":"qwen3.6-35b-a3b","object":"model","created":1792768060,"owned_by":"qwen","mode":"chat","context_length":262144,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":9.5e-7,"cache_read_input_token_cost":1.5e-8},"pricing_endpoint":"flexai/Qwen3.6-35B-A3B-FP8","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"arkanecloud/Qwen/Qwen3.6-35B-A3B","object":"model","created":1792768060,"owned_by":"arkanecloud","model_name":"Qwen/Qwen3.6-35B-A3B","context_length":262144,"max_input_tokens":null,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.5e-7,"output_cost_per_token":1.5e-6,"cache_read_input_token_cost":2e-7},"list_pricing":{"input_cost_per_token":2.5e-7,"output_cost_per_token":1.5e-6,"cache_read_input_token_cost":2e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null},{"id":"greenpt/qwen3.6-35b-a3b","object":"model","created":1791839241,"owned_by":"greenpt","model_name":"qwen3.6-35b-a3b","context_length":256000,"max_input_tokens":null,"max_output_tokens":32000,"quantization":null,"retirement_date":null,"description":"Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.304201291942705e-7,"output_cost_per_token":1.982520775165623e-6},"list_pricing":{"input_cost_per_token":3.304201291942705e-7,"output_cost_per_token":1.982520775165623e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"flexai/Qwen3.6-35B-A3B-FP8","object":"model","created":1790170741,"owned_by":"flexai","model_name":"Qwen3.6-35B-A3B-FP8","context_length":262144,"max_input_tokens":null,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":9.5e-7,"cache_read_input_token_cost":1.5e-8},"list_pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":9.5e-7,"cache_read_input_token_cost":1.5e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"qwen/qwen3.6-35b-a3b","object":"model","created":1785412138,"owned_by":"qwen","model_name":"qwen3.6-35b-a3b","context_length":262144,"max_input_tokens":260096,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"The Qwen3.6 35B-A3B native vision-language model is built on a hybrid architecture that integrates linear attention mechanisms with a sparse mixture-of-experts framework, achieving higher inference efficiency. Compared with the 3.5-35B-A3B, this model demonstrates significantly improved agentic coding capabilities, mathematical and code reasoning abilities, spatial intelligence, as well as object localization and object detection performance.","source":null,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.4375e-7,"output_cost_per_token":1.4625000000000002e-6},"list_pricing":{"input_cost_per_token":3.75e-7,"output_cost_per_token":2.25e-6},"discount":0.35,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null},{"id":"scaleway/qwen3.6-35b-a3b","object":"model","created":1778158991,"owned_by":"scaleway","model_name":"qwen3.6-35b-a3b","context_length":256000,"max_input_tokens":null,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.753501076618921e-7,"output_cost_per_token":1.6521006459713528e-6},"list_pricing":{"input_cost_per_token":2.753501076618921e-7,"output_cost_per_token":1.6521006459713528e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"deepinfra/Qwen/Qwen3.6-35B-A3B","object":"model","created":1777260255,"owned_by":"deepinfra","model_name":"Qwen/Qwen3.6-35B-A3B","context_length":262144,"max_input_tokens":262144,"max_output_tokens":65536,"quantization":"fp8","retirement_date":null,"description":"Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token.","source":null,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.0000000000000001e-7,"output_cost_per_token":9.499999999999999e-7,"cache_read_input_token_cost":1.0000000000000001e-7},"list_pricing":{"input_cost_per_token":1.0000000000000001e-7,"output_cost_per_token":9.499999999999999e-7,"cache_read_input_token_cost":1.0000000000000001e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":6},{"id":"qwen3.8-27b","object":"model","created":1792768060,"owned_by":"qwen","mode":"chat","context_length":1000000,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":9e-8,"output_cost_per_token":4.4e-7,"cache_read_input_token_cost":1.71e-8},"pricing_endpoint":"compactifai/qwen-3-8-27b","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"arkanecloud/qwen38-27b","object":"model","created":1792768060,"owned_by":"arkanecloud","model_name":"qwen38-27b","context_length":1000000,"max_input_tokens":null,"max_output_tokens":500000,"quantization":null,"retirement_date":null,"description":"Qwen3.8 27B is an open-weight dense vision-language model from Qwen.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":2.5e-6,"cache_read_input_token_cost":5e-8},"list_pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":2.5e-6,"cache_read_input_token_cost":5e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"},{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"flexai/Qwen3.8-27B","object":"model","created":1790170741,"owned_by":"flexai","model_name":"Qwen3.8-27B","context_length":262144,"max_input_tokens":null,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"Qwen3.8 27B is an open-weight dense vision-language model from Qwen.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":2.5e-6,"cache_read_input_token_cost":3e-8},"list_pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":2.5e-6,"cache_read_input_token_cost":3e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"ovhcloud/Qwen3.8-27B","object":"model","created":1789657955,"owned_by":"ovhcloud","model_name":"Qwen3.8-27B","context_length":262144,"max_input_tokens":null,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"Qwen3.8 27B is an open-weight dense vision-language model from Qwen.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4.7e-7,"output_cost_per_token":3.19e-6},"list_pricing":{"input_cost_per_token":4.7e-7,"output_cost_per_token":3.19e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"scaleway/qwen3.8-27b","object":"model","created":1789565546,"owned_by":"scaleway","model_name":"qwen3.8-27b","context_length":256000,"max_input_tokens":null,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"Qwen3.8 27B is an open-weight dense vision-language model from Qwen.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6.60840258388541e-7,"output_cost_per_token":3.634621421136976e-6,"cache_read_input_token_cost":1.3216805167770822e-7},"list_pricing":{"input_cost_per_token":6.60840258388541e-7,"output_cost_per_token":3.634621421136976e-6,"cache_read_input_token_cost":1.3216805167770822e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"compactifai/qwen-3-8-27b@eu","object":"model","created":1788457256,"owned_by":"compactifai","model_name":"qwen-3-8-27b","context_length":null,"max_input_tokens":null,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"Qwen3.8 27B is an open-weight dense vision-language model from Qwen.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":9e-8,"output_cost_per_token":4.4e-7,"cache_read_input_token_cost":1.71e-8},"list_pricing":{"input_cost_per_token":9e-8,"output_cost_per_token":4.4e-7,"cache_read_input_token_cost":1.71e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"compactifai/qwen-3-8-27b","object":"model","created":1788457256,"owned_by":"compactifai","model_name":"qwen-3-8-27b","context_length":null,"max_input_tokens":null,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"Qwen3.8 27B is an open-weight dense vision-language model from Qwen.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":9e-8,"output_cost_per_token":4.4e-7,"cache_read_input_token_cost":1.71e-8},"list_pricing":{"input_cost_per_token":9e-8,"output_cost_per_token":4.4e-7,"cache_read_input_token_cost":1.71e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null},{"id":"compactifai/qwen-3-8-27b@us","object":"model","created":1788457256,"owned_by":"compactifai","model_name":"qwen-3-8-27b","context_length":null,"max_input_tokens":null,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"Qwen3.8 27B is an open-weight dense vision-language model from Qwen.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":9e-8,"output_cost_per_token":4.4e-7,"cache_read_input_token_cost":1.71e-8},"list_pricing":{"input_cost_per_token":9e-8,"output_cost_per_token":4.4e-7,"cache_read_input_token_cost":1.71e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":null,"alias_of":null},{"id":"ionos/Qwen/Qwen3.8-27B","object":"model","created":1788215842,"owned_by":"ionos","model_name":"Qwen/Qwen3.8-27B","context_length":262144,"max_input_tokens":null,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"Qwen3.8 27B is an open-weight dense vision-language model from Qwen.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4.405601722590274e-7,"output_cost_per_token":2.973781162748435e-6},"list_pricing":{"input_cost_per_token":4.405601722590274e-7,"output_cost_per_token":2.973781162748435e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"groq/qwen/qwen3.8-27b","object":"model","created":1787757131,"owned_by":"groq","model_name":"qwen/qwen3.8-27b","context_length":131072,"max_input_tokens":131072,"max_output_tokens":16384,"quantization":null,"retirement_date":null,"description":"Qwen3.8 27B is an open-weight dense vision-language model from Qwen.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":8e-7,"output_cost_per_token":4e-6,"cache_read_input_token_cost":4e-7},"list_pricing":{"input_cost_per_token":8e-7,"output_cost_per_token":4e-6,"cache_read_input_token_cost":4e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":null,"alias_of":null},{"id":"tensorx/qwen/qwen3.8-27b","object":"model","created":1787003349,"owned_by":"tensorx","model_name":"qwen/qwen3.8-27b","context_length":262144,"max_input_tokens":262144,"max_output_tokens":32768,"quantization":"fp8","retirement_date":null,"description":"Served by TensorX at fp8 quantization.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4e-7,"output_cost_per_token":2.4e-6,"cache_read_input_token_cost":1e-7},"list_pricing":{"input_cost_per_token":4e-7,"output_cost_per_token":2.4e-6,"cache_read_input_token_cost":1e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"cerebras/qwen-3.8-27b","object":"model","created":1786722910,"owned_by":"cerebras","model_name":"qwen-3.8-27b","context_length":65536,"max_input_tokens":65536,"max_output_tokens":32768,"quantization":"fp16","retirement_date":null,"description":"Qwen3.8 27B is an open-weight dense vision-language model from Qwen.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":9.9e-7,"output_cost_per_token":1.49e-6,"cache_read_input_token_cost":9.9e-7},"list_pricing":{"input_cost_per_token":9.9e-7,"output_cost_per_token":1.49e-6,"cache_read_input_token_cost":9.9e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"cloudflare/@cf/qwen/qwen3.8-27b","object":"model","created":1786722910,"owned_by":"cloudflare","model_name":"@cf/qwen/qwen3.8-27b","context_length":262144,"max_input_tokens":null,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"Qwen3.8 27B is an open-weight dense vision-language model from Qwen.","source":null,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4.5000000000000003e-7,"output_cost_per_token":3.2000000000000003e-6,"cache_read_input_token_cost":5.0000000000000004e-8},"list_pricing":{"input_cost_per_token":4.5000000000000003e-7,"output_cost_per_token":3.2000000000000003e-6,"cache_read_input_token_cost":5.0000000000000004e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"deepinfra/Qwen/Qwen3.8-27B","object":"model","created":1786722910,"owned_by":"deepinfra","model_name":"Qwen/Qwen3.8-27B","context_length":262144,"max_input_tokens":262144,"max_output_tokens":131072,"quantization":"bf16","retirement_date":null,"description":"Qwen3.8 27B is an open-weight dense vision-language model from Qwen.","source":null,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.0000000000000002e-7,"output_cost_per_token":2.5e-6,"cache_read_input_token_cost":5.0000000000000004e-8},"list_pricing":{"input_cost_per_token":2.0000000000000002e-7,"output_cost_per_token":2.5e-6,"cache_read_input_token_cost":5.0000000000000004e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"nebius/Qwen/Qwen3.8-27B","object":"model","created":1786722910,"owned_by":"nebius","model_name":"Qwen/Qwen3.8-27B","context_length":1000000,"max_input_tokens":262144,"max_output_tokens":131072,"quantization":"fp4","retirement_date":null,"description":"Qwen3.8 27B is an open-weight dense vision-language model from Qwen.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4.5e-7,"output_cost_per_token":3e-6,"cache_read_input_token_cost":4.5e-7},"list_pricing":{"input_cost_per_token":4.5e-7,"output_cost_per_token":3e-6,"cache_read_input_token_cost":4.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"qwen/qwen3.8-27b","object":"model","created":1786722910,"owned_by":"qwen","model_name":"qwen3.8-27b","context_length":1000000,"max_input_tokens":991808,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"The Qwen3.8 27B native vision-language dense model builds upon the 3.6-27B version, with key improvements in coding and office productivity capabilities across both text and visual modalities. It enables more reliable end-to-end completion of complex tasks, delivering consistently trustworthy results.","source":null,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.25e-7,"output_cost_per_token":1.95e-6,"cache_read_input_token_cost":6.500000000000001e-8,"cache_creation_input_token_cost":4.0625000000000003e-7},"list_pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":3e-6,"cache_read_input_token_cost":1.0000000000000001e-7,"cache_creation_input_token_cost":6.25e-7},"discount":0.35,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":15},{"id":"qwen38-27b-turbo-v2","object":"model","created":1792768060,"owned_by":"qwen","mode":"chat","context_length":150000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":1.5e-6,"cache_read_input_token_cost":4e-8},"pricing_endpoint":"arkanecloud/qwen38-27b-turbo-v2","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"arkanecloud/qwen38-27b-turbo-v2","object":"model","created":1792768060,"owned_by":"arkanecloud","model_name":"qwen38-27b-turbo-v2","context_length":150000,"max_input_tokens":null,"max_output_tokens":75000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":1.5e-6,"cache_read_input_token_cost":4e-8},"list_pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":1.5e-6,"cache_read_input_token_cost":4e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"},{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":1},{"id":"~glm-latest","object":"model","created":1792768060,"owned_by":"zai","mode":"chat","context_length":1048576,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":6.4e-7,"cache_read_input_token_cost":1.8e-8},"pricing_endpoint":"compactifai/glm-5-3","regions":[{"code":"ap","name":"Asia"},{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":"glm-5.3","endpoints":[{"id":"arkanecloud/zai-org/GLM-5.3","object":"model","created":1792768060,"owned_by":"arkanecloud","model_name":"zai-org/GLM-5.3","context_length":200000,"max_input_tokens":null,"max_output_tokens":100000,"quantization":null,"retirement_date":null,"description":"GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.4e-6,"output_cost_per_token":4.4e-6,"cache_read_input_token_cost":3e-7},"list_pricing":{"input_cost_per_token":1.4e-6,"output_cost_per_token":4.4e-6,"cache_read_input_token_cost":3e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"},{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"sference/zai-org/GLM-5.3","object":"model","created":1792636080,"owned_by":"sference","model_name":"zai-org/GLM-5.3","context_length":1048576,"max_input_tokens":null,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.2e-6,"output_cost_per_token":4.2e-6,"cache_read_input_token_cost":2.6e-7},"list_pricing":{"input_cost_per_token":1.2e-6,"output_cost_per_token":4.2e-6,"cache_read_input_token_cost":2.6e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"greenpt/glm-5.3","object":"model","created":1791839241,"owned_by":"greenpt","model_name":"glm-5.3","context_length":1000000,"max_input_tokens":null,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.2115404737123252e-6,"output_cost_per_token":4.846161894849301e-6,"cache_read_input_token_cost":3.028851184280813e-7},"list_pricing":{"input_cost_per_token":1.2115404737123252e-6,"output_cost_per_token":4.846161894849301e-6,"cache_read_input_token_cost":3.028851184280813e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"scaleway/glm-5.3","object":"model","created":1791474730,"owned_by":"scaleway","model_name":"glm-5.3","context_length":256000,"max_input_tokens":null,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.982520775165623e-6,"output_cost_per_token":6.057702368561627e-6},"list_pricing":{"input_cost_per_token":1.982520775165623e-6,"output_cost_per_token":6.057702368561627e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"tencent/glm-5.3","object":"model","created":1790867221,"owned_by":"tencent","model_name":"glm-5.3","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.4e-6,"output_cost_per_token":4.4e-6,"cache_read_input_token_cost":2.6e-7,"input_cost_per_token_cache_hit":2.6e-7,"cache_creation_input_token_cost":0.0},"list_pricing":{"input_cost_per_token":1.4e-6,"output_cost_per_token":4.4e-6,"cache_read_input_token_cost":2.6e-7,"input_cost_per_token_cache_hit":2.6e-7,"cache_creation_input_token_cost":0.0},"discount":null,"discount_ends_at":null,"regions":[{"code":"ap","name":"Asia"}],"zero_data_retention":true,"alias_of":null},{"id":"mistral/zai-glm-5-3@eu","object":"model","created":1789621775,"owned_by":"mistral","model_name":"zai-glm-5-3","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.54e-6,"output_cost_per_token":4.84e-6,"cache_read_input_token_cost":1.5400000000000003e-7,"input_cost_per_token_batches":7.7e-7,"output_cost_per_token_batches":2.42e-6,"cache_read_input_token_cost_batches":7.700000000000001e-8},"list_pricing":{"input_cost_per_token":1.54e-6,"output_cost_per_token":4.84e-6,"cache_read_input_token_cost":1.5400000000000003e-7,"input_cost_per_token_batches":7.7e-7,"output_cost_per_token_batches":2.42e-6,"cache_read_input_token_cost_batches":7.700000000000001e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"mistral/zai-glm-5-3","object":"model","created":1789621775,"owned_by":"mistral","model_name":"zai-glm-5-3","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.4e-6,"output_cost_per_token":4.4e-6,"cache_read_input_token_cost":1.4e-7,"input_cost_per_token_batches":7e-7,"output_cost_per_token_batches":2.2e-6,"cache_read_input_token_cost_batches":7e-8},"list_pricing":{"input_cost_per_token":1.4e-6,"output_cost_per_token":4.4e-6,"cache_read_input_token_cost":1.4e-7,"input_cost_per_token_batches":7e-7,"output_cost_per_token_batches":2.2e-6,"cache_read_input_token_cost_batches":7e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"databricks/databricks-glm-5-3","object":"model","created":1788671370,"owned_by":"databricks","model_name":"databricks-glm-5-3","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"GLM-5.3 is a text-only mixture-of-experts language model developed by Zhipu AI. It supports a context length of 1,048,576 tokens, function calling, structured output, coding, and agentic tool use. Reasoning is always enabled with low, high, and max effort levels; max is the default.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.4e-6,"output_cost_per_token":4.4e-6,"input_dbu_cost_per_token":0.00002,"output_dbu_cost_per_token":0.000062857,"cache_read_input_token_cost":1.4e-7,"input_cost_per_token_priority":2.45e-6,"cache_creation_input_token_cost":1.4e-6,"cache_creation_input_token_cost_priority":2.45e-6},"list_pricing":{"input_cost_per_token":1.4e-6,"output_cost_per_token":4.4e-6,"input_dbu_cost_per_token":0.00002,"output_dbu_cost_per_token":0.000062857,"cache_read_input_token_cost":1.4e-7,"input_cost_per_token_priority":2.45e-6,"cache_creation_input_token_cost":1.4e-6,"cache_creation_input_token_cost_priority":2.45e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"compactifai/glm-5-3","object":"model","created":1788457256,"owned_by":"compactifai","model_name":"glm-5-3","context_length":null,"max_input_tokens":null,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":6.4e-7,"cache_read_input_token_cost":1.8e-8},"list_pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":6.4e-7,"cache_read_input_token_cost":1.8e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null},{"id":"compactifai/glm-5-3@us","object":"model","created":1788457256,"owned_by":"compactifai","model_name":"glm-5-3","context_length":null,"max_input_tokens":null,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":6.4e-7,"cache_read_input_token_cost":1.8e-8},"list_pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":6.4e-7,"cache_read_input_token_cost":1.8e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":null,"alias_of":null},{"id":"fireworks_ai/accounts/fireworks/models/glm-5p3","object":"model","created":1788066615,"owned_by":"fireworks_ai","model_name":"accounts/fireworks/models/glm-5p3","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.4e-6,"output_cost_per_token":4.4e-6,"cache_read_input_token_cost":2.6e-7,"input_cost_per_token_priority":1.75e-6,"output_cost_per_token_priority":5.5e-6,"cache_read_input_token_cost_priority":3.25e-7},"list_pricing":{"input_cost_per_token":1.4e-6,"output_cost_per_token":4.4e-6,"cache_read_input_token_cost":2.6e-7,"input_cost_per_token_priority":1.75e-6,"output_cost_per_token_priority":5.5e-6,"cache_read_input_token_cost_priority":3.25e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"tensorx/z-ai/glm-5.3","object":"model","created":1787980172,"owned_by":"tensorx","model_name":"z-ai/glm-5.3","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":64000,"quantization":"fp8","retirement_date":null,"description":"Served by TensorX at fp8 quantization.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.75e-6,"output_cost_per_token":4.5e-6,"cache_read_input_token_cost":4.375e-7},"list_pricing":{"input_cost_per_token":1.75e-6,"output_cost_per_token":4.5e-6,"cache_read_input_token_cost":4.375e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"cloudflare/@cf/zai-org/glm-5.3","object":"model","created":1787086655,"owned_by":"cloudflare","model_name":"@cf/zai-org/glm-5.3","context_length":1048576,"max_input_tokens":null,"max_output_tokens":131072,"quantization":null,"retirement_date":"2098-12-31","description":"GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.4e-6,"output_cost_per_token":4.4e-6,"cache_read_input_token_cost":2.6e-7},"list_pricing":{"input_cost_per_token":1.4e-6,"output_cost_per_token":4.4e-6,"cache_read_input_token_cost":2.6e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"deepinfra/zai-org/GLM-5.3","object":"model","created":1787086655,"owned_by":"deepinfra","model_name":"zai-org/GLM-5.3","context_length":1048576,"max_input_tokens":null,"max_output_tokens":131072,"quantization":"fp4","retirement_date":"2098-12-31","description":"GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":9.000000000000001e-7,"output_cost_per_token":4e-6,"cache_read_input_token_cost":1.99999998e-7},"list_pricing":{"input_cost_per_token":9.000000000000001e-7,"output_cost_per_token":4e-6,"cache_read_input_token_cost":1.99999998e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"nebius/zai-org/GLM-5.3","object":"model","created":1787086655,"owned_by":"nebius","model_name":"zai-org/GLM-5.3","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":1024000,"quantization":"fp4","retirement_date":null,"description":"GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.4e-6,"output_cost_per_token":4.4e-6,"cache_read_input_token_cost":1.4e-6},"list_pricing":{"input_cost_per_token":1.4e-6,"output_cost_per_token":4.4e-6,"cache_read_input_token_cost":1.4e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"qwen/glm-5.3","object":"model","created":1787086655,"owned_by":"qwen","model_name":"glm-5.3","context_length":1000000,"max_input_tokens":1048576,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"GLM-5.3 is Z.ai's latest flagship large language model, delivering state-of-the-art coding and agentic performance among open-source models, with a 50% improvement over its predecessor on Z.ai Code Bench and end-to-end delivery of production-grade results. It demonstrates emergent cybersecurity capability, achieving the best result to date on the CyberGym vulnerability discovery benchmark. With a 1M-token context window, 128K-token maximum output, and three reasoning effort levels, GLM-5.3 excels at long-horizon, complex tasks.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":9.1e-7,"output_cost_per_token":2.86e-6,"cache_read_input_token_cost":1.8200000000000002e-7},"list_pricing":{"input_cost_per_token":1.4e-6,"output_cost_per_token":4.4e-6,"cache_read_input_token_cost":2.8e-7},"discount":0.35,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null},{"id":"together_ai/zai-org/GLM-5.3","object":"model","created":1787086655,"owned_by":"together_ai","model_name":"zai-org/GLM-5.3","context_length":1048575,"max_input_tokens":1048575,"max_output_tokens":131072,"quantization":null,"retirement_date":"2098-12-31","description":"GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.4e-6,"output_cost_per_token":4.4e-6,"cache_read_input_token_cost":2.5999999999999995e-7},"list_pricing":{"input_cost_per_token":1.4e-6,"output_cost_per_token":4.4e-6,"cache_read_input_token_cost":2.5999999999999995e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null},{"id":"zai/glm-5.3","object":"model","created":1787086655,"owned_by":"zai","model_name":"glm-5.3","context_length":1048576,"max_input_tokens":1000000,"max_output_tokens":131072,"quantization":"fp8","retirement_date":"2098-12-31","description":"GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.4e-6,"output_cost_per_token":4.4e-6,"cache_read_input_token_cost":2.6e-7,"cache_creation_input_token_cost":0.0},"list_pricing":{"input_cost_per_token":1.4e-6,"output_cost_per_token":4.4e-6,"cache_read_input_token_cost":2.6e-7,"cache_creation_input_token_cost":0.0},"discount":null,"discount_ends_at":null,"regions":[{"code":"ap","name":"Asia"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":18},{"id":"~kimi-latest","object":"model","created":1792768060,"owned_by":"moonshot","mode":"chat","context_length":1048576,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.95e-6,"output_cost_per_token":9.75e-6,"cache_read_input_token_cost":1.9499999999999999e-7},"pricing_endpoint":"qwen/kimi-k3","regions":[{"code":"ap","name":"Asia"},{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":"kimi-k3","endpoints":[{"id":"arkanecloud/moonshotai/Kimi-K3","object":"model","created":1792768060,"owned_by":"arkanecloud","model_name":"moonshotai/Kimi-K3","context_length":1000000,"max_input_tokens":null,"max_output_tokens":500000,"quantization":null,"retirement_date":null,"description":"Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"cache_read_input_token_cost":3e-7},"list_pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"cache_read_input_token_cost":3e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null},{"id":"greenpt/kimi-k3","object":"model","created":1791839241,"owned_by":"greenpt","model_name":"kimi-k3","context_length":1000000,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.634621421136976e-6,"output_cost_per_token":0.00001817310710568488,"cache_read_input_token_cost":9.08655355284244e-7},"list_pricing":{"input_cost_per_token":3.634621421136976e-6,"output_cost_per_token":0.00001817310710568488,"cache_read_input_token_cost":9.08655355284244e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"tencent/kimi-k3","object":"model","created":1790867221,"owned_by":"tencent","model_name":"kimi-k3","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"cache_read_input_token_cost":3e-7,"input_cost_per_token_cache_hit":3e-7,"cache_creation_input_token_cost":0.0},"list_pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"cache_read_input_token_cost":3e-7,"input_cost_per_token_cache_hit":3e-7,"cache_creation_input_token_cost":0.0},"discount":null,"discount_ends_at":null,"regions":[{"code":"ap","name":"Asia"}],"zero_data_retention":true,"alias_of":null},{"id":"databricks/databricks-kimi-k3","object":"model","created":1787893793,"owned_by":"databricks","model_name":"databricks-kimi-k3","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"Kimi K3 is a 2.8T-parameter model developed by Moonshot AI with native vision capabilities. The model supports a context length of 1M tokens and is designed for long-horizon coding, knowledge work, and reasoning.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"input_dbu_cost_per_token":0.000042857,"output_dbu_cost_per_token":0.000214286,"cache_read_input_token_cost":3e-7,"cache_creation_input_token_cost":3e-6,"cache_creation_input_token_cost_priority":5.25e-6},"list_pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"input_dbu_cost_per_token":0.000042857,"output_dbu_cost_per_token":0.000214286,"cache_read_input_token_cost":3e-7,"cache_creation_input_token_cost":3e-6,"cache_creation_input_token_cost_priority":5.25e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"tensorx/moonshotai/kimi-k3","object":"model","created":1787003349,"owned_by":"tensorx","model_name":"moonshotai/kimi-k3","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":64000,"quantization":"fp4","retirement_date":null,"description":"Served by TensorX at mxfp4 quantization.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"cache_read_input_token_cost":7.5e-7},"list_pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"cache_read_input_token_cost":7.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/moonshotai.kimi-k3","object":"model","created":1784215858,"owned_by":"amazon","model_name":"moonshotai.kimi-k3","context_length":1048576,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"cache_read_input_token_cost":3e-7,"cache_creation_input_token_cost":3.75e-6},"list_pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"cache_read_input_token_cost":3e-7,"cache_creation_input_token_cost":3.75e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/moonshotai.kimi-k3@us","object":"model","created":1784215858,"owned_by":"amazon","model_name":"moonshotai.kimi-k3","context_length":1048576,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"cache_read_input_token_cost":3e-7,"cache_creation_input_token_cost":3.75e-6},"list_pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"cache_read_input_token_cost":3e-7,"cache_creation_input_token_cost":3.75e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"deepinfra/moonshotai/Kimi-K3","object":"model","created":1784215858,"owned_by":"deepinfra","model_name":"moonshotai/Kimi-K3","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":16384,"quantization":"fp4","retirement_date":null,"description":"Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.85e-6,"output_cost_per_token":0.00001425,"cache_read_input_token_cost":2.8499999999999997e-7},"list_pricing":{"input_cost_per_token":2.85e-6,"output_cost_per_token":0.00001425,"cache_read_input_token_cost":2.8499999999999997e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"fireworks_ai/accounts/fireworks/models/kimi-k3","object":"model","created":1784215858,"owned_by":"fireworks_ai","model_name":"accounts/fireworks/models/kimi-k3","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI.","source":null,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"cache_read_input_token_cost":3e-7,"input_cost_per_token_priority":3.75e-6,"output_cost_per_token_priority":0.00001875,"cache_read_input_token_cost_priority":3.75e-7},"list_pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"cache_read_input_token_cost":3e-7,"input_cost_per_token_priority":3.75e-6,"output_cost_per_token_priority":0.00001875,"cache_read_input_token_cost_priority":3.75e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"fireworks_ai/kimi-k3","object":"model","created":1784215858,"owned_by":"fireworks_ai","model_name":"kimi-k3","context_length":1048576,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at...","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"cache_read_input_token_cost":3e-7},"list_pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"cache_read_input_token_cost":3e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"moonshot/kimi-k3","object":"model","created":1784215858,"owned_by":"moonshot","model_name":"kimi-k3","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI.","source":null,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"cache_read_input_token_cost":3e-7,"cache_creation_input_token_cost":3e-6,"cache_creation_input_token_cost_above_1hr":6e-6},"list_pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"cache_read_input_token_cost":3e-7,"cache_creation_input_token_cost":3e-6,"cache_creation_input_token_cost_above_1hr":6e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"ap","name":"Asia"}],"zero_data_retention":false,"alias_of":null},{"id":"nebius/moonshotai/Kimi-K3","object":"model","created":1784215858,"owned_by":"nebius","model_name":"moonshotai/Kimi-K3","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":1024000,"quantization":"fp4","retirement_date":null,"description":"Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"cache_read_input_token_cost":3e-6},"list_pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"cache_read_input_token_cost":3e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"qwen/kimi-k3","object":"model","created":1784215858,"owned_by":"qwen","model_name":"kimi-k3","context_length":1000000,"max_input_tokens":1048576,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"Kimi-K3 is Moonshot AI’s most capable flagship model to date, featuring 2.8 trillion parameters. Built on the KDA hybrid linear attention mechanism (Kimi Delta Attention) and Attention Residuals, it natively supports visual understanding and offers a 1-million-token context window. As the world's first open-source model at the 3-trillion-parameter scale, it is designed for frontier intelligence scenarios such as long-horizon programming, knowledge work, and reasoning.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.95e-6,"output_cost_per_token":9.75e-6,"cache_read_input_token_cost":1.9499999999999999e-7},"list_pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"cache_read_input_token_cost":3e-7},"discount":0.35,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null},{"id":"together_ai/moonshotai/Kimi-K3","object":"model","created":1784215858,"owned_by":"together_ai","model_name":"moonshotai/Kimi-K3","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI.","source":null,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"cache_read_input_token_cost":3e-7},"list_pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"cache_read_input_token_cost":3e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":14},{"id":"muse-spark-1.1","object":"model","created":1792552674,"owned_by":"meta","mode":"chat","context_length":1048576,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":4.25e-6,"cache_read_input_token_cost":1.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.0025,"search_context_size_high":0.0025,"search_context_size_medium":0.0025}},"pricing_endpoint":"meta/muse-spark-1.1","regions":[{"code":"eu","name":"Europe"}],"alias_of":null,"endpoints":[{"id":"meta/muse-spark-1.1","object":"model","created":1792552674,"owned_by":"meta","model_name":"muse-spark-1.1","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"Muse Spark 1.1 is a multimodal reasoning model from Meta, built for agentic tasks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":4.25e-6,"cache_read_input_token_cost":1.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.0025,"search_context_size_high":0.0025,"search_context_size_medium":0.0025}},"list_pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":4.25e-6,"cache_read_input_token_cost":1.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.0025,"search_context_size_high":0.0025,"search_context_size_medium":0.0025}},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":1},{"id":"muse-spark-1.2","object":"model","created":1792552674,"owned_by":"meta","mode":"chat","context_length":1048576,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":4.25e-6,"cache_read_input_token_cost":1.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.0025,"search_context_size_high":0.0025,"search_context_size_medium":0.0025}},"pricing_endpoint":"meta/muse-spark-1.2","regions":[{"code":"eu","name":"Europe"}],"alias_of":null,"endpoints":[{"id":"meta/muse-spark-1.2","object":"model","created":1792552674,"owned_by":"meta","model_name":"muse-spark-1.2","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"Muse Spark 1.2 is a reasoning model from Meta, designed for complex agentic tasks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":4.25e-6,"cache_read_input_token_cost":1.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.0025,"search_context_size_high":0.0025,"search_context_size_medium":0.0025}},"list_pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":4.25e-6,"cache_read_input_token_cost":1.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.0025,"search_context_size_high":0.0025,"search_context_size_medium":0.0025}},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":1},{"id":"muse-spark-1.3","object":"model","created":1792552674,"owned_by":"meta","mode":"chat","context_length":1048576,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":4.25e-6,"cache_read_input_token_cost":1.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.0025,"search_context_size_high":0.0025,"search_context_size_medium":0.0025}},"pricing_endpoint":"meta/muse-spark-1.3","regions":[{"code":"eu","name":"Europe"}],"alias_of":null,"endpoints":[{"id":"meta/muse-spark-1.3","object":"model","created":1792552674,"owned_by":"meta","model_name":"muse-spark-1.3","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"Muse Spark 1.3 is a multimodal reasoning model from Meta for long-running agentic, multi-agent, and coding workflows.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":4.25e-6,"cache_read_input_token_cost":1.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.0025,"search_context_size_high":0.0025,"search_context_size_medium":0.0025}},"list_pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":4.25e-6,"cache_read_input_token_cost":1.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.0025,"search_context_size_high":0.0025,"search_context_size_medium":0.0025}},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":1},{"id":"muse-wonder-1.0","object":"model","created":1792552674,"owned_by":"meta","mode":"chat","context_length":1048576,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":4e-6,"output_cost_per_token":0.00002,"cache_read_input_token_cost":2e-7,"search_context_cost_per_query":{"search_context_size_low":0.0025,"search_context_size_high":0.0025,"search_context_size_medium":0.0025}},"pricing_endpoint":"meta/muse-wonder-1.0","regions":[{"code":"eu","name":"Europe"}],"alias_of":null,"endpoints":[{"id":"meta/muse-wonder-1.0","object":"model","created":1792552674,"owned_by":"meta","model_name":"muse-wonder-1.0","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":4e-6,"output_cost_per_token":0.00002,"cache_read_input_token_cost":2e-7,"search_context_cost_per_query":{"search_context_size_low":0.0025,"search_context_size_high":0.0025,"search_context_size_medium":0.0025}},"list_pricing":{"input_cost_per_token":4e-6,"output_cost_per_token":0.00002,"cache_read_input_token_cost":2e-7,"search_context_cost_per_query":{"search_context_size_low":0.0025,"search_context_size_high":0.0025,"search_context_size_medium":0.0025}},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":1},{"id":"qwen3.8-27b-fp8","object":"model","created":1792508826,"owned_by":"qwen","mode":"chat","context_length":100000,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4.4056017225902734e-7,"output_cost_per_token":3.304201291942705e-6},"pricing_endpoint":"infomaniak/Qwen/Qwen3.8-27B-FP8","regions":[{"code":"ch","name":"Switzerland"}],"alias_of":null,"endpoints":[{"id":"infomaniak/Qwen/Qwen3.8-27B-FP8","object":"model","created":1792508826,"owned_by":"infomaniak","model_name":"Qwen/Qwen3.8-27B-FP8","context_length":100000,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"Qwen3.8 27B is an open-weight dense vision-language model from Qwen.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4.4056017225902734e-7,"output_cost_per_token":3.304201291942705e-6},"list_pricing":{"input_cost_per_token":4.4056017225902734e-7,"output_cost_per_token":3.304201291942705e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"ch","name":"Switzerland"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"quasar-1-2-358b","object":"model","created":1792422409,"owned_by":"compactifai","mode":"chat","context_length":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.1e-7,"output_cost_per_token":3.3e-7,"cache_read_input_token_cost":9.9e-9},"pricing_endpoint":"compactifai/quasar-1-2-358b","regions":[{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"compactifai/quasar-1-2-358b","object":"model","created":1792422409,"owned_by":"compactifai","model_name":"quasar-1-2-358b","context_length":null,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.1e-7,"output_cost_per_token":3.3e-7,"cache_read_input_token_cost":9.9e-9},"list_pricing":{"input_cost_per_token":1.1e-7,"output_cost_per_token":3.3e-7,"cache_read_input_token_cost":9.9e-9},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":1},{"id":"beam","object":"model","created":1792163230,"owned_by":"reflection","mode":"chat","context_length":1048576,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.5e-7,"output_cost_per_token":1e-6,"cache_read_input_token_cost":2.5e-7},"pricing_endpoint":"nebius/reflection/beam","regions":[{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"nebius/reflection/beam","object":"model","created":1792163230,"owned_by":"nebius","model_name":"reflection/beam","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.5e-7,"output_cost_per_token":1e-6,"cache_read_input_token_cost":2.5e-7},"list_pricing":{"input_cost_per_token":2.5e-7,"output_cost_per_token":1e-6,"cache_read_input_token_cost":2.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"together_ai/reflection/Beam-1.0-501B-A23B","object":"model","created":1792160499,"owned_by":"together_ai","model_name":"reflection/Beam-1.0-501B-A23B","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"Beam 1.0 is Reflection's open-weight reasoning model for coding and long-horizon agentic workflows.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4.0000000000000003e-7,"output_cost_per_token":1.2e-6,"cache_read_input_token_cost":4e-8},"list_pricing":{"input_cost_per_token":4.0000000000000003e-7,"output_cost_per_token":1.2e-6,"cache_read_input_token_cost":4e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":2},{"id":"muse-spark-open","object":"model","created":1792127615,"owned_by":"meta","mode":"chat","context_length":1048576,"capabilities":{"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":4.25e-6,"cache_read_input_token_cost":1.5e-7},"pricing_endpoint":"together_ai/meta-models/Muse-Spark-Open-816B-A42B","regions":[{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"together_ai/meta-models/Muse-Spark-Open-816B-A42B","object":"model","created":1792127615,"owned_by":"together_ai","model_name":"meta-models/Muse-Spark-Open-816B-A42B","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":4.25e-6,"cache_read_input_token_cost":1.5e-7},"list_pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":4.25e-6,"cache_read_input_token_cost":1.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null},{"id":"fireworks_ai/accounts/fireworks/models/muse-spark-open","object":"model","created":1792087069,"owned_by":"fireworks_ai","model_name":"accounts/fireworks/models/muse-spark-open","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"Muse Spark Open is a coding-optimized open-weight model.","source":null,"capabilities":{"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":4.25e-6,"cache_read_input_token_cost":1.5e-7,"input_cost_per_token_priority":1.875e-6,"output_cost_per_token_priority":6.375e-6,"cache_read_input_token_cost_priority":2.25e-7},"list_pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":4.25e-6,"cache_read_input_token_cost":1.5e-7,"input_cost_per_token_priority":1.875e-6,"output_cost_per_token_priority":6.375e-6,"cache_read_input_token_cost_priority":2.25e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"nebius/meta-models/muse-spark-open","object":"model","created":1792087069,"owned_by":"nebius","model_name":"meta-models/muse-spark-open","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":null,"quantization":"fp4","retirement_date":null,"description":"Muse Spark Open is a coding-optimized open-weight model.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":4.25e-6,"cache_read_input_token_cost":1.25e-6},"list_pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":4.25e-6,"cache_read_input_token_cost":1.25e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":3},{"id":"nemotron-3.5-super-vl","object":"model","created":1792127615,"owned_by":"nvidia","mode":"chat","context_length":1048576,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":1.9999999500000002e-8},"pricing_endpoint":"deepinfra/nvidia/NVIDIA-Nemotron-3.5-Super-VL","regions":[{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"deepinfra/nvidia/NVIDIA-Nemotron-3.5-Super-VL","object":"model","created":1792127615,"owned_by":"deepinfra","model_name":"nvidia/NVIDIA-Nemotron-3.5-Super-VL","context_length":262144,"max_input_tokens":262144,"max_output_tokens":null,"quantization":"fp4","retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":1.9999999500000002e-8},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":1.9999999500000002e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"together_ai/nvidia/NVIDIA-Nemotron-3.5-Super-VL","object":"model","created":1792127615,"owned_by":"together_ai","model_name":"nvidia/NVIDIA-Nemotron-3.5-Super-VL","context_length":262144,"max_input_tokens":262144,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":2e-8},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":2e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null},{"id":"nebius/nvidia/Nemotron-3.5-Super-VL","object":"model","created":1792076662,"owned_by":"nebius","model_name":"nvidia/Nemotron-3.5-Super-VL","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":null,"quantization":"fp4","retirement_date":null,"description":"NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":9e-7,"cache_read_input_token_cost":3e-7},"list_pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":9e-7,"cache_read_input_token_cost":3e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":3},{"id":"apertus-v1.5-70b","object":"model","created":1792029544,"owned_by":"infomaniak","mode":"chat","context_length":100000,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":7.70980301453298e-7,"output_cost_per_token":2.753501076618921e-6},"pricing_endpoint":"infomaniak/swiss-ai/Apertus-v1.5-70B","regions":[{"code":"ch","name":"Switzerland"}],"alias_of":null,"endpoints":[{"id":"infomaniak/swiss-ai/Apertus-v1.5-70B","object":"model","created":1792029544,"owned_by":"infomaniak","model_name":"swiss-ai/Apertus-v1.5-70B","context_length":100000,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":7.70980301453298e-7,"output_cost_per_token":2.753501076618921e-6},"list_pricing":{"input_cost_per_token":7.70980301453298e-7,"output_cost_per_token":2.753501076618921e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"ch","name":"Switzerland"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"kimi-k2.6","object":"model","created":1792029544,"owned_by":"moonshot","mode":"chat","context_length":262144,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6.608402583885411e-7,"output_cost_per_token":3.304201291942705e-6},"pricing_endpoint":"infomaniak/moonshotai/Kimi-K2.6","regions":[{"code":"ap","name":"Asia"},{"code":"ch","name":"Switzerland"},{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"infomaniak/moonshotai/Kimi-K2.6","object":"model","created":1792029544,"owned_by":"infomaniak","model_name":"moonshotai/Kimi-K2.6","context_length":256000,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6.608402583885411e-7,"output_cost_per_token":3.304201291942705e-6},"list_pricing":{"input_cost_per_token":6.608402583885411e-7,"output_cost_per_token":3.304201291942705e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"ch","name":"Switzerland"}],"zero_data_retention":true,"alias_of":null},{"id":"greenpt/kimi-k2.6","object":"model","created":1791839241,"owned_by":"greenpt","model_name":"kimi-k2.6","context_length":256000,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":7.269242842273952e-7,"output_cost_per_token":4.130251614928381e-6,"cache_read_input_token_cost":2.4230809474246506e-7},"list_pricing":{"input_cost_per_token":7.269242842273952e-7,"output_cost_per_token":4.130251614928381e-6,"cache_read_input_token_cost":2.4230809474246506e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"tensorx/moonshotai/kimi-k2.6","object":"model","created":1787003349,"owned_by":"tensorx","model_name":"moonshotai/kimi-k2.6","context_length":262144,"max_input_tokens":262144,"max_output_tokens":64000,"quantization":null,"retirement_date":null,"description":"Served by TensorX at int4 quantization.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":4e-6,"cache_read_input_token_cost":2.5e-7},"list_pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":4e-6,"cache_read_input_token_cost":2.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"cloudflare/@cf/moonshotai/kimi-k2.6","object":"model","created":1776699402,"owned_by":"cloudflare","model_name":"@cf/moonshotai/kimi-k2.6","context_length":262144,"max_input_tokens":262144,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":9.499999999999999e-7,"output_cost_per_token":4e-6,"cache_read_input_token_cost":1.6e-7},"list_pricing":{"input_cost_per_token":9.499999999999999e-7,"output_cost_per_token":4e-6,"cache_read_input_token_cost":1.6e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"deepinfra/moonshotai/Kimi-K2.6","object":"model","created":1776699402,"owned_by":"deepinfra","model_name":"moonshotai/Kimi-K2.6","context_length":262144,"max_input_tokens":262144,"max_output_tokens":16384,"quantization":"fp4","retirement_date":null,"description":"Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":7.499999999999999e-7,"output_cost_per_token":3.5e-6,"cache_read_input_token_cost":1.5e-7},"list_pricing":{"input_cost_per_token":7.499999999999999e-7,"output_cost_per_token":3.5e-6,"cache_read_input_token_cost":1.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"moonshot/kimi-k2.6","object":"model","created":1776699402,"owned_by":"moonshot","model_name":"kimi-k2.6","context_length":262144,"max_input_tokens":262144,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration.","source":null,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":9.5e-7,"output_cost_per_token":4e-6,"cache_read_input_token_cost":1.6e-7},"list_pricing":{"input_cost_per_token":9.5e-7,"output_cost_per_token":4e-6,"cache_read_input_token_cost":1.6e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"ap","name":"Asia"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":6},{"id":"qwen3.5-122b-a10b","object":"model","created":1792029544,"owned_by":"qwen","mode":"chat","context_length":262144,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.2e-7,"output_cost_per_token":2.2e-6,"input_dbu_cost_per_token":3.143e-6,"output_dbu_cost_per_token":0.000031429,"cache_read_input_token_cost":2.2e-8,"cache_creation_input_token_cost":2.2e-7,"cache_creation_input_token_cost_priority":3.85e-7},"pricing_endpoint":"databricks/databricks-qwen35-122b-a10b","regions":[{"code":"ch","name":"Switzerland"},{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"infomaniak/Qwen/Qwen3.5-122B-A10B-FP8","object":"model","created":1792029544,"owned_by":"infomaniak","model_name":"Qwen/Qwen3.5-122B-A10B-FP8","context_length":200000,"max_input_tokens":null,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4.4899979682759196e-7,"output_cost_per_token":3.5919983746207357e-6},"list_pricing":{"input_cost_per_token":4.4899979682759196e-7,"output_cost_per_token":3.5919983746207357e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"ch","name":"Switzerland"}],"zero_data_retention":true,"alias_of":null},{"id":"tensorx/qwen/qwen3.5-122b-a10b","object":"model","created":1787003349,"owned_by":"tensorx","model_name":"qwen/qwen3.5-122b-a10b","context_length":262144,"max_input_tokens":262144,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"Served by TensorX at fp8 quantization.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":3.5e-6,"cache_read_input_token_cost":1.25e-7},"list_pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":3.5e-6,"cache_read_input_token_cost":1.25e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"databricks/databricks-qwen35-122b-a10b@eu","object":"model","created":1785417770,"owned_by":"databricks","model_name":"databricks-qwen35-122b-a10b","context_length":262144,"max_input_tokens":262144,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.2e-7,"output_cost_per_token":2.2e-6,"input_dbu_cost_per_token":3.143e-6,"output_dbu_cost_per_token":0.000031429,"cache_read_input_token_cost":2.2e-8,"cache_creation_input_token_cost":2.2e-7,"cache_creation_input_token_cost_priority":3.85e-7},"list_pricing":{"input_cost_per_token":2.2e-7,"output_cost_per_token":2.2e-6,"input_dbu_cost_per_token":3.143e-6,"output_dbu_cost_per_token":0.000031429,"cache_read_input_token_cost":2.2e-8,"cache_creation_input_token_cost":2.2e-7,"cache_creation_input_token_cost_priority":3.85e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"databricks/databricks-qwen35-122b-a10b","object":"model","created":1785417770,"owned_by":"databricks","model_name":"databricks-qwen35-122b-a10b","context_length":262144,"max_input_tokens":262144,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.2e-7,"output_cost_per_token":2.2e-6,"input_dbu_cost_per_token":3.143e-6,"output_dbu_cost_per_token":0.000031429,"cache_read_input_token_cost":2.2e-8,"cache_creation_input_token_cost":2.2e-7,"cache_creation_input_token_cost_priority":3.85e-7},"list_pricing":{"input_cost_per_token":2.2e-7,"output_cost_per_token":2.2e-6,"input_dbu_cost_per_token":3.143e-6,"output_dbu_cost_per_token":0.000031429,"cache_read_input_token_cost":2.2e-8,"cache_creation_input_token_cost":2.2e-7,"cache_creation_input_token_cost_priority":3.85e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"deepinfra/Qwen/Qwen3.5-122B-A10B","object":"model","created":1772053789,"owned_by":"deepinfra","model_name":"Qwen/Qwen3.5-122B-A10B","context_length":262144,"max_input_tokens":262144,"max_output_tokens":81920,"quantization":null,"retirement_date":null,"description":"The Qwen3.5 122B-A10B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. In terms of...","source":null,"capabilities":{"input_modalities":["image","text","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.9e-7,"output_cost_per_token":2.4e-6},"list_pricing":{"input_cost_per_token":2.9e-7,"output_cost_per_token":2.4e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"qwen/qwen3.5-122b-a10b","object":"model","created":1772053789,"owned_by":"qwen","model_name":"qwen3.5-122b-a10b","context_length":262144,"max_input_tokens":260096,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"The Qwen3.5 122B-A10B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. In terms of overall performance, this model is second only to Qwen3.5-397B-A17B. Its text capabilities significantly outperform those of Qwen3-235B-2507, and its visual capabilities surpass those of Qwen3-VL-235B.","source":null,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.6000000000000005e-7,"output_cost_per_token":2.0800000000000004e-6},"list_pricing":{"input_cost_per_token":4.0000000000000003e-7,"output_cost_per_token":3.2000000000000003e-6},"discount":0.35,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":6},{"id":"qwen3.5-397b-a17b","object":"model","created":1792029544,"owned_by":"qwen","mode":"chat","context_length":262144,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.8999999999999997e-7,"output_cost_per_token":2.34e-6},"pricing_endpoint":"qwen/qwen3.5-397b-a17b","regions":[{"code":"ch","name":"Switzerland"},{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"infomaniak/Qwen/Qwen3.5-397B-A17B-FP8","object":"model","created":1792029544,"owned_by":"infomaniak","model_name":"Qwen/Qwen3.5-397B-A17B-FP8","context_length":200000,"max_input_tokens":null,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":8.811203445180547e-7,"output_cost_per_token":3.965041550331246e-6},"list_pricing":{"input_cost_per_token":8.811203445180547e-7,"output_cost_per_token":3.965041550331246e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"ch","name":"Switzerland"}],"zero_data_retention":true,"alias_of":null},{"id":"greenpt/qwen3.5-397b-a17b","object":"model","created":1791839241,"owned_by":"greenpt","model_name":"qwen3.5-397b-a17b","context_length":250000,"max_input_tokens":null,"max_output_tokens":16000,"quantization":null,"retirement_date":null,"description":"The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":7.709803014532979e-7,"output_cost_per_token":4.791091873316923e-6},"list_pricing":{"input_cost_per_token":7.709803014532979e-7,"output_cost_per_token":4.791091873316923e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"ionos/Qwen/Qwen3.5-397B-A17B","object":"model","created":1786647205,"owned_by":"ionos","model_name":"Qwen/Qwen3.5-397B-A17B","context_length":262144,"max_input_tokens":null,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6.60840258388541e-7,"output_cost_per_token":3.965041550331247e-6},"list_pricing":{"input_cost_per_token":6.60840258388541e-7,"output_cost_per_token":3.965041550331247e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"ovhcloud/Qwen3.5-397B-A17B","object":"model","created":1780673223,"owned_by":"ovhcloud","model_name":"Qwen3.5-397B-A17B","context_length":262144,"max_input_tokens":null,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":7.1e-7,"output_cost_per_token":4.25e-6},"list_pricing":{"input_cost_per_token":7.1e-7,"output_cost_per_token":4.25e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"scaleway/qwen3.5-397b-a17b","object":"model","created":1773394870,"owned_by":"scaleway","model_name":"qwen3.5-397b-a17b","context_length":250000,"max_input_tokens":null,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6.60840258388541e-7,"output_cost_per_token":3.965041550331246e-6},"list_pricing":{"input_cost_per_token":6.60840258388541e-7,"output_cost_per_token":3.965041550331246e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"deepinfra/Qwen/Qwen3.5-397B-A17B","object":"model","created":1771223018,"owned_by":"deepinfra","model_name":"Qwen/Qwen3.5-397B-A17B","context_length":262144,"max_input_tokens":262144,"max_output_tokens":81920,"quantization":"fp8","retirement_date":null,"description":"The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency.","source":null,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4.5000000000000003e-7,"output_cost_per_token":2.9999999999999997e-6,"cache_read_input_token_cost":2.200000005e-7},"list_pricing":{"input_cost_per_token":4.5000000000000003e-7,"output_cost_per_token":2.9999999999999997e-6,"cache_read_input_token_cost":2.200000005e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"qwen/qwen3.5-397b-a17b","object":"model","created":1771223018,"owned_by":"qwen","model_name":"qwen3.5-397b-a17b","context_length":262144,"max_input_tokens":260096,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. It delivers state-of-the-art performance comparable to leading-edge models across a wide range of tasks, including language understanding, logical reasoning, code generation, agent-based tasks, image understanding, video understanding, and graphical user interface (GUI) interactions. With its robust code-generation and agent capabilities, the model exhibits strong generalization across diverse agent.","source":null,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.8999999999999997e-7,"output_cost_per_token":2.34e-6},"list_pricing":{"input_cost_per_token":6e-7,"output_cost_per_token":3.6000000000000003e-6},"discount":0.35,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":7},{"id":"claude-haiku-5.5","object":"model","created":1791954861,"owned_by":"anthropic","mode":"chat","context_length":1000000,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":5e-7,"provider_specific_entry":{"us":1.1},"cache_read_input_token_cost":1e-8,"input_cost_per_token_batches":5e-8,"output_cost_per_token_batches":2.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":1.25e-7,"cache_read_input_token_cost_batches":5e-9,"input_cost_per_token_above_100k_tokens":5e-7,"output_cost_per_token_above_100k_tokens":2.5e-6,"cache_creation_input_token_cost_above_1hr":2e-7,"cache_read_input_token_cost_above_100k_tokens":5e-8,"cache_creation_input_token_cost_above_100k_tokens":6.25e-7,"cache_creation_input_token_cost_above_1hr_above_100k_tokens":1e-6},"pricing_endpoint":"anthropic/claude-haiku-5-5","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"databricks/databricks-claude-haiku-5-5@eu","object":"model","created":1791954861,"owned_by":"databricks","model_name":"databricks-claude-haiku-5-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Haiku 5.5 is Anthropic's fastest model in the Claude 5.5 family, optimized for high-volume, speed-sensitive workloads. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":5e-7,"input_dbu_cost_per_token":1.429e-6,"output_dbu_cost_per_token":7.143e-6,"cache_read_input_token_cost":1e-8,"cache_creation_input_token_cost":1.25e-7,"input_cost_per_token_above_100k_tokens":5e-7,"output_cost_per_token_above_100k_tokens":2.5e-6,"cache_creation_input_token_cost_above_1hr":2e-7,"cache_read_input_token_cost_above_100k_tokens":5e-8,"cache_creation_input_token_cost_above_100k_tokens":6.25e-7,"cache_creation_input_token_cost_above_1hr_above_100k_tokens":1e-6},"list_pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":5e-7,"input_dbu_cost_per_token":1.429e-6,"output_dbu_cost_per_token":7.143e-6,"cache_read_input_token_cost":1e-8,"cache_creation_input_token_cost":1.25e-7,"input_cost_per_token_above_100k_tokens":5e-7,"output_cost_per_token_above_100k_tokens":2.5e-6,"cache_creation_input_token_cost_above_1hr":2e-7,"cache_read_input_token_cost_above_100k_tokens":5e-8,"cache_creation_input_token_cost_above_100k_tokens":6.25e-7,"cache_creation_input_token_cost_above_1hr_above_100k_tokens":1e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"databricks/databricks-claude-haiku-5-5","object":"model","created":1791954861,"owned_by":"databricks","model_name":"databricks-claude-haiku-5-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Haiku 5.5 is Anthropic's fastest model in the Claude 5.5 family, optimized for high-volume, speed-sensitive workloads. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":5e-7,"input_dbu_cost_per_token":1.429e-6,"output_dbu_cost_per_token":7.143e-6,"cache_read_input_token_cost":1e-8,"cache_creation_input_token_cost":1.25e-7,"input_cost_per_token_above_100k_tokens":5e-7,"output_cost_per_token_above_100k_tokens":2.5e-6,"cache_creation_input_token_cost_above_1hr":2e-7,"cache_read_input_token_cost_above_100k_tokens":5e-8,"cache_creation_input_token_cost_above_100k_tokens":6.25e-7,"cache_creation_input_token_cost_above_1hr_above_100k_tokens":1e-6},"list_pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":5e-7,"input_dbu_cost_per_token":1.429e-6,"output_dbu_cost_per_token":7.143e-6,"cache_read_input_token_cost":1e-8,"cache_creation_input_token_cost":1.25e-7,"input_cost_per_token_above_100k_tokens":5e-7,"output_cost_per_token_above_100k_tokens":2.5e-6,"cache_creation_input_token_cost_above_1hr":2e-7,"cache_read_input_token_cost_above_100k_tokens":5e-8,"cache_creation_input_token_cost_above_100k_tokens":6.25e-7,"cache_creation_input_token_cost_above_1hr_above_100k_tokens":1e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"amazon/anthropic.claude-haiku-5-5@eu","object":"model","created":1791397883,"owned_by":"amazon","model_name":"anthropic.claude-haiku-5-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.1e-7,"output_cost_per_token":5.5e-7,"cache_read_input_token_cost":1.1000000000000001e-8,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":1.375e-7,"input_cost_per_token_above_100k_tokens":5.5e-7,"output_cost_per_token_above_100k_tokens":2.7500000000000004e-6,"cache_creation_input_token_cost_above_1hr":2.2e-7,"cache_read_input_token_cost_above_100k_tokens":5.5e-8,"cache_creation_input_token_cost_above_100k_tokens":6.875000000000001e-7,"cache_creation_input_token_cost_above_1hr_above_100k_tokens":1.1e-6},"list_pricing":{"input_cost_per_token":1.1e-7,"output_cost_per_token":5.5e-7,"cache_read_input_token_cost":1.1000000000000001e-8,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":1.375e-7,"input_cost_per_token_above_100k_tokens":5.5e-7,"output_cost_per_token_above_100k_tokens":2.7500000000000004e-6,"cache_creation_input_token_cost_above_1hr":2.2e-7,"cache_read_input_token_cost_above_100k_tokens":5.5e-8,"cache_creation_input_token_cost_above_100k_tokens":6.875000000000001e-7,"cache_creation_input_token_cost_above_1hr_above_100k_tokens":1.1e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/anthropic.claude-haiku-5-5","object":"model","created":1791397883,"owned_by":"amazon","model_name":"anthropic.claude-haiku-5-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":1e-8,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":1.25e-7,"input_cost_per_token_above_100k_tokens":5e-7,"output_cost_per_token_above_100k_tokens":2.5e-6,"cache_creation_input_token_cost_above_1hr":2e-7,"cache_read_input_token_cost_above_100k_tokens":5e-8,"cache_creation_input_token_cost_above_100k_tokens":6.25e-7,"cache_creation_input_token_cost_above_1hr_above_100k_tokens":1e-6},"list_pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":1e-8,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":1.25e-7,"input_cost_per_token_above_100k_tokens":5e-7,"output_cost_per_token_above_100k_tokens":2.5e-6,"cache_creation_input_token_cost_above_1hr":2e-7,"cache_read_input_token_cost_above_100k_tokens":5e-8,"cache_creation_input_token_cost_above_100k_tokens":6.25e-7,"cache_creation_input_token_cost_above_1hr_above_100k_tokens":1e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/anthropic.claude-haiku-5-5@us","object":"model","created":1791397883,"owned_by":"amazon","model_name":"anthropic.claude-haiku-5-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.1e-7,"output_cost_per_token":5.5e-7,"cache_read_input_token_cost":1.1000000000000001e-8,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":1.375e-7,"input_cost_per_token_above_100k_tokens":5.5e-7,"output_cost_per_token_above_100k_tokens":2.7500000000000004e-6,"cache_creation_input_token_cost_above_1hr":2.2e-7,"cache_read_input_token_cost_above_100k_tokens":5.5e-8,"cache_creation_input_token_cost_above_100k_tokens":6.875000000000001e-7,"cache_creation_input_token_cost_above_1hr_above_100k_tokens":1.1e-6},"list_pricing":{"input_cost_per_token":1.1e-7,"output_cost_per_token":5.5e-7,"cache_read_input_token_cost":1.1000000000000001e-8,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":1.375e-7,"input_cost_per_token_above_100k_tokens":5.5e-7,"output_cost_per_token_above_100k_tokens":2.7500000000000004e-6,"cache_creation_input_token_cost_above_1hr":2.2e-7,"cache_read_input_token_cost_above_100k_tokens":5.5e-8,"cache_creation_input_token_cost_above_100k_tokens":6.875000000000001e-7,"cache_creation_input_token_cost_above_1hr_above_100k_tokens":1.1e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"anthropic/claude-haiku-5-5","object":"model","created":1791397883,"owned_by":"anthropic","model_name":"claude-haiku-5-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":5e-7,"provider_specific_entry":{"us":1.1},"cache_read_input_token_cost":1e-8,"input_cost_per_token_batches":5e-8,"output_cost_per_token_batches":2.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":1.25e-7,"cache_read_input_token_cost_batches":5e-9,"input_cost_per_token_above_100k_tokens":5e-7,"output_cost_per_token_above_100k_tokens":2.5e-6,"cache_creation_input_token_cost_above_1hr":2e-7,"cache_read_input_token_cost_above_100k_tokens":5e-8,"cache_creation_input_token_cost_above_100k_tokens":6.25e-7,"cache_creation_input_token_cost_above_1hr_above_100k_tokens":1e-6},"list_pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":5e-7,"provider_specific_entry":{"us":1.1},"cache_read_input_token_cost":1e-8,"input_cost_per_token_batches":5e-8,"output_cost_per_token_batches":2.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":1.25e-7,"cache_read_input_token_cost_batches":5e-9,"input_cost_per_token_above_100k_tokens":5e-7,"output_cost_per_token_above_100k_tokens":2.5e-6,"cache_creation_input_token_cost_above_1hr":2e-7,"cache_read_input_token_cost_above_100k_tokens":5e-8,"cache_creation_input_token_cost_above_100k_tokens":6.25e-7,"cache_creation_input_token_cost_above_1hr_above_100k_tokens":1e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null},{"id":"vertex/claude-haiku-5-5@eu","object":"model","created":1791397883,"owned_by":"vertex","model_name":"claude-haiku-5-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.1e-7,"output_cost_per_token":5.5e-7,"cache_read_input_token_cost":1.1000000000000001e-8,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":1.375e-7,"input_cost_per_token_above_100k_tokens":5.5e-7,"output_cost_per_token_above_100k_tokens":2.7500000000000004e-6,"cache_creation_input_token_cost_above_1hr":2.2e-7,"cache_read_input_token_cost_above_100k_tokens":5.5e-8,"cache_creation_input_token_cost_above_100k_tokens":6.875000000000001e-7,"cache_creation_input_token_cost_above_1hr_above_100k_tokens":1.1e-6},"list_pricing":{"input_cost_per_token":1.1e-7,"output_cost_per_token":5.5e-7,"cache_read_input_token_cost":1.1000000000000001e-8,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":1.375e-7,"input_cost_per_token_above_100k_tokens":5.5e-7,"output_cost_per_token_above_100k_tokens":2.7500000000000004e-6,"cache_creation_input_token_cost_above_1hr":2.2e-7,"cache_read_input_token_cost_above_100k_tokens":5.5e-8,"cache_creation_input_token_cost_above_100k_tokens":6.875000000000001e-7,"cache_creation_input_token_cost_above_1hr_above_100k_tokens":1.1e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"vertex/claude-haiku-5-5","object":"model","created":1791397883,"owned_by":"vertex","model_name":"claude-haiku-5-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":1e-8,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":1.25e-7,"input_cost_per_token_above_100k_tokens":5e-7,"output_cost_per_token_above_100k_tokens":2.5e-6,"cache_creation_input_token_cost_above_1hr":2e-7,"cache_read_input_token_cost_above_100k_tokens":5e-8,"cache_creation_input_token_cost_above_100k_tokens":6.25e-7,"cache_creation_input_token_cost_above_1hr_above_100k_tokens":1e-6},"list_pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":1e-8,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":1.25e-7,"input_cost_per_token_above_100k_tokens":5e-7,"output_cost_per_token_above_100k_tokens":2.5e-6,"cache_creation_input_token_cost_above_1hr":2e-7,"cache_read_input_token_cost_above_100k_tokens":5e-8,"cache_creation_input_token_cost_above_100k_tokens":6.25e-7,"cache_creation_input_token_cost_above_1hr_above_100k_tokens":1e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"vertex/claude-haiku-5-5@us","object":"model","created":1791397883,"owned_by":"vertex","model_name":"claude-haiku-5-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.1e-7,"output_cost_per_token":5.5e-7,"cache_read_input_token_cost":1.1000000000000001e-8,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":1.375e-7,"input_cost_per_token_above_100k_tokens":5.5e-7,"output_cost_per_token_above_100k_tokens":2.7500000000000004e-6,"cache_creation_input_token_cost_above_1hr":2.2e-7,"cache_read_input_token_cost_above_100k_tokens":5.5e-8,"cache_creation_input_token_cost_above_100k_tokens":6.875000000000001e-7,"cache_creation_input_token_cost_above_1hr_above_100k_tokens":1.1e-6},"list_pricing":{"input_cost_per_token":1.1e-7,"output_cost_per_token":5.5e-7,"cache_read_input_token_cost":1.1000000000000001e-8,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":1.375e-7,"input_cost_per_token_above_100k_tokens":5.5e-7,"output_cost_per_token_above_100k_tokens":2.7500000000000004e-6,"cache_creation_input_token_cost_above_1hr":2.2e-7,"cache_read_input_token_cost_above_100k_tokens":5.5e-8,"cache_creation_input_token_cost_above_100k_tokens":6.875000000000001e-7,"cache_creation_input_token_cost_above_1hr_above_100k_tokens":1.1e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":9},{"id":"~claude-haiku-latest","object":"model","created":1791954861,"owned_by":"anthropic","mode":"chat","context_length":1000000,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":5e-7,"provider_specific_entry":{"us":1.1},"cache_read_input_token_cost":1e-8,"input_cost_per_token_batches":5e-8,"output_cost_per_token_batches":2.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":1.25e-7,"cache_read_input_token_cost_batches":5e-9,"input_cost_per_token_above_100k_tokens":5e-7,"output_cost_per_token_above_100k_tokens":2.5e-6,"cache_creation_input_token_cost_above_1hr":2e-7,"cache_read_input_token_cost_above_100k_tokens":5e-8,"cache_creation_input_token_cost_above_100k_tokens":6.25e-7,"cache_creation_input_token_cost_above_1hr_above_100k_tokens":1e-6},"pricing_endpoint":"anthropic/claude-haiku-5-5","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":"claude-haiku-5.5","endpoints":[{"id":"databricks/databricks-claude-haiku-5-5@eu","object":"model","created":1791954861,"owned_by":"databricks","model_name":"databricks-claude-haiku-5-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Haiku 5.5 is Anthropic's fastest model in the Claude 5.5 family, optimized for high-volume, speed-sensitive workloads. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":5e-7,"input_dbu_cost_per_token":1.429e-6,"output_dbu_cost_per_token":7.143e-6,"cache_read_input_token_cost":1e-8,"cache_creation_input_token_cost":1.25e-7,"input_cost_per_token_above_100k_tokens":5e-7,"output_cost_per_token_above_100k_tokens":2.5e-6,"cache_creation_input_token_cost_above_1hr":2e-7,"cache_read_input_token_cost_above_100k_tokens":5e-8,"cache_creation_input_token_cost_above_100k_tokens":6.25e-7,"cache_creation_input_token_cost_above_1hr_above_100k_tokens":1e-6},"list_pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":5e-7,"input_dbu_cost_per_token":1.429e-6,"output_dbu_cost_per_token":7.143e-6,"cache_read_input_token_cost":1e-8,"cache_creation_input_token_cost":1.25e-7,"input_cost_per_token_above_100k_tokens":5e-7,"output_cost_per_token_above_100k_tokens":2.5e-6,"cache_creation_input_token_cost_above_1hr":2e-7,"cache_read_input_token_cost_above_100k_tokens":5e-8,"cache_creation_input_token_cost_above_100k_tokens":6.25e-7,"cache_creation_input_token_cost_above_1hr_above_100k_tokens":1e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"databricks/databricks-claude-haiku-5-5","object":"model","created":1791954861,"owned_by":"databricks","model_name":"databricks-claude-haiku-5-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Haiku 5.5 is Anthropic's fastest model in the Claude 5.5 family, optimized for high-volume, speed-sensitive workloads. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":5e-7,"input_dbu_cost_per_token":1.429e-6,"output_dbu_cost_per_token":7.143e-6,"cache_read_input_token_cost":1e-8,"cache_creation_input_token_cost":1.25e-7,"input_cost_per_token_above_100k_tokens":5e-7,"output_cost_per_token_above_100k_tokens":2.5e-6,"cache_creation_input_token_cost_above_1hr":2e-7,"cache_read_input_token_cost_above_100k_tokens":5e-8,"cache_creation_input_token_cost_above_100k_tokens":6.25e-7,"cache_creation_input_token_cost_above_1hr_above_100k_tokens":1e-6},"list_pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":5e-7,"input_dbu_cost_per_token":1.429e-6,"output_dbu_cost_per_token":7.143e-6,"cache_read_input_token_cost":1e-8,"cache_creation_input_token_cost":1.25e-7,"input_cost_per_token_above_100k_tokens":5e-7,"output_cost_per_token_above_100k_tokens":2.5e-6,"cache_creation_input_token_cost_above_1hr":2e-7,"cache_read_input_token_cost_above_100k_tokens":5e-8,"cache_creation_input_token_cost_above_100k_tokens":6.25e-7,"cache_creation_input_token_cost_above_1hr_above_100k_tokens":1e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"amazon/anthropic.claude-haiku-5-5@eu","object":"model","created":1791397883,"owned_by":"amazon","model_name":"anthropic.claude-haiku-5-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.1e-7,"output_cost_per_token":5.5e-7,"cache_read_input_token_cost":1.1000000000000001e-8,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":1.375e-7,"input_cost_per_token_above_100k_tokens":5.5e-7,"output_cost_per_token_above_100k_tokens":2.7500000000000004e-6,"cache_creation_input_token_cost_above_1hr":2.2e-7,"cache_read_input_token_cost_above_100k_tokens":5.5e-8,"cache_creation_input_token_cost_above_100k_tokens":6.875000000000001e-7,"cache_creation_input_token_cost_above_1hr_above_100k_tokens":1.1e-6},"list_pricing":{"input_cost_per_token":1.1e-7,"output_cost_per_token":5.5e-7,"cache_read_input_token_cost":1.1000000000000001e-8,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":1.375e-7,"input_cost_per_token_above_100k_tokens":5.5e-7,"output_cost_per_token_above_100k_tokens":2.7500000000000004e-6,"cache_creation_input_token_cost_above_1hr":2.2e-7,"cache_read_input_token_cost_above_100k_tokens":5.5e-8,"cache_creation_input_token_cost_above_100k_tokens":6.875000000000001e-7,"cache_creation_input_token_cost_above_1hr_above_100k_tokens":1.1e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/anthropic.claude-haiku-5-5","object":"model","created":1791397883,"owned_by":"amazon","model_name":"anthropic.claude-haiku-5-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":1e-8,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":1.25e-7,"input_cost_per_token_above_100k_tokens":5e-7,"output_cost_per_token_above_100k_tokens":2.5e-6,"cache_creation_input_token_cost_above_1hr":2e-7,"cache_read_input_token_cost_above_100k_tokens":5e-8,"cache_creation_input_token_cost_above_100k_tokens":6.25e-7,"cache_creation_input_token_cost_above_1hr_above_100k_tokens":1e-6},"list_pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":1e-8,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":1.25e-7,"input_cost_per_token_above_100k_tokens":5e-7,"output_cost_per_token_above_100k_tokens":2.5e-6,"cache_creation_input_token_cost_above_1hr":2e-7,"cache_read_input_token_cost_above_100k_tokens":5e-8,"cache_creation_input_token_cost_above_100k_tokens":6.25e-7,"cache_creation_input_token_cost_above_1hr_above_100k_tokens":1e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/anthropic.claude-haiku-5-5@us","object":"model","created":1791397883,"owned_by":"amazon","model_name":"anthropic.claude-haiku-5-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.1e-7,"output_cost_per_token":5.5e-7,"cache_read_input_token_cost":1.1000000000000001e-8,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":1.375e-7,"input_cost_per_token_above_100k_tokens":5.5e-7,"output_cost_per_token_above_100k_tokens":2.7500000000000004e-6,"cache_creation_input_token_cost_above_1hr":2.2e-7,"cache_read_input_token_cost_above_100k_tokens":5.5e-8,"cache_creation_input_token_cost_above_100k_tokens":6.875000000000001e-7,"cache_creation_input_token_cost_above_1hr_above_100k_tokens":1.1e-6},"list_pricing":{"input_cost_per_token":1.1e-7,"output_cost_per_token":5.5e-7,"cache_read_input_token_cost":1.1000000000000001e-8,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":1.375e-7,"input_cost_per_token_above_100k_tokens":5.5e-7,"output_cost_per_token_above_100k_tokens":2.7500000000000004e-6,"cache_creation_input_token_cost_above_1hr":2.2e-7,"cache_read_input_token_cost_above_100k_tokens":5.5e-8,"cache_creation_input_token_cost_above_100k_tokens":6.875000000000001e-7,"cache_creation_input_token_cost_above_1hr_above_100k_tokens":1.1e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"anthropic/claude-haiku-5-5","object":"model","created":1791397883,"owned_by":"anthropic","model_name":"claude-haiku-5-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":5e-7,"provider_specific_entry":{"us":1.1},"cache_read_input_token_cost":1e-8,"input_cost_per_token_batches":5e-8,"output_cost_per_token_batches":2.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":1.25e-7,"cache_read_input_token_cost_batches":5e-9,"input_cost_per_token_above_100k_tokens":5e-7,"output_cost_per_token_above_100k_tokens":2.5e-6,"cache_creation_input_token_cost_above_1hr":2e-7,"cache_read_input_token_cost_above_100k_tokens":5e-8,"cache_creation_input_token_cost_above_100k_tokens":6.25e-7,"cache_creation_input_token_cost_above_1hr_above_100k_tokens":1e-6},"list_pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":5e-7,"provider_specific_entry":{"us":1.1},"cache_read_input_token_cost":1e-8,"input_cost_per_token_batches":5e-8,"output_cost_per_token_batches":2.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":1.25e-7,"cache_read_input_token_cost_batches":5e-9,"input_cost_per_token_above_100k_tokens":5e-7,"output_cost_per_token_above_100k_tokens":2.5e-6,"cache_creation_input_token_cost_above_1hr":2e-7,"cache_read_input_token_cost_above_100k_tokens":5e-8,"cache_creation_input_token_cost_above_100k_tokens":6.25e-7,"cache_creation_input_token_cost_above_1hr_above_100k_tokens":1e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null},{"id":"vertex/claude-haiku-5-5@eu","object":"model","created":1791397883,"owned_by":"vertex","model_name":"claude-haiku-5-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.1e-7,"output_cost_per_token":5.5e-7,"cache_read_input_token_cost":1.1000000000000001e-8,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":1.375e-7,"input_cost_per_token_above_100k_tokens":5.5e-7,"output_cost_per_token_above_100k_tokens":2.7500000000000004e-6,"cache_creation_input_token_cost_above_1hr":2.2e-7,"cache_read_input_token_cost_above_100k_tokens":5.5e-8,"cache_creation_input_token_cost_above_100k_tokens":6.875000000000001e-7,"cache_creation_input_token_cost_above_1hr_above_100k_tokens":1.1e-6},"list_pricing":{"input_cost_per_token":1.1e-7,"output_cost_per_token":5.5e-7,"cache_read_input_token_cost":1.1000000000000001e-8,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":1.375e-7,"input_cost_per_token_above_100k_tokens":5.5e-7,"output_cost_per_token_above_100k_tokens":2.7500000000000004e-6,"cache_creation_input_token_cost_above_1hr":2.2e-7,"cache_read_input_token_cost_above_100k_tokens":5.5e-8,"cache_creation_input_token_cost_above_100k_tokens":6.875000000000001e-7,"cache_creation_input_token_cost_above_1hr_above_100k_tokens":1.1e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"vertex/claude-haiku-5-5","object":"model","created":1791397883,"owned_by":"vertex","model_name":"claude-haiku-5-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":1e-8,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":1.25e-7,"input_cost_per_token_above_100k_tokens":5e-7,"output_cost_per_token_above_100k_tokens":2.5e-6,"cache_creation_input_token_cost_above_1hr":2e-7,"cache_read_input_token_cost_above_100k_tokens":5e-8,"cache_creation_input_token_cost_above_100k_tokens":6.25e-7,"cache_creation_input_token_cost_above_1hr_above_100k_tokens":1e-6},"list_pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":1e-8,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":1.25e-7,"input_cost_per_token_above_100k_tokens":5e-7,"output_cost_per_token_above_100k_tokens":2.5e-6,"cache_creation_input_token_cost_above_1hr":2e-7,"cache_read_input_token_cost_above_100k_tokens":5e-8,"cache_creation_input_token_cost_above_100k_tokens":6.25e-7,"cache_creation_input_token_cost_above_1hr_above_100k_tokens":1e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"vertex/claude-haiku-5-5@us","object":"model","created":1791397883,"owned_by":"vertex","model_name":"claude-haiku-5-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.1e-7,"output_cost_per_token":5.5e-7,"cache_read_input_token_cost":1.1000000000000001e-8,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":1.375e-7,"input_cost_per_token_above_100k_tokens":5.5e-7,"output_cost_per_token_above_100k_tokens":2.7500000000000004e-6,"cache_creation_input_token_cost_above_1hr":2.2e-7,"cache_read_input_token_cost_above_100k_tokens":5.5e-8,"cache_creation_input_token_cost_above_100k_tokens":6.875000000000001e-7,"cache_creation_input_token_cost_above_1hr_above_100k_tokens":1.1e-6},"list_pricing":{"input_cost_per_token":1.1e-7,"output_cost_per_token":5.5e-7,"cache_read_input_token_cost":1.1000000000000001e-8,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":1.375e-7,"input_cost_per_token_above_100k_tokens":5.5e-7,"output_cost_per_token_above_100k_tokens":2.7500000000000004e-6,"cache_creation_input_token_cost_above_1hr":2.2e-7,"cache_read_input_token_cost_above_100k_tokens":5.5e-8,"cache_creation_input_token_cost_above_100k_tokens":6.875000000000001e-7,"cache_creation_input_token_cost_above_1hr_above_100k_tokens":1.1e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":9},{"id":"gemini-4-argon","object":"model","created":1791907477,"owned_by":"google","mode":"chat","context_length":1048576,"capabilities":{"input_modalities":["audio","file","image","text","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"input_cost_per_audio_token":2e-6,"input_cost_per_image_token":2e-6,"cache_read_input_token_cost":1e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"cache_creation_input_token_cost":1.875e-7,"output_cost_per_reasoning_token":0.00001,"cache_read_input_audio_token_cost":1e-7,"google_maps_grounding_cost_per_query":0.007},"pricing_endpoint":"google/gemini-4-argon","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"google/gemini-4-argon","object":"model","created":1791907477,"owned_by":"google","model_name":"gemini-4-argon","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":32768,"quantization":null,"retirement_date":null,"description":"Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents.","source":null,"capabilities":{"input_modalities":["audio","file","image","text","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"input_cost_per_audio_token":2e-6,"input_cost_per_image_token":2e-6,"cache_read_input_token_cost":1e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"cache_creation_input_token_cost":1.875e-7,"output_cost_per_reasoning_token":0.00001,"cache_read_input_audio_token_cost":1e-7,"google_maps_grounding_cost_per_query":0.007},"list_pricing":{"input_cost_per_token":4e-6,"output_cost_per_token":0.00002,"input_cost_per_audio_token":4e-6,"input_cost_per_image_token":4e-6,"cache_read_input_token_cost":2e-7,"search_context_cost_per_query":{"search_context_size_low":0.028,"search_context_size_high":0.028,"search_context_size_medium":0.028},"cache_creation_input_token_cost":3.75e-7,"output_cost_per_reasoning_token":0.00002,"cache_read_input_audio_token_cost":2e-7,"google_maps_grounding_cost_per_query":0.014},"discount":0.5,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"vertex/gemini-4-argon@eu","object":"model","created":1791907477,"owned_by":"vertex","model_name":"gemini-4-argon","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":32768,"quantization":null,"retirement_date":null,"description":"Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents.","source":null,"capabilities":{"input_modalities":["audio","file","image","text","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2.2e-6,"output_cost_per_token":0.000011000000000000001,"input_cost_per_audio_token":2.2e-6,"input_cost_per_image_token":2.2e-6,"cache_read_input_token_cost":1.1e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"cache_creation_input_token_cost":2.0625e-7,"output_cost_per_reasoning_token":0.000011000000000000001,"cache_read_input_audio_token_cost":1.1e-7,"google_maps_grounding_cost_per_query":0.007700000000000001},"list_pricing":{"input_cost_per_token":4.4e-6,"output_cost_per_token":0.000022000000000000003,"input_cost_per_audio_token":4.4e-6,"input_cost_per_image_token":4.4e-6,"cache_read_input_token_cost":2.2e-7,"search_context_cost_per_query":{"search_context_size_low":0.028,"search_context_size_high":0.028,"search_context_size_medium":0.028},"cache_creation_input_token_cost":4.125e-7,"output_cost_per_reasoning_token":0.000022000000000000003,"cache_read_input_audio_token_cost":2.2e-7,"google_maps_grounding_cost_per_query":0.015400000000000002},"discount":0.5,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"vertex/gemini-4-argon","object":"model","created":1791907477,"owned_by":"vertex","model_name":"gemini-4-argon","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":32768,"quantization":null,"retirement_date":null,"description":"Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents.","source":null,"capabilities":{"input_modalities":["audio","file","image","text","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"input_cost_per_audio_token":2e-6,"input_cost_per_image_token":2e-6,"cache_read_input_token_cost":1e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"cache_creation_input_token_cost":1.875e-7,"output_cost_per_reasoning_token":0.00001,"cache_read_input_audio_token_cost":1e-7,"google_maps_grounding_cost_per_query":0.007},"list_pricing":{"input_cost_per_token":4e-6,"output_cost_per_token":0.00002,"input_cost_per_audio_token":4e-6,"input_cost_per_image_token":4e-6,"cache_read_input_token_cost":2e-7,"search_context_cost_per_query":{"search_context_size_low":0.028,"search_context_size_high":0.028,"search_context_size_medium":0.028},"cache_creation_input_token_cost":3.75e-7,"output_cost_per_reasoning_token":0.00002,"cache_read_input_audio_token_cost":2e-7,"google_maps_grounding_cost_per_query":0.014},"discount":0.5,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"vertex/gemini-4-argon@us","object":"model","created":1791907477,"owned_by":"vertex","model_name":"gemini-4-argon","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":32768,"quantization":null,"retirement_date":null,"description":"Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents.","source":null,"capabilities":{"input_modalities":["audio","file","image","text","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2.2e-6,"output_cost_per_token":0.000011000000000000001,"input_cost_per_audio_token":2.2e-6,"input_cost_per_image_token":2.2e-6,"cache_read_input_token_cost":1.1e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"cache_creation_input_token_cost":2.0625e-7,"output_cost_per_reasoning_token":0.000011000000000000001,"cache_read_input_audio_token_cost":1.1e-7,"google_maps_grounding_cost_per_query":0.007700000000000001},"list_pricing":{"input_cost_per_token":4.4e-6,"output_cost_per_token":0.000022000000000000003,"input_cost_per_audio_token":4.4e-6,"input_cost_per_image_token":4.4e-6,"cache_read_input_token_cost":2.2e-7,"search_context_cost_per_query":{"search_context_size_low":0.028,"search_context_size_high":0.028,"search_context_size_medium":0.028},"cache_creation_input_token_cost":4.125e-7,"output_cost_per_reasoning_token":0.000022000000000000003,"cache_read_input_audio_token_cost":2.2e-7,"google_maps_grounding_cost_per_query":0.015400000000000002},"discount":0.5,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":4},{"id":"glm-5.2-caveman","object":"model","created":1791839241,"owned_by":"greenpt","mode":"chat","context_length":1000000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.707170667503731e-6,"output_cost_per_token":5.066441980978815e-6,"cache_read_input_token_cost":4.4056017225902734e-7},"pricing_endpoint":"greenpt/glm-5.2-caveman","regions":[{"code":"eu","name":"Europe"}],"alias_of":null,"endpoints":[{"id":"greenpt/glm-5.2-caveman","object":"model","created":1791839241,"owned_by":"greenpt","model_name":"glm-5.2-caveman","context_length":1000000,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.707170667503731e-6,"output_cost_per_token":5.066441980978815e-6,"cache_read_input_token_cost":4.4056017225902734e-7},"list_pricing":{"input_cost_per_token":1.707170667503731e-6,"output_cost_per_token":5.066441980978815e-6,"cache_read_input_token_cost":4.4056017225902734e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"glm-5.2-caveman-lite","object":"model","created":1791839241,"owned_by":"greenpt","mode":"chat","context_length":1000000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.707170667503731e-6,"output_cost_per_token":5.066441980978815e-6,"cache_read_input_token_cost":4.4056017225902734e-7},"pricing_endpoint":"greenpt/glm-5.2-caveman-lite","regions":[{"code":"eu","name":"Europe"}],"alias_of":null,"endpoints":[{"id":"greenpt/glm-5.2-caveman-lite","object":"model","created":1791839241,"owned_by":"greenpt","model_name":"glm-5.2-caveman-lite","context_length":1000000,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.707170667503731e-6,"output_cost_per_token":5.066441980978815e-6,"cache_read_input_token_cost":4.4056017225902734e-7},"list_pricing":{"input_cost_per_token":1.707170667503731e-6,"output_cost_per_token":5.066441980978815e-6,"cache_read_input_token_cost":4.4056017225902734e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"glm-5.2-caveman-ultra","object":"model","created":1791839241,"owned_by":"greenpt","mode":"chat","context_length":1000000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.707170667503731e-6,"output_cost_per_token":5.066441980978815e-6,"cache_read_input_token_cost":4.4056017225902734e-7},"pricing_endpoint":"greenpt/glm-5.2-caveman-ultra","regions":[{"code":"eu","name":"Europe"}],"alias_of":null,"endpoints":[{"id":"greenpt/glm-5.2-caveman-ultra","object":"model","created":1791839241,"owned_by":"greenpt","model_name":"glm-5.2-caveman-ultra","context_length":1000000,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.707170667503731e-6,"output_cost_per_token":5.066441980978815e-6,"cache_read_input_token_cost":4.4056017225902734e-7},"list_pricing":{"input_cost_per_token":1.707170667503731e-6,"output_cost_per_token":5.066441980978815e-6,"cache_read_input_token_cost":4.4056017225902734e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"glm-5.2-honey","object":"model","created":1791839241,"owned_by":"greenpt","mode":"chat","context_length":1000000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.707170667503731e-6,"output_cost_per_token":5.066441980978815e-6,"cache_read_input_token_cost":4.4056017225902734e-7},"pricing_endpoint":"greenpt/glm-5.2-honey","regions":[{"code":"eu","name":"Europe"}],"alias_of":null,"endpoints":[{"id":"greenpt/glm-5.2-honey","object":"model","created":1791839241,"owned_by":"greenpt","model_name":"glm-5.2-honey","context_length":1000000,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.707170667503731e-6,"output_cost_per_token":5.066441980978815e-6,"cache_read_input_token_cost":4.4056017225902734e-7},"list_pricing":{"input_cost_per_token":1.707170667503731e-6,"output_cost_per_token":5.066441980978815e-6,"cache_read_input_token_cost":4.4056017225902734e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"glm-5.2-honey-lite","object":"model","created":1791839241,"owned_by":"greenpt","mode":"chat","context_length":1000000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.707170667503731e-6,"output_cost_per_token":5.066441980978815e-6,"cache_read_input_token_cost":4.4056017225902734e-7},"pricing_endpoint":"greenpt/glm-5.2-honey-lite","regions":[{"code":"eu","name":"Europe"}],"alias_of":null,"endpoints":[{"id":"greenpt/glm-5.2-honey-lite","object":"model","created":1791839241,"owned_by":"greenpt","model_name":"glm-5.2-honey-lite","context_length":1000000,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.707170667503731e-6,"output_cost_per_token":5.066441980978815e-6,"cache_read_input_token_cost":4.4056017225902734e-7},"list_pricing":{"input_cost_per_token":1.707170667503731e-6,"output_cost_per_token":5.066441980978815e-6,"cache_read_input_token_cost":4.4056017225902734e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"glm-5.2-honey-ultra","object":"model","created":1791839241,"owned_by":"greenpt","mode":"chat","context_length":1000000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.707170667503731e-6,"output_cost_per_token":5.066441980978815e-6,"cache_read_input_token_cost":4.4056017225902734e-7},"pricing_endpoint":"greenpt/glm-5.2-honey-ultra","regions":[{"code":"eu","name":"Europe"}],"alias_of":null,"endpoints":[{"id":"greenpt/glm-5.2-honey-ultra","object":"model","created":1791839241,"owned_by":"greenpt","model_name":"glm-5.2-honey-ultra","context_length":1000000,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.707170667503731e-6,"output_cost_per_token":5.066441980978815e-6,"cache_read_input_token_cost":4.4056017225902734e-7},"list_pricing":{"input_cost_per_token":1.707170667503731e-6,"output_cost_per_token":5.066441980978815e-6,"cache_read_input_token_cost":4.4056017225902734e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"glm-5.2-ponytail","object":"model","created":1791839241,"owned_by":"greenpt","mode":"chat","context_length":1000000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.707170667503731e-6,"output_cost_per_token":5.066441980978815e-6,"cache_read_input_token_cost":4.4056017225902734e-7},"pricing_endpoint":"greenpt/glm-5.2-ponytail","regions":[{"code":"eu","name":"Europe"}],"alias_of":null,"endpoints":[{"id":"greenpt/glm-5.2-ponytail","object":"model","created":1791839241,"owned_by":"greenpt","model_name":"glm-5.2-ponytail","context_length":1000000,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.707170667503731e-6,"output_cost_per_token":5.066441980978815e-6,"cache_read_input_token_cost":4.4056017225902734e-7},"list_pricing":{"input_cost_per_token":1.707170667503731e-6,"output_cost_per_token":5.066441980978815e-6,"cache_read_input_token_cost":4.4056017225902734e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"glm-5.2-ponytail-lite","object":"model","created":1791839241,"owned_by":"greenpt","mode":"chat","context_length":1000000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.707170667503731e-6,"output_cost_per_token":5.066441980978815e-6,"cache_read_input_token_cost":4.4056017225902734e-7},"pricing_endpoint":"greenpt/glm-5.2-ponytail-lite","regions":[{"code":"eu","name":"Europe"}],"alias_of":null,"endpoints":[{"id":"greenpt/glm-5.2-ponytail-lite","object":"model","created":1791839241,"owned_by":"greenpt","model_name":"glm-5.2-ponytail-lite","context_length":1000000,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.707170667503731e-6,"output_cost_per_token":5.066441980978815e-6,"cache_read_input_token_cost":4.4056017225902734e-7},"list_pricing":{"input_cost_per_token":1.707170667503731e-6,"output_cost_per_token":5.066441980978815e-6,"cache_read_input_token_cost":4.4056017225902734e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"glm-5.2-ponytail-ultra","object":"model","created":1791839241,"owned_by":"greenpt","mode":"chat","context_length":1000000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.707170667503731e-6,"output_cost_per_token":5.066441980978815e-6,"cache_read_input_token_cost":4.4056017225902734e-7},"pricing_endpoint":"greenpt/glm-5.2-ponytail-ultra","regions":[{"code":"eu","name":"Europe"}],"alias_of":null,"endpoints":[{"id":"greenpt/glm-5.2-ponytail-ultra","object":"model","created":1791839241,"owned_by":"greenpt","model_name":"glm-5.2-ponytail-ultra","context_length":1000000,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.707170667503731e-6,"output_cost_per_token":5.066441980978815e-6,"cache_read_input_token_cost":4.4056017225902734e-7},"list_pricing":{"input_cost_per_token":1.707170667503731e-6,"output_cost_per_token":5.066441980978815e-6,"cache_read_input_token_cost":4.4056017225902734e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"grok-4.7","object":"model","created":1791839241,"owned_by":"xai","mode":"chat","context_length":524288,"capabilities":{"input_modalities":["text","file","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":6e-6,"input_dbu_cost_per_token":0.000035714,"output_dbu_cost_per_token":0.00010714,"cache_read_input_token_cost":2e-7,"cache_creation_input_token_cost":2.5e-6},"pricing_endpoint":"databricks/databricks-grok-4-7","regions":[{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"databricks/databricks-grok-4-7","object":"model","created":1791839241,"owned_by":"databricks","model_name":"databricks-grok-4-7","context_length":500000,"max_input_tokens":500000,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"Grok 4.7 is a reasoning model developed by xAI for coding, agentic tasks, and knowledge work.","source":null,"capabilities":{"input_modalities":["text","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":6e-6,"input_dbu_cost_per_token":0.000035714,"output_dbu_cost_per_token":0.00010714,"cache_read_input_token_cost":2e-7,"cache_creation_input_token_cost":2.5e-6},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":6e-6,"input_dbu_cost_per_token":0.000035714,"output_dbu_cost_per_token":0.00010714,"cache_read_input_token_cost":2e-7,"cache_creation_input_token_cost":2.5e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"amazon/xai.grok-4.7","object":"model","created":1790658829,"owned_by":"amazon","model_name":"xai.grok-4.7","context_length":524288,"max_input_tokens":524288,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":6e-6,"input_cost_per_token_flex":1e-6,"output_cost_per_token_flex":3e-6,"cache_read_input_token_cost":5e-7,"input_cost_per_token_priority":3.5e-6,"output_cost_per_token_priority":0.0000105,"cache_read_input_token_cost_flex":2.5e-7,"cache_read_input_token_cost_priority":8.75e-7},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":6e-6,"input_cost_per_token_flex":1e-6,"output_cost_per_token_flex":3e-6,"cache_read_input_token_cost":5e-7,"input_cost_per_token_priority":3.5e-6,"output_cost_per_token_priority":0.0000105,"cache_read_input_token_cost_flex":2.5e-7,"cache_read_input_token_cost_priority":8.75e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/xai.grok-4.7@us","object":"model","created":1790658829,"owned_by":"amazon","model_name":"xai.grok-4.7","context_length":524288,"max_input_tokens":524288,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":6e-6,"input_cost_per_token_flex":1e-6,"output_cost_per_token_flex":3e-6,"cache_read_input_token_cost":5e-7,"input_cost_per_token_priority":3.5e-6,"output_cost_per_token_priority":0.0000105,"cache_read_input_token_cost_flex":2.5e-7,"cache_read_input_token_cost_priority":8.75e-7},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":6e-6,"input_cost_per_token_flex":1e-6,"output_cost_per_token_flex":3e-6,"cache_read_input_token_cost":5e-7,"input_cost_per_token_priority":3.5e-6,"output_cost_per_token_priority":0.0000105,"cache_read_input_token_cost_flex":2.5e-7,"cache_read_input_token_cost_priority":8.75e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"xai/grok-4.7","object":"model","created":1790007541,"owned_by":"xai","model_name":"grok-4.7","context_length":500000,"max_input_tokens":500000,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"Grok 4.7 is SpaceXAI's flagship model for coding, agentic tasks, and knowledge work, succeeding Grok 4.6.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":6e-6,"input_cost_per_image_token":2e-6,"cache_read_input_token_cost":5e-7,"search_context_cost_per_query":{"search_context_size_low":0.005,"search_context_size_high":0.005,"search_context_size_medium":0.005},"input_cost_per_token_above_200k_tokens":4e-6,"output_cost_per_token_above_200k_tokens":0.000012,"cache_read_input_token_cost_above_200k_tokens":1e-6},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":6e-6,"input_cost_per_image_token":2e-6,"cache_read_input_token_cost":5e-7,"search_context_cost_per_query":{"search_context_size_low":0.005,"search_context_size_high":0.005,"search_context_size_medium":0.005},"input_cost_per_token_above_200k_tokens":4e-6,"output_cost_per_token_above_200k_tokens":0.000012,"cache_read_input_token_cost_above_200k_tokens":1e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":4},{"id":"kimi-k2.7-code","object":"model","created":1791839241,"owned_by":"moonshot","mode":"chat","context_length":262144,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6.174999999999999e-7,"output_cost_per_token":2.6e-6,"cache_read_input_token_cost":1.2350000000000001e-7},"pricing_endpoint":"qwen/kimi-k2.7-code","regions":[{"code":"ap","name":"Asia"},{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"greenpt/kimi-k2.7-code","object":"model","created":1791839241,"owned_by":"greenpt","model_name":"kimi-k2.7-code","context_length":256000,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":8.480783315986277e-7,"output_cost_per_token":4.240391657993138e-6,"cache_read_input_token_cost":2.1807728526821854e-7},"list_pricing":{"input_cost_per_token":8.480783315986277e-7,"output_cost_per_token":4.240391657993138e-6,"cache_read_input_token_cost":2.1807728526821854e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"tencent/kimi-k2.7-code","object":"model","created":1790867221,"owned_by":"tencent","model_name":"kimi-k2.7-code","context_length":256000,"max_input_tokens":256000,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":9.5e-7,"output_cost_per_token":4e-6,"cache_read_input_token_cost":1.9e-7,"input_cost_per_token_cache_hit":1.9e-7,"cache_creation_input_token_cost":0.0},"list_pricing":{"input_cost_per_token":9.5e-7,"output_cost_per_token":4e-6,"cache_read_input_token_cost":1.9e-7,"input_cost_per_token_cache_hit":1.9e-7,"cache_creation_input_token_cost":0.0},"discount":null,"discount_ends_at":null,"regions":[{"code":"ap","name":"Asia"}],"zero_data_retention":true,"alias_of":null},{"id":"tensorx/moonshotai/kimi-k2.7-code","object":"model","created":1787003349,"owned_by":"tensorx","model_name":"moonshotai/kimi-k2.7-code","context_length":262144,"max_input_tokens":262144,"max_output_tokens":64000,"quantization":null,"retirement_date":null,"description":"Served by TensorX at int4 quantization.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":4.5e-6,"cache_read_input_token_cost":3.125e-7},"list_pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":4.5e-6,"cache_read_input_token_cost":3.125e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"cloudflare/@cf/moonshotai/kimi-k2.7-code","object":"model","created":1781266361,"owned_by":"cloudflare","model_name":"@cf/moonshotai/kimi-k2.7-code","context_length":262144,"max_input_tokens":262144,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":9.499999999999999e-7,"output_cost_per_token":4e-6,"cache_read_input_token_cost":1.9e-7},"list_pricing":{"input_cost_per_token":9.499999999999999e-7,"output_cost_per_token":4e-6,"cache_read_input_token_cost":1.9e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"deepinfra/moonshotai/Kimi-K2.7-Code","object":"model","created":1781266361,"owned_by":"deepinfra","model_name":"moonshotai/Kimi-K2.7-Code","context_length":262144,"max_input_tokens":null,"max_output_tokens":16384,"quantization":null,"retirement_date":null,"description":"MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts. It uses a native multimodal mixture-of-experts...","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6.8e-7,"output_cost_per_token":3.4e-6,"cache_read_input_token_cost":1.36e-7},"list_pricing":{"input_cost_per_token":6.8e-7,"output_cost_per_token":3.4e-6,"cache_read_input_token_cost":1.36e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"moonshot/kimi-k2.7-code","object":"model","created":1781266361,"owned_by":"moonshot","model_name":"kimi-k2.7-code","context_length":262144,"max_input_tokens":262144,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts.","source":null,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":9.5e-7,"output_cost_per_token":4e-6,"cache_read_input_token_cost":1.9e-7},"list_pricing":{"input_cost_per_token":9.5e-7,"output_cost_per_token":4e-6,"cache_read_input_token_cost":1.9e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"ap","name":"Asia"}],"zero_data_retention":false,"alias_of":null},{"id":"qwen/kimi-k2.7-code","object":"model","created":1781266361,"owned_by":"qwen","model_name":"kimi-k2.7-code","context_length":262144,"max_input_tokens":229376,"max_output_tokens":16384,"quantization":"fp8","retirement_date":null,"description":"kimi-k2.7-code is Kimi's most intelligent coding model to date. It follows instructions more reliably over long contexts and completes programming tasks with higher success rates. It supports text, image, and video inputs, along with thinking mode, conversation, and agent tasks.","source":null,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6.174999999999999e-7,"output_cost_per_token":2.6e-6,"cache_read_input_token_cost":1.2350000000000001e-7},"list_pricing":{"input_cost_per_token":9.499999999999999e-7,"output_cost_per_token":4e-6,"cache_read_input_token_cost":1.9e-7},"discount":0.35,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":7},{"id":"llama-3.3-70b-instruct","object":"model","created":1791839241,"owned_by":"meta","mode":"chat","context_length":131072,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":3.2e-7},"pricing_endpoint":"deepinfra/meta-llama/Llama-3.3-70B-Instruct","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"greenpt/llama-3.3-70b-instruct","object":"model","created":1791839241,"owned_by":"greenpt","model_name":"llama-3.3-70b-instruct","context_length":128000,"max_input_tokens":null,"max_output_tokens":16000,"quantization":null,"retirement_date":null,"description":"The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out).","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.2115404737123252e-6,"output_cost_per_token":1.2115404737123252e-6},"list_pricing":{"input_cost_per_token":1.2115404737123252e-6,"output_cost_per_token":1.2115404737123252e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"ionos/meta-llama/Llama-3.3-70B-Instruct","object":"model","created":1786647205,"owned_by":"ionos","model_name":"meta-llama/Llama-3.3-70B-Instruct","context_length":128000,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out).","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":7.159102799209195e-7,"output_cost_per_token":7.159102799209195e-7},"list_pricing":{"input_cost_per_token":7.159102799209195e-7,"output_cost_per_token":7.159102799209195e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/meta.llama3-3-70b-instruct-v1:0","object":"model","created":1781775085,"owned_by":"amazon","model_name":"meta.llama3-3-70b-instruct-v1:0","context_length":128000,"max_input_tokens":128000,"max_output_tokens":4096,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":7.2e-7,"output_cost_per_token":7.2e-7},"list_pricing":{"input_cost_per_token":7.2e-7,"output_cost_per_token":7.2e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"databricks/databricks-meta-llama-3-3-70b-instruct@eu","object":"model","created":1769507058,"owned_by":"databricks","model_name":"databricks-meta-llama-3-3-70b-instruct","context_length":128000,"max_input_tokens":128000,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"Llama 3.3 is a state-of-the-art 70B parameter dense language model trained and released by Meta. The model supports a context length of 128K tokens. The model is optimized for multilingual dialogue use cases and aligned with human preferences for helpfulness and safety. It is not intended for use in languages other than English. Meta Llama 3.3 is licensed under the Meta Llama 3.3 Community License, Copyright © Meta Platforms, Inc. All Rights Reserved. Customers are responsible for ensuring compliance with applicable model licenses.","source":"https://www.databricks.com/product/pricing/foundation-model-serving","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":1.5e-6,"input_dbu_cost_per_token":7.143e-6,"output_dbu_cost_per_token":0.000021429,"cache_read_input_token_cost":5e-8,"cache_creation_input_token_cost":5e-7},"list_pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":1.5e-6,"input_dbu_cost_per_token":7.143e-6,"output_dbu_cost_per_token":0.000021429,"cache_read_input_token_cost":5e-8,"cache_creation_input_token_cost":5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"databricks/databricks-meta-llama-3-3-70b-instruct","object":"model","created":1769507058,"owned_by":"databricks","model_name":"databricks-meta-llama-3-3-70b-instruct","context_length":128000,"max_input_tokens":128000,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"Llama 3.3 is a state-of-the-art 70B parameter dense language model trained and released by Meta. The model supports a context length of 128K tokens. The model is optimized for multilingual dialogue use cases and aligned with human preferences for helpfulness and safety. It is not intended for use in languages other than English. Meta Llama 3.3 is licensed under the Meta Llama 3.3 Community License, Copyright © Meta Platforms, Inc. All Rights Reserved. Customers are responsible for ensuring compliance with applicable model licenses.","source":"https://www.databricks.com/product/pricing/foundation-model-serving","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":1.5e-6,"input_dbu_cost_per_token":7.143e-6,"output_dbu_cost_per_token":0.000021429,"cache_read_input_token_cost":5e-8,"cache_creation_input_token_cost":5e-7},"list_pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":1.5e-6,"input_dbu_cost_per_token":7.143e-6,"output_dbu_cost_per_token":0.000021429,"cache_read_input_token_cost":5e-8,"cache_creation_input_token_cost":5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"ovhcloud/Meta-Llama-3_3-70B-Instruct","object":"model","created":1769507058,"owned_by":"ovhcloud","model_name":"Meta-Llama-3_3-70B-Instruct","context_length":131072,"max_input_tokens":131000,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":"https://endpoints.ai.cloud.ovh.net/models/meta-llama-3-3-70b-instruct","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":7.4e-7,"output_cost_per_token":7.4e-7},"list_pricing":{"input_cost_per_token":7.4e-7,"output_cost_per_token":7.4e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"scaleway/llama-3.3-70b-instruct","object":"model","created":1736258559,"owned_by":"scaleway","model_name":"llama-3.3-70b-instruct","context_length":128000,"max_input_tokens":null,"max_output_tokens":16384,"quantization":null,"retirement_date":null,"description":"The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out).","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":9.912603875828115e-7,"output_cost_per_token":9.912603875828115e-7},"list_pricing":{"input_cost_per_token":9.912603875828115e-7,"output_cost_per_token":9.912603875828115e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"deepinfra/meta-llama/Llama-3.3-70B-Instruct","object":"model","created":1733506137,"owned_by":"deepinfra","model_name":"meta-llama/Llama-3.3-70B-Instruct","context_length":131072,"max_input_tokens":131072,"max_output_tokens":16384,"quantization":"fp8","retirement_date":null,"description":"The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out).","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":3.2e-7},"list_pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":3.2e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":8},{"id":"mistral-medium-3.5","object":"model","created":1791839241,"owned_by":"mistral","mode":"chat","context_length":262144,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-6,"output_cost_per_token":7.5e-6,"cache_read_input_token_cost":1.5e-7,"input_cost_per_token_batches":7.5e-7,"output_cost_per_token_batches":3.75e-6,"cache_read_input_token_cost_batches":7.5e-8},"pricing_endpoint":"mistral/mistral-medium-3-5","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"greenpt/mistral-medium-3.5-128b","object":"model","created":1791839241,"owned_by":"greenpt","model_name":"mistral-medium-3.5-128b","context_length":180000,"max_input_tokens":null,"max_output_tokens":16000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.982520775165623e-6,"output_cost_per_token":9.912603875828116e-6},"list_pricing":{"input_cost_per_token":1.982520775165623e-6,"output_cost_per_token":9.912603875828116e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"scaleway/mistral-medium-3.5-128b","object":"model","created":1778158991,"owned_by":"scaleway","model_name":"mistral-medium-3.5-128b","context_length":256000,"max_input_tokens":null,"max_output_tokens":209715,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.6521006459713528e-6,"output_cost_per_token":8.260503229856763e-6},"list_pricing":{"input_cost_per_token":1.6521006459713528e-6,"output_cost_per_token":8.260503229856763e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"mistral/mistral-medium-3-5@eu","object":"model","created":1777570439,"owned_by":"mistral","model_name":"mistral-medium-3-5","context_length":262144,"max_input_tokens":262144,"max_output_tokens":209715,"quantization":null,"retirement_date":"2027-01-31","description":"Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.65e-6,"output_cost_per_token":8.25e-6,"cache_read_input_token_cost":1.65e-7,"input_cost_per_token_batches":8.25e-7,"output_cost_per_token_batches":4.125e-6,"cache_read_input_token_cost_batches":8.25e-8},"list_pricing":{"input_cost_per_token":1.65e-6,"output_cost_per_token":8.25e-6,"cache_read_input_token_cost":1.65e-7,"input_cost_per_token_batches":8.25e-7,"output_cost_per_token_batches":4.125e-6,"cache_read_input_token_cost_batches":8.25e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"mistral/mistral-medium-3-5","object":"model","created":1777570439,"owned_by":"mistral","model_name":"mistral-medium-3-5","context_length":262144,"max_input_tokens":262144,"max_output_tokens":209715,"quantization":null,"retirement_date":"2027-01-31","description":"Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-6,"output_cost_per_token":7.5e-6,"cache_read_input_token_cost":1.5e-7,"input_cost_per_token_batches":7.5e-7,"output_cost_per_token_batches":3.75e-6,"cache_read_input_token_cost_batches":7.5e-8},"list_pricing":{"input_cost_per_token":1.5e-6,"output_cost_per_token":7.5e-6,"cache_read_input_token_cost":1.5e-7,"input_cost_per_token_batches":7.5e-7,"output_cost_per_token_batches":3.75e-6,"cache_read_input_token_cost_batches":7.5e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"mistral/mistral-medium-3.5@eu","object":"model","created":1777570439,"owned_by":"mistral","model_name":"mistral-medium-3.5","context_length":262144,"max_input_tokens":262144,"max_output_tokens":209715,"quantization":null,"retirement_date":"2027-01-31","description":"Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.65e-6,"output_cost_per_token":8.25e-6,"cache_read_input_token_cost":1.65e-7,"input_cost_per_token_batches":8.25e-7,"output_cost_per_token_batches":4.125e-6,"cache_read_input_token_cost_batches":8.25e-8},"list_pricing":{"input_cost_per_token":1.65e-6,"output_cost_per_token":8.25e-6,"cache_read_input_token_cost":1.65e-7,"input_cost_per_token_batches":8.25e-7,"output_cost_per_token_batches":4.125e-6,"cache_read_input_token_cost_batches":8.25e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"mistral/mistral-medium-3.5","object":"model","created":1777570439,"owned_by":"mistral","model_name":"mistral-medium-3.5","context_length":262144,"max_input_tokens":262144,"max_output_tokens":209715,"quantization":null,"retirement_date":"2027-01-31","description":"Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-6,"output_cost_per_token":7.5e-6,"cache_read_input_token_cost":1.5e-7,"input_cost_per_token_batches":7.5e-7,"output_cost_per_token_batches":3.75e-6,"cache_read_input_token_cost_batches":7.5e-8},"list_pricing":{"input_cost_per_token":1.5e-6,"output_cost_per_token":7.5e-6,"cache_read_input_token_cost":1.5e-7,"input_cost_per_token_batches":7.5e-7,"output_cost_per_token_batches":3.75e-6,"cache_read_input_token_cost_batches":7.5e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":6},{"id":"mistral-small-3.2-24b-instruct-2506","object":"model","created":1791839241,"owned_by":"mistral","mode":"chat","context_length":131072,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":7.5e-8,"output_cost_per_token":2.0000000000000002e-7},"pricing_endpoint":"deepinfra/mistralai/Mistral-Small-3.2-24B-Instruct-2506","regions":[{"code":"eu","name":"Europe"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"greenpt/mistral-small-3.2-24b-instruct-2506","object":"model","created":1791839241,"owned_by":"greenpt","model_name":"mistral-small-3.2-24b-instruct-2506","context_length":128000,"max_input_tokens":null,"max_output_tokens":32000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.2028008612951367e-7,"output_cost_per_token":4.4056017225902734e-7},"list_pricing":{"input_cost_per_token":2.2028008612951367e-7,"output_cost_per_token":4.4056017225902734e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"ovhcloud/Mistral-Small-3.2-24B-Instruct-2506","object":"model","created":1769507058,"owned_by":"ovhcloud","model_name":"Mistral-Small-3.2-24B-Instruct-2506","context_length":131072,"max_input_tokens":128000,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":"https://endpoints.ai.cloud.ovh.net/models/mistral-small-3-2-24b-instruct-2506","capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":3.1e-7},"list_pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":3.1e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"deepinfra/mistralai/Mistral-Small-3.2-24B-Instruct-2506","object":"model","created":1767692616,"owned_by":"deepinfra","model_name":"mistralai/Mistral-Small-3.2-24B-Instruct-2506","context_length":128000,"max_input_tokens":128000,"max_output_tokens":null,"quantization":"fp8","retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":7.5e-8,"output_cost_per_token":2.0000000000000002e-7},"list_pricing":{"input_cost_per_token":7.5e-8,"output_cost_per_token":2.0000000000000002e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"scaleway/mistral-small-3.2-24b-instruct-2506","object":"model","created":1755006551,"owned_by":"scaleway","model_name":"mistral-small-3.2-24b-instruct-2506","context_length":128000,"max_input_tokens":null,"max_output_tokens":32768,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.6521006459713525e-7,"output_cost_per_token":3.8549015072664893e-7},"list_pricing":{"input_cost_per_token":1.6521006459713525e-7,"output_cost_per_token":3.8549015072664893e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":4},{"id":"~grok-latest","object":"model","created":1791839241,"owned_by":"xai","mode":"chat","context_length":524288,"capabilities":{"input_modalities":["text","file","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":6e-6,"input_dbu_cost_per_token":0.000035714,"output_dbu_cost_per_token":0.00010714,"cache_read_input_token_cost":2e-7,"cache_creation_input_token_cost":2.5e-6},"pricing_endpoint":"databricks/databricks-grok-4-7","regions":[{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":"grok-4.7","endpoints":[{"id":"databricks/databricks-grok-4-7","object":"model","created":1791839241,"owned_by":"databricks","model_name":"databricks-grok-4-7","context_length":500000,"max_input_tokens":500000,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"Grok 4.7 is a reasoning model developed by xAI for coding, agentic tasks, and knowledge work.","source":null,"capabilities":{"input_modalities":["text","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":6e-6,"input_dbu_cost_per_token":0.000035714,"output_dbu_cost_per_token":0.00010714,"cache_read_input_token_cost":2e-7,"cache_creation_input_token_cost":2.5e-6},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":6e-6,"input_dbu_cost_per_token":0.000035714,"output_dbu_cost_per_token":0.00010714,"cache_read_input_token_cost":2e-7,"cache_creation_input_token_cost":2.5e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"amazon/xai.grok-4.7","object":"model","created":1790658829,"owned_by":"amazon","model_name":"xai.grok-4.7","context_length":524288,"max_input_tokens":524288,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":6e-6,"input_cost_per_token_flex":1e-6,"output_cost_per_token_flex":3e-6,"cache_read_input_token_cost":5e-7,"input_cost_per_token_priority":3.5e-6,"output_cost_per_token_priority":0.0000105,"cache_read_input_token_cost_flex":2.5e-7,"cache_read_input_token_cost_priority":8.75e-7},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":6e-6,"input_cost_per_token_flex":1e-6,"output_cost_per_token_flex":3e-6,"cache_read_input_token_cost":5e-7,"input_cost_per_token_priority":3.5e-6,"output_cost_per_token_priority":0.0000105,"cache_read_input_token_cost_flex":2.5e-7,"cache_read_input_token_cost_priority":8.75e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/xai.grok-4.7@us","object":"model","created":1790658829,"owned_by":"amazon","model_name":"xai.grok-4.7","context_length":524288,"max_input_tokens":524288,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":6e-6,"input_cost_per_token_flex":1e-6,"output_cost_per_token_flex":3e-6,"cache_read_input_token_cost":5e-7,"input_cost_per_token_priority":3.5e-6,"output_cost_per_token_priority":0.0000105,"cache_read_input_token_cost_flex":2.5e-7,"cache_read_input_token_cost_priority":8.75e-7},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":6e-6,"input_cost_per_token_flex":1e-6,"output_cost_per_token_flex":3e-6,"cache_read_input_token_cost":5e-7,"input_cost_per_token_priority":3.5e-6,"output_cost_per_token_priority":0.0000105,"cache_read_input_token_cost_flex":2.5e-7,"cache_read_input_token_cost_priority":8.75e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"xai/grok-4.7","object":"model","created":1790007541,"owned_by":"xai","model_name":"grok-4.7","context_length":500000,"max_input_tokens":500000,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"Grok 4.7 is SpaceXAI's flagship model for coding, agentic tasks, and knowledge work, succeeding Grok 4.6.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":6e-6,"input_cost_per_image_token":2e-6,"cache_read_input_token_cost":5e-7,"search_context_cost_per_query":{"search_context_size_low":0.005,"search_context_size_high":0.005,"search_context_size_medium":0.005},"input_cost_per_token_above_200k_tokens":4e-6,"output_cost_per_token_above_200k_tokens":0.000012,"cache_read_input_token_cost_above_200k_tokens":1e-6},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":6e-6,"input_cost_per_image_token":2e-6,"cache_read_input_token_cost":5e-7,"search_context_cost_per_query":{"search_context_size_low":0.005,"search_context_size_high":0.005,"search_context_size_medium":0.005},"input_cost_per_token_above_200k_tokens":4e-6,"output_cost_per_token_above_200k_tokens":0.000012,"cache_read_input_token_cost_above_200k_tokens":1e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":4},{"id":"green-l","object":"model","created":1791649789,"owned_by":"greenpt","mode":"chat","context_length":128000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.753501076618921e-7,"output_cost_per_token":8.811203445180547e-7},"pricing_endpoint":"greenpt/green-l","regions":[{"code":"eu","name":"Europe"}],"alias_of":null,"endpoints":[{"id":"greenpt/green-l","object":"model","created":1791649789,"owned_by":"greenpt","model_name":"green-l","context_length":128000,"max_input_tokens":null,"max_output_tokens":32000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.753501076618921e-7,"output_cost_per_token":8.811203445180547e-7},"list_pricing":{"input_cost_per_token":2.753501076618921e-7,"output_cost_per_token":8.811203445180547e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"green-l-raw","object":"model","created":1791649789,"owned_by":"greenpt","mode":"chat","context_length":128000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.753501076618921e-7,"output_cost_per_token":8.811203445180547e-7},"pricing_endpoint":"greenpt/green-l-raw","regions":[{"code":"eu","name":"Europe"}],"alias_of":null,"endpoints":[{"id":"greenpt/green-l-raw","object":"model","created":1791649789,"owned_by":"greenpt","model_name":"green-l-raw","context_length":128000,"max_input_tokens":null,"max_output_tokens":32000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.753501076618921e-7,"output_cost_per_token":8.811203445180547e-7},"list_pricing":{"input_cost_per_token":2.753501076618921e-7,"output_cost_per_token":8.811203445180547e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"green-r","object":"model","created":1791649789,"owned_by":"greenpt","mode":"chat","context_length":128000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.8549015072664893e-7,"output_cost_per_token":1.04633040911519e-6},"pricing_endpoint":"greenpt/green-r","regions":[{"code":"eu","name":"Europe"}],"alias_of":null,"endpoints":[{"id":"greenpt/green-r","object":"model","created":1791649789,"owned_by":"greenpt","model_name":"green-r","context_length":128000,"max_input_tokens":null,"max_output_tokens":32000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.8549015072664893e-7,"output_cost_per_token":1.04633040911519e-6},"list_pricing":{"input_cost_per_token":3.8549015072664893e-7,"output_cost_per_token":1.04633040911519e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"green-r-raw","object":"model","created":1791649789,"owned_by":"greenpt","mode":"chat","context_length":128000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.8549015072664893e-7,"output_cost_per_token":1.04633040911519e-6},"pricing_endpoint":"greenpt/green-r-raw","regions":[{"code":"eu","name":"Europe"}],"alias_of":null,"endpoints":[{"id":"greenpt/green-r-raw","object":"model","created":1791649789,"owned_by":"greenpt","model_name":"green-r-raw","context_length":128000,"max_input_tokens":null,"max_output_tokens":32000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.8549015072664893e-7,"output_cost_per_token":1.04633040911519e-6},"list_pricing":{"input_cost_per_token":3.8549015072664893e-7,"output_cost_per_token":1.04633040911519e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"step-5-preview","object":"model","created":1791462849,"owned_by":"stepfun","mode":"chat","context_length":1048576,"capabilities":{"input_modalities":["text","image","video","audio"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":2.7e-6,"cache_read_input_token_cost":5e-8},"pricing_endpoint":"tencent/step-5-preview","regions":[{"code":"ap","name":"Asia"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"deepinfra/stepfun-ai/Step-5-Preview","object":"model","created":1791462849,"owned_by":"deepinfra","model_name":"stepfun-ai/Step-5-Preview","context_length":1048576,"max_input_tokens":null,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"Step 5 Preview is StepFun's flagship model for agentic work, built on a sparse Mixture-of-Experts architecture (27B active / 600B total parameters). It performs strongly in software engineering and professional...","source":null,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":2.7e-6,"cache_read_input_token_cost":1.0000000000000001e-7},"list_pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":2.7e-6,"cache_read_input_token_cost":1.0000000000000001e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"tencent/step-5-preview","object":"model","created":1791004468,"owned_by":"tencent","model_name":"step-5-preview","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":64000,"quantization":null,"retirement_date":null,"description":"Step 5 Preview is StepFun's flagship model for agentic work, built on a sparse Mixture-of-Experts architecture (27B active / 600B total parameters).","source":null,"capabilities":{"input_modalities":["text","image","video","audio"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":2.7e-6,"cache_read_input_token_cost":5e-8},"list_pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":2.7e-6,"cache_read_input_token_cost":5e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"ap","name":"Asia"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"gpt-4.1-nano","object":"model","created":1791407575,"owned_by":"openai","mode":"chat","context_length":1047576,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":4e-7,"cache_read_input_token_cost":2.5e-8},"pricing_endpoint":"azure/gpt-4.1-nano","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"azure/gpt-4.1-nano@eu","object":"model","created":1791407575,"owned_by":"azure","model_name":"gpt-4.1-nano","context_length":1047576,"max_input_tokens":1047576,"max_output_tokens":32768,"quantization":null,"retirement_date":null,"description":"For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.1e-7,"output_cost_per_token":4.4e-7,"cache_read_input_token_cost":2.75e-8},"list_pricing":{"input_cost_per_token":1.1e-7,"output_cost_per_token":4.4e-7,"cache_read_input_token_cost":2.75e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"azure/gpt-4.1-nano","object":"model","created":1791407575,"owned_by":"azure","model_name":"gpt-4.1-nano","context_length":1047576,"max_input_tokens":1047576,"max_output_tokens":32768,"quantization":null,"retirement_date":null,"description":"For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":4e-7,"cache_read_input_token_cost":2.5e-8},"list_pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":4e-7,"cache_read_input_token_cost":2.5e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"gpt-6.1-sol","object":"model","created":1791350016,"owned_by":"openai","mode":"chat","context_length":1050000,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"input_cost_per_token_flex":1e-6,"output_cost_per_token_flex":5e-6,"cache_read_input_token_cost":1e-7,"input_cost_per_token_batches":1e-6,"input_cost_per_token_priority":4e-6,"output_cost_per_token_batches":5e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"input_cost_per_token_ultrafast":0.000012,"output_cost_per_token_priority":0.00002,"cache_creation_input_token_cost":2.5e-6,"output_cost_per_token_ultrafast":0.00006,"cache_read_input_token_cost_flex":5e-8,"cache_read_input_token_cost_batches":5e-8,"cache_creation_input_token_cost_flex":1.25e-6,"cache_read_input_token_cost_priority":2e-7,"cache_read_input_token_cost_ultrafast":6e-7,"input_cost_per_token_above_272k_tokens":4e-6,"output_cost_per_token_above_272k_tokens":0.000015,"cache_creation_input_token_cost_priority":5e-6,"cache_creation_input_token_cost_ultrafast":0.000015,"cache_creation_input_token_cost_above_12hr":5e-6,"input_cost_per_token_above_272k_tokens_flex":2e-6,"output_cost_per_token_above_272k_tokens_flex":7.5e-6,"cache_read_input_token_cost_above_272k_tokens":2e-7,"cache_creation_input_token_cost_above_12hr_flex":2.5e-6,"input_cost_per_token_above_272k_tokens_priority":8e-6,"input_cost_per_token_above_272k_tokens_ultrafast":0.000024,"output_cost_per_token_above_272k_tokens_priority":0.00003,"cache_creation_input_token_cost_above_272k_tokens":5e-6,"output_cost_per_token_above_272k_tokens_ultrafast":0.00009,"cache_read_input_token_cost_above_272k_tokens_flex":1e-7,"cache_creation_input_token_cost_above_12hr_priority":0.00001,"cache_creation_input_token_cost_above_12hr_ultrafast":0.00003,"cache_creation_input_token_cost_above_272k_tokens_flex":2.5e-6,"cache_read_input_token_cost_above_272k_tokens_priority":4e-7,"cache_read_input_token_cost_above_272k_tokens_ultrafast":1.2e-6,"cache_creation_input_token_cost_above_272k_tokens_priority":0.00001,"cache_creation_input_token_cost_above_272k_tokens_ultrafast":0.00003,"cache_creation_input_token_cost_above_12hr_above_272k_tokens":0.00001,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_flex":5e-6,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_priority":0.00002,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_ultrafast":0.00006},"pricing_endpoint":"openai/gpt-6.1-sol","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"databricks/databricks-gpt-6-1-sol@eu","object":"model","created":1791350016,"owned_by":"databricks","model_name":"databricks-gpt-6-1-sol","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-6.1 Sol is OpenAI's upgrade to GPT-6 Sol, with strong performance on agentic coding, computer use, and professional work. It supports text and image inputs and a long context window. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"input_dbu_cost_per_token":0.000028571,"output_dbu_cost_per_token":0.00014286,"cache_read_input_token_cost":2e-7,"cache_creation_input_token_cost":2.5e-6,"input_cost_per_token_above_272k_tokens":4e-6,"output_cost_per_token_above_272k_tokens":0.000015,"cache_creation_input_token_cost_priority":5e-6,"cache_read_input_token_cost_above_272k_tokens":2e-7,"input_cost_per_token_above_272k_tokens_priority":8e-6,"output_cost_per_token_above_272k_tokens_priority":0.00003,"cache_creation_input_token_cost_above_272k_tokens":5e-6,"cache_read_input_token_cost_above_272k_tokens_priority":4e-7,"cache_creation_input_token_cost_above_272k_tokens_priority":0.00001},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"input_dbu_cost_per_token":0.000028571,"output_dbu_cost_per_token":0.00014286,"cache_read_input_token_cost":2e-7,"cache_creation_input_token_cost":2.5e-6,"input_cost_per_token_above_272k_tokens":4e-6,"output_cost_per_token_above_272k_tokens":0.000015,"cache_creation_input_token_cost_priority":5e-6,"cache_read_input_token_cost_above_272k_tokens":2e-7,"input_cost_per_token_above_272k_tokens_priority":8e-6,"output_cost_per_token_above_272k_tokens_priority":0.00003,"cache_creation_input_token_cost_above_272k_tokens":5e-6,"cache_read_input_token_cost_above_272k_tokens_priority":4e-7,"cache_creation_input_token_cost_above_272k_tokens_priority":0.00001},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"databricks/databricks-gpt-6-1-sol","object":"model","created":1791350016,"owned_by":"databricks","model_name":"databricks-gpt-6-1-sol","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-6.1 Sol is OpenAI's upgrade to GPT-6 Sol, with strong performance on agentic coding, computer use, and professional work. It supports text and image inputs and a long context window. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"input_dbu_cost_per_token":0.000028571,"output_dbu_cost_per_token":0.00014286,"cache_read_input_token_cost":2e-7,"cache_creation_input_token_cost":2.5e-6,"input_cost_per_token_above_272k_tokens":4e-6,"output_cost_per_token_above_272k_tokens":0.000015,"cache_creation_input_token_cost_priority":5e-6,"cache_read_input_token_cost_above_272k_tokens":2e-7,"input_cost_per_token_above_272k_tokens_priority":8e-6,"output_cost_per_token_above_272k_tokens_priority":0.00003,"cache_creation_input_token_cost_above_272k_tokens":5e-6,"cache_read_input_token_cost_above_272k_tokens_priority":4e-7,"cache_creation_input_token_cost_above_272k_tokens_priority":0.00001},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"input_dbu_cost_per_token":0.000028571,"output_dbu_cost_per_token":0.00014286,"cache_read_input_token_cost":2e-7,"cache_creation_input_token_cost":2.5e-6,"input_cost_per_token_above_272k_tokens":4e-6,"output_cost_per_token_above_272k_tokens":0.000015,"cache_creation_input_token_cost_priority":5e-6,"cache_read_input_token_cost_above_272k_tokens":2e-7,"input_cost_per_token_above_272k_tokens_priority":8e-6,"output_cost_per_token_above_272k_tokens_priority":0.00003,"cache_creation_input_token_cost_above_272k_tokens":5e-6,"cache_read_input_token_cost_above_272k_tokens_priority":4e-7,"cache_creation_input_token_cost_above_272k_tokens_priority":0.00001},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"amazon/openai.gpt-6.1-sol","object":"model","created":1790725775,"owned_by":"amazon","model_name":"openai.gpt-6.1-sol","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"cache_read_input_token_cost":1e-7,"input_cost_per_token_ultrafast":0.000012,"cache_creation_input_token_cost":2.5e-6,"output_cost_per_token_ultrafast":0.00006,"cache_read_input_token_cost_ultrafast":6e-7,"input_cost_per_token_above_272k_tokens":4e-6,"output_cost_per_token_above_272k_tokens":0.000015,"cache_creation_input_token_cost_ultrafast":0.000015,"cache_read_input_token_cost_above_272k_tokens":2e-7,"input_cost_per_token_above_272k_tokens_ultrafast":0.000024,"cache_creation_input_token_cost_above_272k_tokens":5e-6,"output_cost_per_token_above_272k_tokens_ultrafast":0.00009,"cache_read_input_token_cost_above_272k_tokens_ultrafast":1.2e-6,"cache_creation_input_token_cost_above_272k_tokens_ultrafast":0.00003},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"cache_read_input_token_cost":1e-7,"input_cost_per_token_ultrafast":0.000012,"cache_creation_input_token_cost":2.5e-6,"output_cost_per_token_ultrafast":0.00006,"cache_read_input_token_cost_ultrafast":6e-7,"input_cost_per_token_above_272k_tokens":4e-6,"output_cost_per_token_above_272k_tokens":0.000015,"cache_creation_input_token_cost_ultrafast":0.000015,"cache_read_input_token_cost_above_272k_tokens":2e-7,"input_cost_per_token_above_272k_tokens_ultrafast":0.000024,"cache_creation_input_token_cost_above_272k_tokens":5e-6,"output_cost_per_token_above_272k_tokens_ultrafast":0.00009,"cache_read_input_token_cost_above_272k_tokens_ultrafast":1.2e-6,"cache_creation_input_token_cost_above_272k_tokens_ultrafast":0.00003},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"amazon/openai.gpt-6.1-sol@us","object":"model","created":1790725775,"owned_by":"amazon","model_name":"openai.gpt-6.1-sol","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"cache_read_input_token_cost":1e-7,"input_cost_per_token_ultrafast":0.000012,"cache_creation_input_token_cost":2.5e-6,"output_cost_per_token_ultrafast":0.00006,"cache_read_input_token_cost_ultrafast":6e-7,"input_cost_per_token_above_272k_tokens":4e-6,"output_cost_per_token_above_272k_tokens":0.000015,"cache_creation_input_token_cost_ultrafast":0.000015,"cache_read_input_token_cost_above_272k_tokens":2e-7,"input_cost_per_token_above_272k_tokens_ultrafast":0.000024,"cache_creation_input_token_cost_above_272k_tokens":5e-6,"output_cost_per_token_above_272k_tokens_ultrafast":0.00009,"cache_read_input_token_cost_above_272k_tokens_ultrafast":1.2e-6,"cache_creation_input_token_cost_above_272k_tokens_ultrafast":0.00003},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"cache_read_input_token_cost":1e-7,"input_cost_per_token_ultrafast":0.000012,"cache_creation_input_token_cost":2.5e-6,"output_cost_per_token_ultrafast":0.00006,"cache_read_input_token_cost_ultrafast":6e-7,"input_cost_per_token_above_272k_tokens":4e-6,"output_cost_per_token_above_272k_tokens":0.000015,"cache_creation_input_token_cost_ultrafast":0.000015,"cache_read_input_token_cost_above_272k_tokens":2e-7,"input_cost_per_token_above_272k_tokens_ultrafast":0.000024,"cache_creation_input_token_cost_above_272k_tokens":5e-6,"output_cost_per_token_above_272k_tokens_ultrafast":0.00009,"cache_read_input_token_cost_above_272k_tokens_ultrafast":1.2e-6,"cache_creation_input_token_cost_above_272k_tokens_ultrafast":0.00003},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null},{"id":"azure/gpt-6.1-sol@eu","object":"model","created":1790725775,"owned_by":"azure","model_name":"gpt-6.1-sol","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2.4e-6,"output_cost_per_token":0.000012,"input_cost_per_token_flex":1.2e-6,"output_cost_per_token_flex":6e-6,"cache_read_input_token_cost":1.2e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"cache_creation_input_token_cost":3e-6,"cache_read_input_token_cost_flex":6e-8,"cache_creation_input_token_cost_flex":1.5e-6,"input_cost_per_token_above_272k_tokens":4.8e-6,"output_cost_per_token_above_272k_tokens":0.000018,"input_cost_per_token_above_272k_tokens_flex":2.4e-6,"output_cost_per_token_above_272k_tokens_flex":9e-6,"cache_read_input_token_cost_above_272k_tokens":2.4e-7,"cache_creation_input_token_cost_above_272k_tokens":6e-6,"cache_read_input_token_cost_above_272k_tokens_flex":1.2e-7,"cache_creation_input_token_cost_above_272k_tokens_flex":3e-6},"list_pricing":{"input_cost_per_token":2.4e-6,"output_cost_per_token":0.000012,"input_cost_per_token_flex":1.2e-6,"output_cost_per_token_flex":6e-6,"cache_read_input_token_cost":1.2e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"cache_creation_input_token_cost":3e-6,"cache_read_input_token_cost_flex":6e-8,"cache_creation_input_token_cost_flex":1.5e-6,"input_cost_per_token_above_272k_tokens":4.8e-6,"output_cost_per_token_above_272k_tokens":0.000018,"input_cost_per_token_above_272k_tokens_flex":2.4e-6,"output_cost_per_token_above_272k_tokens_flex":9e-6,"cache_read_input_token_cost_above_272k_tokens":2.4e-7,"cache_creation_input_token_cost_above_272k_tokens":6e-6,"cache_read_input_token_cost_above_272k_tokens_flex":1.2e-7,"cache_creation_input_token_cost_above_272k_tokens_flex":3e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"azure/gpt-6.1-sol","object":"model","created":1790725775,"owned_by":"azure","model_name":"gpt-6.1-sol","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"input_cost_per_token_flex":1e-6,"output_cost_per_token_flex":5e-6,"cache_read_input_token_cost":1e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"cache_creation_input_token_cost":2.5e-6,"cache_read_input_token_cost_flex":5e-8,"cache_creation_input_token_cost_flex":1.25e-6,"input_cost_per_token_above_272k_tokens":4e-6,"output_cost_per_token_above_272k_tokens":0.000015,"input_cost_per_token_above_272k_tokens_flex":2e-6,"output_cost_per_token_above_272k_tokens_flex":7.5e-6,"cache_read_input_token_cost_above_272k_tokens":2e-7,"cache_creation_input_token_cost_above_272k_tokens":5e-6,"cache_read_input_token_cost_above_272k_tokens_flex":1e-7,"cache_creation_input_token_cost_above_272k_tokens_flex":2.5e-6},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"input_cost_per_token_flex":1e-6,"output_cost_per_token_flex":5e-6,"cache_read_input_token_cost":1e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"cache_creation_input_token_cost":2.5e-6,"cache_read_input_token_cost_flex":5e-8,"cache_creation_input_token_cost_flex":1.25e-6,"input_cost_per_token_above_272k_tokens":4e-6,"output_cost_per_token_above_272k_tokens":0.000015,"input_cost_per_token_above_272k_tokens_flex":2e-6,"output_cost_per_token_above_272k_tokens_flex":7.5e-6,"cache_read_input_token_cost_above_272k_tokens":2e-7,"cache_creation_input_token_cost_above_272k_tokens":5e-6,"cache_read_input_token_cost_above_272k_tokens_flex":1e-7,"cache_creation_input_token_cost_above_272k_tokens_flex":2.5e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"azure/gpt-6.1-sol@us","object":"model","created":1790725775,"owned_by":"azure","model_name":"gpt-6.1-sol","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2.2e-6,"output_cost_per_token":0.000011000000000000001,"input_cost_per_token_flex":1.1e-6,"output_cost_per_token_flex":5.500000000000001e-6,"cache_read_input_token_cost":1.1e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"cache_creation_input_token_cost":2.7500000000000004e-6,"cache_read_input_token_cost_flex":5.5e-8,"cache_creation_input_token_cost_flex":1.3750000000000002e-6,"input_cost_per_token_above_272k_tokens":4.4e-6,"output_cost_per_token_above_272k_tokens":0.0000165,"input_cost_per_token_above_272k_tokens_flex":2.2e-6,"output_cost_per_token_above_272k_tokens_flex":8.25e-6,"cache_read_input_token_cost_above_272k_tokens":2.2e-7,"cache_creation_input_token_cost_above_272k_tokens":5.500000000000001e-6,"cache_read_input_token_cost_above_272k_tokens_flex":1.1e-7,"cache_creation_input_token_cost_above_272k_tokens_flex":2.7500000000000004e-6},"list_pricing":{"input_cost_per_token":2.2e-6,"output_cost_per_token":0.000011000000000000001,"input_cost_per_token_flex":1.1e-6,"output_cost_per_token_flex":5.500000000000001e-6,"cache_read_input_token_cost":1.1e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"cache_creation_input_token_cost":2.7500000000000004e-6,"cache_read_input_token_cost_flex":5.5e-8,"cache_creation_input_token_cost_flex":1.3750000000000002e-6,"input_cost_per_token_above_272k_tokens":4.4e-6,"output_cost_per_token_above_272k_tokens":0.0000165,"input_cost_per_token_above_272k_tokens_flex":2.2e-6,"output_cost_per_token_above_272k_tokens_flex":8.25e-6,"cache_read_input_token_cost_above_272k_tokens":2.2e-7,"cache_creation_input_token_cost_above_272k_tokens":5.500000000000001e-6,"cache_read_input_token_cost_above_272k_tokens_flex":1.1e-7,"cache_creation_input_token_cost_above_272k_tokens_flex":2.7500000000000004e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"openai/gpt-6.1-sol","object":"model","created":1790702882,"owned_by":"openai","model_name":"gpt-6.1-sol","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series.","source":null,"capabilities":{"input_modalities":["file","image","text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"input_cost_per_token_flex":1e-6,"output_cost_per_token_flex":5e-6,"cache_read_input_token_cost":1e-7,"input_cost_per_token_batches":1e-6,"input_cost_per_token_priority":4e-6,"output_cost_per_token_batches":5e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"input_cost_per_token_ultrafast":0.000012,"output_cost_per_token_priority":0.00002,"cache_creation_input_token_cost":2.5e-6,"output_cost_per_token_ultrafast":0.00006,"cache_read_input_token_cost_flex":5e-8,"cache_read_input_token_cost_batches":5e-8,"cache_creation_input_token_cost_flex":1.25e-6,"cache_read_input_token_cost_priority":2e-7,"cache_read_input_token_cost_ultrafast":6e-7,"input_cost_per_token_above_272k_tokens":4e-6,"output_cost_per_token_above_272k_tokens":0.000015,"cache_creation_input_token_cost_priority":5e-6,"cache_creation_input_token_cost_ultrafast":0.000015,"cache_creation_input_token_cost_above_12hr":5e-6,"input_cost_per_token_above_272k_tokens_flex":2e-6,"output_cost_per_token_above_272k_tokens_flex":7.5e-6,"cache_read_input_token_cost_above_272k_tokens":2e-7,"cache_creation_input_token_cost_above_12hr_flex":2.5e-6,"input_cost_per_token_above_272k_tokens_priority":8e-6,"input_cost_per_token_above_272k_tokens_ultrafast":0.000024,"output_cost_per_token_above_272k_tokens_priority":0.00003,"cache_creation_input_token_cost_above_272k_tokens":5e-6,"output_cost_per_token_above_272k_tokens_ultrafast":0.00009,"cache_read_input_token_cost_above_272k_tokens_flex":1e-7,"cache_creation_input_token_cost_above_12hr_priority":0.00001,"cache_creation_input_token_cost_above_12hr_ultrafast":0.00003,"cache_creation_input_token_cost_above_272k_tokens_flex":2.5e-6,"cache_read_input_token_cost_above_272k_tokens_priority":4e-7,"cache_read_input_token_cost_above_272k_tokens_ultrafast":1.2e-6,"cache_creation_input_token_cost_above_272k_tokens_priority":0.00001,"cache_creation_input_token_cost_above_272k_tokens_ultrafast":0.00003,"cache_creation_input_token_cost_above_12hr_above_272k_tokens":0.00001,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_flex":5e-6,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_priority":0.00002,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_ultrafast":0.00006},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"input_cost_per_token_flex":1e-6,"output_cost_per_token_flex":5e-6,"cache_read_input_token_cost":1e-7,"input_cost_per_token_batches":1e-6,"input_cost_per_token_priority":4e-6,"output_cost_per_token_batches":5e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"input_cost_per_token_ultrafast":0.000012,"output_cost_per_token_priority":0.00002,"cache_creation_input_token_cost":2.5e-6,"output_cost_per_token_ultrafast":0.00006,"cache_read_input_token_cost_flex":5e-8,"cache_read_input_token_cost_batches":5e-8,"cache_creation_input_token_cost_flex":1.25e-6,"cache_read_input_token_cost_priority":2e-7,"cache_read_input_token_cost_ultrafast":6e-7,"input_cost_per_token_above_272k_tokens":4e-6,"output_cost_per_token_above_272k_tokens":0.000015,"cache_creation_input_token_cost_priority":5e-6,"cache_creation_input_token_cost_ultrafast":0.000015,"cache_creation_input_token_cost_above_12hr":5e-6,"input_cost_per_token_above_272k_tokens_flex":2e-6,"output_cost_per_token_above_272k_tokens_flex":7.5e-6,"cache_read_input_token_cost_above_272k_tokens":2e-7,"cache_creation_input_token_cost_above_12hr_flex":2.5e-6,"input_cost_per_token_above_272k_tokens_priority":8e-6,"input_cost_per_token_above_272k_tokens_ultrafast":0.000024,"output_cost_per_token_above_272k_tokens_priority":0.00003,"cache_creation_input_token_cost_above_272k_tokens":5e-6,"output_cost_per_token_above_272k_tokens_ultrafast":0.00009,"cache_read_input_token_cost_above_272k_tokens_flex":1e-7,"cache_creation_input_token_cost_above_12hr_priority":0.00001,"cache_creation_input_token_cost_above_12hr_ultrafast":0.00003,"cache_creation_input_token_cost_above_272k_tokens_flex":2.5e-6,"cache_read_input_token_cost_above_272k_tokens_priority":4e-7,"cache_read_input_token_cost_above_272k_tokens_ultrafast":1.2e-6,"cache_creation_input_token_cost_above_272k_tokens_priority":0.00001,"cache_creation_input_token_cost_above_272k_tokens_ultrafast":0.00003,"cache_creation_input_token_cost_above_12hr_above_272k_tokens":0.00001,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_flex":5e-6,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_priority":0.00002,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_ultrafast":0.00006},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":8},{"id":"~gpt-sol-latest","object":"model","created":1791350016,"owned_by":"openai","mode":"chat","context_length":1050000,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"input_cost_per_token_flex":1e-6,"output_cost_per_token_flex":5e-6,"cache_read_input_token_cost":1e-7,"input_cost_per_token_batches":1e-6,"input_cost_per_token_priority":4e-6,"output_cost_per_token_batches":5e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"input_cost_per_token_ultrafast":0.000012,"output_cost_per_token_priority":0.00002,"cache_creation_input_token_cost":2.5e-6,"output_cost_per_token_ultrafast":0.00006,"cache_read_input_token_cost_flex":5e-8,"cache_read_input_token_cost_batches":5e-8,"cache_creation_input_token_cost_flex":1.25e-6,"cache_read_input_token_cost_priority":2e-7,"cache_read_input_token_cost_ultrafast":6e-7,"input_cost_per_token_above_272k_tokens":4e-6,"output_cost_per_token_above_272k_tokens":0.000015,"cache_creation_input_token_cost_priority":5e-6,"cache_creation_input_token_cost_ultrafast":0.000015,"cache_creation_input_token_cost_above_12hr":5e-6,"input_cost_per_token_above_272k_tokens_flex":2e-6,"output_cost_per_token_above_272k_tokens_flex":7.5e-6,"cache_read_input_token_cost_above_272k_tokens":2e-7,"cache_creation_input_token_cost_above_12hr_flex":2.5e-6,"input_cost_per_token_above_272k_tokens_priority":8e-6,"input_cost_per_token_above_272k_tokens_ultrafast":0.000024,"output_cost_per_token_above_272k_tokens_priority":0.00003,"cache_creation_input_token_cost_above_272k_tokens":5e-6,"output_cost_per_token_above_272k_tokens_ultrafast":0.00009,"cache_read_input_token_cost_above_272k_tokens_flex":1e-7,"cache_creation_input_token_cost_above_12hr_priority":0.00001,"cache_creation_input_token_cost_above_12hr_ultrafast":0.00003,"cache_creation_input_token_cost_above_272k_tokens_flex":2.5e-6,"cache_read_input_token_cost_above_272k_tokens_priority":4e-7,"cache_read_input_token_cost_above_272k_tokens_ultrafast":1.2e-6,"cache_creation_input_token_cost_above_272k_tokens_priority":0.00001,"cache_creation_input_token_cost_above_272k_tokens_ultrafast":0.00003,"cache_creation_input_token_cost_above_12hr_above_272k_tokens":0.00001,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_flex":5e-6,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_priority":0.00002,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_ultrafast":0.00006},"pricing_endpoint":"openai/gpt-6.1-sol","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":"gpt-6.1-sol","endpoints":[{"id":"databricks/databricks-gpt-6-1-sol@eu","object":"model","created":1791350016,"owned_by":"databricks","model_name":"databricks-gpt-6-1-sol","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-6.1 Sol is OpenAI's upgrade to GPT-6 Sol, with strong performance on agentic coding, computer use, and professional work. It supports text and image inputs and a long context window. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"input_dbu_cost_per_token":0.000028571,"output_dbu_cost_per_token":0.00014286,"cache_read_input_token_cost":2e-7,"cache_creation_input_token_cost":2.5e-6,"input_cost_per_token_above_272k_tokens":4e-6,"output_cost_per_token_above_272k_tokens":0.000015,"cache_creation_input_token_cost_priority":5e-6,"cache_read_input_token_cost_above_272k_tokens":2e-7,"input_cost_per_token_above_272k_tokens_priority":8e-6,"output_cost_per_token_above_272k_tokens_priority":0.00003,"cache_creation_input_token_cost_above_272k_tokens":5e-6,"cache_read_input_token_cost_above_272k_tokens_priority":4e-7,"cache_creation_input_token_cost_above_272k_tokens_priority":0.00001},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"input_dbu_cost_per_token":0.000028571,"output_dbu_cost_per_token":0.00014286,"cache_read_input_token_cost":2e-7,"cache_creation_input_token_cost":2.5e-6,"input_cost_per_token_above_272k_tokens":4e-6,"output_cost_per_token_above_272k_tokens":0.000015,"cache_creation_input_token_cost_priority":5e-6,"cache_read_input_token_cost_above_272k_tokens":2e-7,"input_cost_per_token_above_272k_tokens_priority":8e-6,"output_cost_per_token_above_272k_tokens_priority":0.00003,"cache_creation_input_token_cost_above_272k_tokens":5e-6,"cache_read_input_token_cost_above_272k_tokens_priority":4e-7,"cache_creation_input_token_cost_above_272k_tokens_priority":0.00001},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"databricks/databricks-gpt-6-1-sol","object":"model","created":1791350016,"owned_by":"databricks","model_name":"databricks-gpt-6-1-sol","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-6.1 Sol is OpenAI's upgrade to GPT-6 Sol, with strong performance on agentic coding, computer use, and professional work. It supports text and image inputs and a long context window. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"input_dbu_cost_per_token":0.000028571,"output_dbu_cost_per_token":0.00014286,"cache_read_input_token_cost":2e-7,"cache_creation_input_token_cost":2.5e-6,"input_cost_per_token_above_272k_tokens":4e-6,"output_cost_per_token_above_272k_tokens":0.000015,"cache_creation_input_token_cost_priority":5e-6,"cache_read_input_token_cost_above_272k_tokens":2e-7,"input_cost_per_token_above_272k_tokens_priority":8e-6,"output_cost_per_token_above_272k_tokens_priority":0.00003,"cache_creation_input_token_cost_above_272k_tokens":5e-6,"cache_read_input_token_cost_above_272k_tokens_priority":4e-7,"cache_creation_input_token_cost_above_272k_tokens_priority":0.00001},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"input_dbu_cost_per_token":0.000028571,"output_dbu_cost_per_token":0.00014286,"cache_read_input_token_cost":2e-7,"cache_creation_input_token_cost":2.5e-6,"input_cost_per_token_above_272k_tokens":4e-6,"output_cost_per_token_above_272k_tokens":0.000015,"cache_creation_input_token_cost_priority":5e-6,"cache_read_input_token_cost_above_272k_tokens":2e-7,"input_cost_per_token_above_272k_tokens_priority":8e-6,"output_cost_per_token_above_272k_tokens_priority":0.00003,"cache_creation_input_token_cost_above_272k_tokens":5e-6,"cache_read_input_token_cost_above_272k_tokens_priority":4e-7,"cache_creation_input_token_cost_above_272k_tokens_priority":0.00001},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"amazon/openai.gpt-6.1-sol","object":"model","created":1790725775,"owned_by":"amazon","model_name":"openai.gpt-6.1-sol","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"cache_read_input_token_cost":1e-7,"input_cost_per_token_ultrafast":0.000012,"cache_creation_input_token_cost":2.5e-6,"output_cost_per_token_ultrafast":0.00006,"cache_read_input_token_cost_ultrafast":6e-7,"input_cost_per_token_above_272k_tokens":4e-6,"output_cost_per_token_above_272k_tokens":0.000015,"cache_creation_input_token_cost_ultrafast":0.000015,"cache_read_input_token_cost_above_272k_tokens":2e-7,"input_cost_per_token_above_272k_tokens_ultrafast":0.000024,"cache_creation_input_token_cost_above_272k_tokens":5e-6,"output_cost_per_token_above_272k_tokens_ultrafast":0.00009,"cache_read_input_token_cost_above_272k_tokens_ultrafast":1.2e-6,"cache_creation_input_token_cost_above_272k_tokens_ultrafast":0.00003},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"cache_read_input_token_cost":1e-7,"input_cost_per_token_ultrafast":0.000012,"cache_creation_input_token_cost":2.5e-6,"output_cost_per_token_ultrafast":0.00006,"cache_read_input_token_cost_ultrafast":6e-7,"input_cost_per_token_above_272k_tokens":4e-6,"output_cost_per_token_above_272k_tokens":0.000015,"cache_creation_input_token_cost_ultrafast":0.000015,"cache_read_input_token_cost_above_272k_tokens":2e-7,"input_cost_per_token_above_272k_tokens_ultrafast":0.000024,"cache_creation_input_token_cost_above_272k_tokens":5e-6,"output_cost_per_token_above_272k_tokens_ultrafast":0.00009,"cache_read_input_token_cost_above_272k_tokens_ultrafast":1.2e-6,"cache_creation_input_token_cost_above_272k_tokens_ultrafast":0.00003},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"amazon/openai.gpt-6.1-sol@us","object":"model","created":1790725775,"owned_by":"amazon","model_name":"openai.gpt-6.1-sol","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"cache_read_input_token_cost":1e-7,"input_cost_per_token_ultrafast":0.000012,"cache_creation_input_token_cost":2.5e-6,"output_cost_per_token_ultrafast":0.00006,"cache_read_input_token_cost_ultrafast":6e-7,"input_cost_per_token_above_272k_tokens":4e-6,"output_cost_per_token_above_272k_tokens":0.000015,"cache_creation_input_token_cost_ultrafast":0.000015,"cache_read_input_token_cost_above_272k_tokens":2e-7,"input_cost_per_token_above_272k_tokens_ultrafast":0.000024,"cache_creation_input_token_cost_above_272k_tokens":5e-6,"output_cost_per_token_above_272k_tokens_ultrafast":0.00009,"cache_read_input_token_cost_above_272k_tokens_ultrafast":1.2e-6,"cache_creation_input_token_cost_above_272k_tokens_ultrafast":0.00003},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"cache_read_input_token_cost":1e-7,"input_cost_per_token_ultrafast":0.000012,"cache_creation_input_token_cost":2.5e-6,"output_cost_per_token_ultrafast":0.00006,"cache_read_input_token_cost_ultrafast":6e-7,"input_cost_per_token_above_272k_tokens":4e-6,"output_cost_per_token_above_272k_tokens":0.000015,"cache_creation_input_token_cost_ultrafast":0.000015,"cache_read_input_token_cost_above_272k_tokens":2e-7,"input_cost_per_token_above_272k_tokens_ultrafast":0.000024,"cache_creation_input_token_cost_above_272k_tokens":5e-6,"output_cost_per_token_above_272k_tokens_ultrafast":0.00009,"cache_read_input_token_cost_above_272k_tokens_ultrafast":1.2e-6,"cache_creation_input_token_cost_above_272k_tokens_ultrafast":0.00003},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null},{"id":"azure/gpt-6.1-sol@eu","object":"model","created":1790725775,"owned_by":"azure","model_name":"gpt-6.1-sol","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2.4e-6,"output_cost_per_token":0.000012,"input_cost_per_token_flex":1.2e-6,"output_cost_per_token_flex":6e-6,"cache_read_input_token_cost":1.2e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"cache_creation_input_token_cost":3e-6,"cache_read_input_token_cost_flex":6e-8,"cache_creation_input_token_cost_flex":1.5e-6,"input_cost_per_token_above_272k_tokens":4.8e-6,"output_cost_per_token_above_272k_tokens":0.000018,"input_cost_per_token_above_272k_tokens_flex":2.4e-6,"output_cost_per_token_above_272k_tokens_flex":9e-6,"cache_read_input_token_cost_above_272k_tokens":2.4e-7,"cache_creation_input_token_cost_above_272k_tokens":6e-6,"cache_read_input_token_cost_above_272k_tokens_flex":1.2e-7,"cache_creation_input_token_cost_above_272k_tokens_flex":3e-6},"list_pricing":{"input_cost_per_token":2.4e-6,"output_cost_per_token":0.000012,"input_cost_per_token_flex":1.2e-6,"output_cost_per_token_flex":6e-6,"cache_read_input_token_cost":1.2e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"cache_creation_input_token_cost":3e-6,"cache_read_input_token_cost_flex":6e-8,"cache_creation_input_token_cost_flex":1.5e-6,"input_cost_per_token_above_272k_tokens":4.8e-6,"output_cost_per_token_above_272k_tokens":0.000018,"input_cost_per_token_above_272k_tokens_flex":2.4e-6,"output_cost_per_token_above_272k_tokens_flex":9e-6,"cache_read_input_token_cost_above_272k_tokens":2.4e-7,"cache_creation_input_token_cost_above_272k_tokens":6e-6,"cache_read_input_token_cost_above_272k_tokens_flex":1.2e-7,"cache_creation_input_token_cost_above_272k_tokens_flex":3e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"azure/gpt-6.1-sol","object":"model","created":1790725775,"owned_by":"azure","model_name":"gpt-6.1-sol","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"input_cost_per_token_flex":1e-6,"output_cost_per_token_flex":5e-6,"cache_read_input_token_cost":1e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"cache_creation_input_token_cost":2.5e-6,"cache_read_input_token_cost_flex":5e-8,"cache_creation_input_token_cost_flex":1.25e-6,"input_cost_per_token_above_272k_tokens":4e-6,"output_cost_per_token_above_272k_tokens":0.000015,"input_cost_per_token_above_272k_tokens_flex":2e-6,"output_cost_per_token_above_272k_tokens_flex":7.5e-6,"cache_read_input_token_cost_above_272k_tokens":2e-7,"cache_creation_input_token_cost_above_272k_tokens":5e-6,"cache_read_input_token_cost_above_272k_tokens_flex":1e-7,"cache_creation_input_token_cost_above_272k_tokens_flex":2.5e-6},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"input_cost_per_token_flex":1e-6,"output_cost_per_token_flex":5e-6,"cache_read_input_token_cost":1e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"cache_creation_input_token_cost":2.5e-6,"cache_read_input_token_cost_flex":5e-8,"cache_creation_input_token_cost_flex":1.25e-6,"input_cost_per_token_above_272k_tokens":4e-6,"output_cost_per_token_above_272k_tokens":0.000015,"input_cost_per_token_above_272k_tokens_flex":2e-6,"output_cost_per_token_above_272k_tokens_flex":7.5e-6,"cache_read_input_token_cost_above_272k_tokens":2e-7,"cache_creation_input_token_cost_above_272k_tokens":5e-6,"cache_read_input_token_cost_above_272k_tokens_flex":1e-7,"cache_creation_input_token_cost_above_272k_tokens_flex":2.5e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"azure/gpt-6.1-sol@us","object":"model","created":1790725775,"owned_by":"azure","model_name":"gpt-6.1-sol","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2.2e-6,"output_cost_per_token":0.000011000000000000001,"input_cost_per_token_flex":1.1e-6,"output_cost_per_token_flex":5.500000000000001e-6,"cache_read_input_token_cost":1.1e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"cache_creation_input_token_cost":2.7500000000000004e-6,"cache_read_input_token_cost_flex":5.5e-8,"cache_creation_input_token_cost_flex":1.3750000000000002e-6,"input_cost_per_token_above_272k_tokens":4.4e-6,"output_cost_per_token_above_272k_tokens":0.0000165,"input_cost_per_token_above_272k_tokens_flex":2.2e-6,"output_cost_per_token_above_272k_tokens_flex":8.25e-6,"cache_read_input_token_cost_above_272k_tokens":2.2e-7,"cache_creation_input_token_cost_above_272k_tokens":5.500000000000001e-6,"cache_read_input_token_cost_above_272k_tokens_flex":1.1e-7,"cache_creation_input_token_cost_above_272k_tokens_flex":2.7500000000000004e-6},"list_pricing":{"input_cost_per_token":2.2e-6,"output_cost_per_token":0.000011000000000000001,"input_cost_per_token_flex":1.1e-6,"output_cost_per_token_flex":5.500000000000001e-6,"cache_read_input_token_cost":1.1e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"cache_creation_input_token_cost":2.7500000000000004e-6,"cache_read_input_token_cost_flex":5.5e-8,"cache_creation_input_token_cost_flex":1.3750000000000002e-6,"input_cost_per_token_above_272k_tokens":4.4e-6,"output_cost_per_token_above_272k_tokens":0.0000165,"input_cost_per_token_above_272k_tokens_flex":2.2e-6,"output_cost_per_token_above_272k_tokens_flex":8.25e-6,"cache_read_input_token_cost_above_272k_tokens":2.2e-7,"cache_creation_input_token_cost_above_272k_tokens":5.500000000000001e-6,"cache_read_input_token_cost_above_272k_tokens_flex":1.1e-7,"cache_creation_input_token_cost_above_272k_tokens_flex":2.7500000000000004e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"openai/gpt-6.1-sol","object":"model","created":1790702882,"owned_by":"openai","model_name":"gpt-6.1-sol","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series.","source":null,"capabilities":{"input_modalities":["file","image","text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"input_cost_per_token_flex":1e-6,"output_cost_per_token_flex":5e-6,"cache_read_input_token_cost":1e-7,"input_cost_per_token_batches":1e-6,"input_cost_per_token_priority":4e-6,"output_cost_per_token_batches":5e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"input_cost_per_token_ultrafast":0.000012,"output_cost_per_token_priority":0.00002,"cache_creation_input_token_cost":2.5e-6,"output_cost_per_token_ultrafast":0.00006,"cache_read_input_token_cost_flex":5e-8,"cache_read_input_token_cost_batches":5e-8,"cache_creation_input_token_cost_flex":1.25e-6,"cache_read_input_token_cost_priority":2e-7,"cache_read_input_token_cost_ultrafast":6e-7,"input_cost_per_token_above_272k_tokens":4e-6,"output_cost_per_token_above_272k_tokens":0.000015,"cache_creation_input_token_cost_priority":5e-6,"cache_creation_input_token_cost_ultrafast":0.000015,"cache_creation_input_token_cost_above_12hr":5e-6,"input_cost_per_token_above_272k_tokens_flex":2e-6,"output_cost_per_token_above_272k_tokens_flex":7.5e-6,"cache_read_input_token_cost_above_272k_tokens":2e-7,"cache_creation_input_token_cost_above_12hr_flex":2.5e-6,"input_cost_per_token_above_272k_tokens_priority":8e-6,"input_cost_per_token_above_272k_tokens_ultrafast":0.000024,"output_cost_per_token_above_272k_tokens_priority":0.00003,"cache_creation_input_token_cost_above_272k_tokens":5e-6,"output_cost_per_token_above_272k_tokens_ultrafast":0.00009,"cache_read_input_token_cost_above_272k_tokens_flex":1e-7,"cache_creation_input_token_cost_above_12hr_priority":0.00001,"cache_creation_input_token_cost_above_12hr_ultrafast":0.00003,"cache_creation_input_token_cost_above_272k_tokens_flex":2.5e-6,"cache_read_input_token_cost_above_272k_tokens_priority":4e-7,"cache_read_input_token_cost_above_272k_tokens_ultrafast":1.2e-6,"cache_creation_input_token_cost_above_272k_tokens_priority":0.00001,"cache_creation_input_token_cost_above_272k_tokens_ultrafast":0.00003,"cache_creation_input_token_cost_above_12hr_above_272k_tokens":0.00001,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_flex":5e-6,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_priority":0.00002,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_ultrafast":0.00006},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"input_cost_per_token_flex":1e-6,"output_cost_per_token_flex":5e-6,"cache_read_input_token_cost":1e-7,"input_cost_per_token_batches":1e-6,"input_cost_per_token_priority":4e-6,"output_cost_per_token_batches":5e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"input_cost_per_token_ultrafast":0.000012,"output_cost_per_token_priority":0.00002,"cache_creation_input_token_cost":2.5e-6,"output_cost_per_token_ultrafast":0.00006,"cache_read_input_token_cost_flex":5e-8,"cache_read_input_token_cost_batches":5e-8,"cache_creation_input_token_cost_flex":1.25e-6,"cache_read_input_token_cost_priority":2e-7,"cache_read_input_token_cost_ultrafast":6e-7,"input_cost_per_token_above_272k_tokens":4e-6,"output_cost_per_token_above_272k_tokens":0.000015,"cache_creation_input_token_cost_priority":5e-6,"cache_creation_input_token_cost_ultrafast":0.000015,"cache_creation_input_token_cost_above_12hr":5e-6,"input_cost_per_token_above_272k_tokens_flex":2e-6,"output_cost_per_token_above_272k_tokens_flex":7.5e-6,"cache_read_input_token_cost_above_272k_tokens":2e-7,"cache_creation_input_token_cost_above_12hr_flex":2.5e-6,"input_cost_per_token_above_272k_tokens_priority":8e-6,"input_cost_per_token_above_272k_tokens_ultrafast":0.000024,"output_cost_per_token_above_272k_tokens_priority":0.00003,"cache_creation_input_token_cost_above_272k_tokens":5e-6,"output_cost_per_token_above_272k_tokens_ultrafast":0.00009,"cache_read_input_token_cost_above_272k_tokens_flex":1e-7,"cache_creation_input_token_cost_above_12hr_priority":0.00001,"cache_creation_input_token_cost_above_12hr_ultrafast":0.00003,"cache_creation_input_token_cost_above_272k_tokens_flex":2.5e-6,"cache_read_input_token_cost_above_272k_tokens_priority":4e-7,"cache_read_input_token_cost_above_272k_tokens_ultrafast":1.2e-6,"cache_creation_input_token_cost_above_272k_tokens_priority":0.00001,"cache_creation_input_token_cost_above_272k_tokens_ultrafast":0.00003,"cache_creation_input_token_cost_above_12hr_above_272k_tokens":0.00001,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_flex":5e-6,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_priority":0.00002,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_ultrafast":0.00006},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":8},{"id":"gemini-nano-banana-2.1","object":"model","created":1791318261,"owned_by":"google","mode":"chat","context_length":65536,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text","image"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-6,"output_cost_per_token":7.5e-6,"output_cost_per_image_token":0.00003,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014}},"pricing_endpoint":"google/gemini-nano-banana-2.1","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"vertex/gemini-nano-banana-2.1","object":"model","created":1791318261,"owned_by":"vertex","model_name":"gemini-nano-banana-2.1","context_length":null,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"Nano Banana 2.1 (Gemini Nano Banana 2.1) is Google's image generation and editing model on the Flash tier, succeeding Nano Banana 2 and Nano Banana Pro.","source":"https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-6,"output_cost_per_token":7.5e-6,"output_cost_per_image_token":0.00003,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014}},"list_pricing":{"input_cost_per_token":1.5e-6,"output_cost_per_token":7.5e-6,"output_cost_per_image_token":0.00003,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014}},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"google/gemini-nano-banana-2.1","object":"model","created":1791300825,"owned_by":"google","model_name":"gemini-nano-banana-2.1","context_length":65536,"max_input_tokens":65536,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"Nano Banana 2.1 (Gemini Nano Banana 2.1) is Google's image generation and editing model on the Flash tier, succeeding Nano Banana 2 and Nano Banana Pro.","source":null,"capabilities":{"input_modalities":["image","text"],"output_modalities":["image","text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-6,"output_cost_per_token":7.5e-6,"output_cost_per_image_token":0.00003,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014}},"list_pricing":{"input_cost_per_token":1.5e-6,"output_cost_per_token":7.5e-6,"output_cost_per_image_token":0.00003,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014}},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":2},{"id":"mistral-large-4","object":"model","created":1791294122,"owned_by":"mistral","mode":"chat","context_length":1048576,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6.8e-7,"output_cost_per_token":2.09e-6,"cache_read_input_token_cost":7e-8},"pricing_endpoint":"mistral/mistral-large-4","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"mistral/mistral-large-4-0@eu","object":"model","created":1791294122,"owned_by":"mistral","model_name":"mistral-large-4-0","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":262144,"quantization":null,"retirement_date":null,"description":"Mistral Large 4 is a frontier multimodal (text and image input) model from Mistral AI built for reasoning, coding, and agentic workloads.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":7.7e-7,"output_cost_per_token":2.31e-6,"cache_read_input_token_cost":7.700000000000001e-8,"input_cost_per_token_batches":3.85e-7,"output_cost_per_token_batches":1.155e-6,"cache_read_input_token_cost_batches":3.850000000000001e-8},"list_pricing":{"input_cost_per_token":7.7e-7,"output_cost_per_token":2.31e-6,"cache_read_input_token_cost":7.700000000000001e-8,"input_cost_per_token_batches":3.85e-7,"output_cost_per_token_batches":1.155e-6,"cache_read_input_token_cost_batches":3.850000000000001e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"mistral/mistral-large-4-0","object":"model","created":1791294122,"owned_by":"mistral","model_name":"mistral-large-4-0","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":262144,"quantization":null,"retirement_date":null,"description":"Mistral Large 4 is a frontier multimodal (text and image input) model from Mistral AI built for reasoning, coding, and agentic workloads.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":7e-7,"output_cost_per_token":2.1e-6,"cache_read_input_token_cost":7e-8,"input_cost_per_token_batches":3.5e-7,"output_cost_per_token_batches":1.05e-6,"cache_read_input_token_cost_batches":3.5e-8},"list_pricing":{"input_cost_per_token":7e-7,"output_cost_per_token":2.1e-6,"cache_read_input_token_cost":7e-8,"input_cost_per_token_batches":3.5e-7,"output_cost_per_token_batches":1.05e-6,"cache_read_input_token_cost_batches":3.5e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"mistral/mistral-large-4@eu","object":"model","created":1791244800,"owned_by":"mistral","model_name":"mistral-large-4","context_length":524288,"max_input_tokens":524288,"max_output_tokens":209715,"quantization":null,"retirement_date":null,"description":"Mistral Large 4 (public preview): 1.05T-parameter open-weight multimodal MoE, 49B active.","source":"https://docs.mistral.ai/models/mistral-large-4-0","capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":7.48e-7,"output_cost_per_token":2.299e-6,"cache_read_input_token_cost":7.700000000000001e-8},"list_pricing":{"input_cost_per_token":7.48e-7,"output_cost_per_token":2.299e-6,"cache_read_input_token_cost":7.700000000000001e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"mistral/mistral-large-4","object":"model","created":1791244800,"owned_by":"mistral","model_name":"mistral-large-4","context_length":524288,"max_input_tokens":524288,"max_output_tokens":209715,"quantization":null,"retirement_date":null,"description":"Mistral Large 4 (public preview): 1.05T-parameter open-weight multimodal MoE, 49B active.","source":"https://docs.mistral.ai/models/mistral-large-4-0","capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6.8e-7,"output_cost_per_token":2.09e-6,"cache_read_input_token_cost":7e-8},"list_pricing":{"input_cost_per_token":6.8e-7,"output_cost_per_token":2.09e-6,"cache_read_input_token_cost":7e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":4},{"id":"gpt-oss-20b","object":"model","created":1791004468,"owned_by":"openai","mode":"chat","context_length":131072,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":9e-9,"output_cost_per_token":4.5e-8,"input_cost_per_image_token":0.0,"cache_read_input_token_cost":4.5e-9,"cache_creation_input_token_cost":0.0},"pricing_endpoint":"greenference/gpt-oss-20b","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"greenference/gpt-oss-20b","object":"model","created":1791004468,"owned_by":"greenference","model_name":"gpt-oss-20b","context_length":131072,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":9e-9,"output_cost_per_token":4.5e-8,"input_cost_per_image_token":0.0,"cache_read_input_token_cost":4.5e-9,"cache_creation_input_token_cost":0.0},"list_pricing":{"input_cost_per_token":9e-9,"output_cost_per_token":4.5e-8,"input_cost_per_image_token":0.0,"cache_read_input_token_cost":4.5e-9,"cache_creation_input_token_cost":0.0},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"flexai/gpt-oss-20b@eu","object":"model","created":1786610410,"owned_by":"flexai","model_name":"gpt-oss-20b","context_length":131072,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.8e-8,"output_cost_per_token":9e-8,"cache_read_input_token_cost":2.7e-9},"list_pricing":{"input_cost_per_token":1.8e-8,"output_cost_per_token":9e-8,"cache_read_input_token_cost":2.7e-9},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"flexai/gpt-oss-20b","object":"model","created":1786610410,"owned_by":"flexai","model_name":"gpt-oss-20b","context_length":131072,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.8e-8,"output_cost_per_token":9e-8,"cache_read_input_token_cost":2.7e-9},"list_pricing":{"input_cost_per_token":1.8e-8,"output_cost_per_token":9e-8,"cache_read_input_token_cost":2.7e-9},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"cloudflare/@cf/openai/gpt-oss-20b","object":"model","created":1782119040,"owned_by":"cloudflare","model_name":"@cf/openai/gpt-oss-20b","context_length":128000,"max_input_tokens":128000,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.0000000000000002e-7,"output_cost_per_token":3e-7},"list_pricing":{"input_cost_per_token":2.0000000000000002e-7,"output_cost_per_token":3e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"databricks/databricks-gpt-oss-20b@eu","object":"model","created":1769507058,"owned_by":"databricks","model_name":"databricks-gpt-oss-20b","context_length":131072,"max_input_tokens":131072,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"GPT OSS 20B is a state-of-the-art, lightweight reasoning model built and trained by OpenAI. This model also has a 128K token context window and excels at real-time copilots and batch inference tasks.","source":"https://www.databricks.com/product/pricing/foundation-model-serving","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":7e-8,"output_cost_per_token":3e-7,"input_dbu_cost_per_token":1e-6,"output_dbu_cost_per_token":4.285999999999999e-6,"cache_read_input_token_cost":7e-9,"cache_creation_input_token_cost":7e-8},"list_pricing":{"input_cost_per_token":7e-8,"output_cost_per_token":3e-7,"input_dbu_cost_per_token":1e-6,"output_dbu_cost_per_token":4.285999999999999e-6,"cache_read_input_token_cost":7e-9,"cache_creation_input_token_cost":7e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"databricks/databricks-gpt-oss-20b","object":"model","created":1769507058,"owned_by":"databricks","model_name":"databricks-gpt-oss-20b","context_length":131072,"max_input_tokens":131072,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"GPT OSS 20B is a state-of-the-art, lightweight reasoning model built and trained by OpenAI. This model also has a 128K token context window and excels at real-time copilots and batch inference tasks.","source":"https://www.databricks.com/product/pricing/foundation-model-serving","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":7e-8,"output_cost_per_token":3e-7,"input_dbu_cost_per_token":1e-6,"output_dbu_cost_per_token":4.285999999999999e-6,"cache_read_input_token_cost":7e-9,"cache_creation_input_token_cost":7e-8},"list_pricing":{"input_cost_per_token":7e-8,"output_cost_per_token":3e-7,"input_dbu_cost_per_token":1e-6,"output_dbu_cost_per_token":4.285999999999999e-6,"cache_read_input_token_cost":7e-9,"cache_creation_input_token_cost":7e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"ovhcloud/gpt-oss-20b","object":"model","created":1769507058,"owned_by":"ovhcloud","model_name":"gpt-oss-20b","context_length":131072,"max_input_tokens":131000,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license.","source":"https://endpoints.ai.cloud.ovh.net/models/gpt-oss-20b","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-8,"output_cost_per_token":1.8e-7},"list_pricing":{"input_cost_per_token":5e-8,"output_cost_per_token":1.8e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/openai.gpt-oss-20b-1:0","object":"model","created":1767692616,"owned_by":"amazon","model_name":"openai.gpt-oss-20b-1:0","context_length":128000,"max_input_tokens":128000,"max_output_tokens":16384,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":7e-8,"output_cost_per_token":3e-7,"input_cost_per_token_flex":3.5e-8,"output_cost_per_token_flex":1.5e-7,"input_cost_per_token_priority":1.225e-7,"output_cost_per_token_priority":5.25e-7},"list_pricing":{"input_cost_per_token":7e-8,"output_cost_per_token":3e-7,"input_cost_per_token_flex":3.5e-8,"output_cost_per_token_flex":1.5e-7,"input_cost_per_token_priority":1.225e-7,"output_cost_per_token_priority":5.25e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/openai.gpt-oss-20b-1:0@us","object":"model","created":1767692616,"owned_by":"amazon","model_name":"openai.gpt-oss-20b-1:0","context_length":128000,"max_input_tokens":128000,"max_output_tokens":16384,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":7e-8,"output_cost_per_token":3e-7,"input_cost_per_token_flex":3.5e-8,"output_cost_per_token_flex":1.5e-7,"input_cost_per_token_priority":1.225e-7,"output_cost_per_token_priority":5.25e-7},"list_pricing":{"input_cost_per_token":7e-8,"output_cost_per_token":3e-7,"input_cost_per_token_flex":3.5e-8,"output_cost_per_token_flex":1.5e-7,"input_cost_per_token_priority":1.225e-7,"output_cost_per_token_priority":5.25e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"deepinfra/openai/gpt-oss-20b","object":"model","created":1754414229,"owned_by":"deepinfra","model_name":"openai/gpt-oss-20b","context_length":131072,"max_input_tokens":131072,"max_output_tokens":null,"quantization":"bf16","retirement_date":null,"description":"gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.0000000000000004e-8,"output_cost_per_token":1.4e-7,"cache_read_input_token_cost":1.5000000000000002e-8},"list_pricing":{"input_cost_per_token":3.0000000000000004e-8,"output_cost_per_token":1.4e-7,"cache_read_input_token_cost":1.5000000000000002e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"groq/openai/gpt-oss-20b","object":"model","created":1754414229,"owned_by":"groq","model_name":"openai/gpt-oss-20b","context_length":131072,"max_input_tokens":131072,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":7.5e-8,"output_cost_per_token":3e-7,"cache_read_input_token_cost":3.75e-8,"search_context_cost_per_query":{"search_context_size_low":0.005,"search_context_size_high":0.005,"search_context_size_medium":0.005}},"list_pricing":{"input_cost_per_token":7.5e-8,"output_cost_per_token":3e-7,"cache_read_input_token_cost":3.75e-8,"search_context_cost_per_query":{"search_context_size_low":0.005,"search_context_size_high":0.005,"search_context_size_medium":0.005}},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":11},{"id":"ling-3.1-flash","object":"model","created":1790950024,"owned_by":"","mode":"chat","context_length":262144,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":9.000000000000001e-7,"cache_read_input_token_cost":6e-8},"pricing_endpoint":"deepinfra/inclusionAI/Ling-3.1-flash","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"deepinfra/inclusionAI/Ling-3.1-flash","object":"model","created":1790950024,"owned_by":"deepinfra","model_name":"inclusionAI/Ling-3.1-flash","context_length":262144,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"Ling 3.1 Flash is a hybrid reasoning mixture-of-experts model from inclusionAI, with 25B active parameters out of 560B total.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":9.000000000000001e-7,"cache_read_input_token_cost":6e-8},"list_pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":9.000000000000001e-7,"cache_read_input_token_cost":6e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"glm-4.7-flash","object":"model","created":1790948154,"owned_by":"zai","mode":"chat","context_length":203000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":6e-8,"output_cost_per_token":4e-7,"cache_read_input_token_cost":1e-8},"pricing_endpoint":"deepinfra/zai-org/GLM-4.7-Flash","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"greenference/glm-4.7-flash","object":"model","created":1790948154,"owned_by":"greenference","model_name":"glm-4.7-flash","context_length":131072,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"As a 30B-class SOTA model, GLM-4.7-Flash offers a new option that balances performance and efficiency.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":7e-8,"output_cost_per_token":4.0756e-7,"input_cost_per_image_token":0.0,"cache_read_input_token_cost":1.4331e-8,"cache_creation_input_token_cost":0.0},"list_pricing":{"input_cost_per_token":7e-8,"output_cost_per_token":4.0756e-7,"input_cost_per_image_token":0.0,"cache_read_input_token_cost":1.4331e-8,"cache_creation_input_token_cost":0.0},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"amazon/zai.glm-4.7-flash","object":"model","created":1772697599,"owned_by":"amazon","model_name":"zai.glm-4.7-flash","context_length":203000,"max_input_tokens":203000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":null,"source":"https://aws.amazon.com/bedrock/pricing/","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":7e-8,"output_cost_per_token":4e-7,"input_cost_per_token_flex":3.5e-8,"output_cost_per_token_flex":2e-7,"input_cost_per_token_priority":1.225e-7,"output_cost_per_token_priority":7e-7},"list_pricing":{"input_cost_per_token":7e-8,"output_cost_per_token":4e-7,"input_cost_per_token_flex":3.5e-8,"output_cost_per_token_flex":2e-7,"input_cost_per_token_priority":1.225e-7,"output_cost_per_token_priority":7e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/zai.glm-4.7-flash@us","object":"model","created":1772697599,"owned_by":"amazon","model_name":"zai.glm-4.7-flash","context_length":203000,"max_input_tokens":203000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":null,"source":"https://aws.amazon.com/bedrock/pricing/","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":7e-8,"output_cost_per_token":4e-7,"input_cost_per_token_flex":3.5e-8,"output_cost_per_token_flex":2e-7,"input_cost_per_token_priority":1.225e-7,"output_cost_per_token_priority":7e-7},"list_pricing":{"input_cost_per_token":7e-8,"output_cost_per_token":4e-7,"input_cost_per_token_flex":3.5e-8,"output_cost_per_token_flex":2e-7,"input_cost_per_token_priority":1.225e-7,"output_cost_per_token_priority":7e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"cloudflare/@cf/zai-org/glm-4.7-flash","object":"model","created":1768833913,"owned_by":"cloudflare","model_name":"@cf/zai-org/glm-4.7-flash","context_length":131072,"max_input_tokens":131072,"max_output_tokens":null,"quantization":null,"retirement_date":"2026-09-10","description":"As a 30B-class SOTA model, GLM-4.7-Flash offers a new option that balances performance and efficiency.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6.049999999999999e-8,"output_cost_per_token":4.0000000000000003e-7},"list_pricing":{"input_cost_per_token":6.049999999999999e-8,"output_cost_per_token":4.0000000000000003e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"deepinfra/zai-org/GLM-4.7-Flash","object":"model","created":1768833913,"owned_by":"deepinfra","model_name":"zai-org/GLM-4.7-Flash","context_length":202752,"max_input_tokens":null,"max_output_tokens":16384,"quantization":null,"retirement_date":"2026-09-10","description":"As a 30B-class SOTA model, GLM-4.7-Flash offers a new option that balances performance and efficiency. It is further optimized for agentic coding use cases, strengthening coding capabilities, long-horizon task planning,...","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6e-8,"output_cost_per_token":4e-7,"cache_read_input_token_cost":1e-8},"list_pricing":{"input_cost_per_token":6e-8,"output_cost_per_token":4e-7,"cache_read_input_token_cost":1e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":5},{"id":"qwen3-14b","object":"model","created":1790948154,"owned_by":"qwen","mode":"chat","context_length":41000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":7.6e-8,"output_cost_per_token":2.28e-7,"input_cost_per_image_token":0.0,"cache_read_input_token_cost":3.8e-8,"cache_creation_input_token_cost":0.0},"pricing_endpoint":"greenference/qwen3-14b","regions":[{"code":"eu","name":"Europe"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"greenference/qwen3-14b","object":"model","created":1790948154,"owned_by":"greenference","model_name":"qwen3-14b","context_length":41000,"max_input_tokens":null,"max_output_tokens":32768,"quantization":null,"retirement_date":null,"description":"Qwen3-14B is a dense 14.8B parameter causal language model from the Qwen3 series, designed for both complex reasoning and efficient dialogue.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":7.6e-8,"output_cost_per_token":2.28e-7,"input_cost_per_image_token":0.0,"cache_read_input_token_cost":3.8e-8,"cache_creation_input_token_cost":0.0},"list_pricing":{"input_cost_per_token":7.6e-8,"output_cost_per_token":2.28e-7,"input_cost_per_image_token":0.0,"cache_read_input_token_cost":3.8e-8,"cache_creation_input_token_cost":0.0},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"deepinfra/Qwen/Qwen3-14B","object":"model","created":1745876478,"owned_by":"deepinfra","model_name":"Qwen/Qwen3-14B","context_length":40960,"max_input_tokens":40960,"max_output_tokens":16384,"quantization":"fp8","retirement_date":null,"description":"Qwen3-14B is a dense 14.8B parameter causal language model from the Qwen3 series, designed for both complex reasoning and efficient dialogue.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.2000000000000002e-7,"output_cost_per_token":2.4000000000000003e-7},"list_pricing":{"input_cost_per_token":1.2000000000000002e-7,"output_cost_per_token":2.4000000000000003e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"qwen3-30b-a3b","object":"model","created":1790948154,"owned_by":"qwen","mode":"chat","context_length":41000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":9.5e-8,"output_cost_per_token":2.85e-7,"input_cost_per_image_token":0.0,"cache_read_input_token_cost":4.75e-8,"cache_creation_input_token_cost":0.0},"pricing_endpoint":"greenference/qwen3-30b-a3b","regions":[{"code":"eu","name":"Europe"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"greenference/qwen3-30b-a3b","object":"model","created":1790948154,"owned_by":"greenference","model_name":"qwen3-30b-a3b","context_length":41000,"max_input_tokens":null,"max_output_tokens":32768,"quantization":null,"retirement_date":null,"description":"Qwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to excel in reasoning, multilingual support, and advanced agent tasks.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":9.5e-8,"output_cost_per_token":2.85e-7,"input_cost_per_image_token":0.0,"cache_read_input_token_cost":4.75e-8,"cache_creation_input_token_cost":0.0},"list_pricing":{"input_cost_per_token":9.5e-8,"output_cost_per_token":2.85e-7,"input_cost_per_image_token":0.0,"cache_read_input_token_cost":4.75e-8,"cache_creation_input_token_cost":0.0},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"deepinfra/Qwen/Qwen3-30B-A3B","object":"model","created":1745878604,"owned_by":"deepinfra","model_name":"Qwen/Qwen3-30B-A3B","context_length":40960,"max_input_tokens":40960,"max_output_tokens":16384,"quantization":"fp8","retirement_date":"2026-10-09","description":"Qwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to excel in reasoning, multilingual support, and advanced agent tasks.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.2000000000000002e-7,"output_cost_per_token":5e-7},"list_pricing":{"input_cost_per_token":1.2000000000000002e-7,"output_cost_per_token":5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"qwen3-32b","object":"model","created":1790948154,"owned_by":"qwen","mode":"chat","context_length":41000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":8e-8,"output_cost_per_token":2.8e-7},"pricing_endpoint":"deepinfra/Qwen/Qwen3-32B","regions":[{"code":"eu","name":"Europe"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"greenference/qwen3-32b","object":"model","created":1790948154,"owned_by":"greenference","model_name":"qwen3-32b","context_length":41000,"max_input_tokens":null,"max_output_tokens":32768,"quantization":null,"retirement_date":null,"description":"Qwen3-32B is a dense 32.8B parameter causal language model from the Qwen3 series, optimized for both complex reasoning and efficient dialogue.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":9.5e-8,"output_cost_per_token":2.85e-7,"input_cost_per_image_token":0.0,"cache_read_input_token_cost":4.75e-8,"cache_creation_input_token_cost":0.0},"list_pricing":{"input_cost_per_token":9.5e-8,"output_cost_per_token":2.85e-7,"input_cost_per_image_token":0.0,"cache_read_input_token_cost":4.75e-8,"cache_creation_input_token_cost":0.0},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"amazon/qwen.qwen3-32b-v1:0","object":"model","created":1767692616,"owned_by":"amazon","model_name":"qwen.qwen3-32b-v1:0","context_length":32768,"max_input_tokens":32768,"max_output_tokens":8192,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"input_cost_per_token_flex":7.5e-8,"output_cost_per_token_flex":3e-7,"input_cost_per_token_priority":2.625e-7,"output_cost_per_token_priority":1.05e-6},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"input_cost_per_token_flex":7.5e-8,"output_cost_per_token_flex":3e-7,"input_cost_per_token_priority":2.625e-7,"output_cost_per_token_priority":1.05e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/qwen.qwen3-32b-v1:0@us","object":"model","created":1767692616,"owned_by":"amazon","model_name":"qwen.qwen3-32b-v1:0","context_length":32768,"max_input_tokens":32768,"max_output_tokens":8192,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"input_cost_per_token_flex":7.5e-8,"output_cost_per_token_flex":3e-7,"input_cost_per_token_priority":2.625e-7,"output_cost_per_token_priority":1.05e-6},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"input_cost_per_token_flex":7.5e-8,"output_cost_per_token_flex":3e-7,"input_cost_per_token_priority":2.625e-7,"output_cost_per_token_priority":1.05e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"deepinfra/Qwen/Qwen3-32B","object":"model","created":1745875945,"owned_by":"deepinfra","model_name":"Qwen/Qwen3-32B","context_length":40960,"max_input_tokens":40960,"max_output_tokens":16384,"quantization":"fp8","retirement_date":null,"description":"Qwen3-32B is a dense 32.8B parameter causal language model from the Qwen3 series, optimized for both complex reasoning and efficient dialogue.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":8e-8,"output_cost_per_token":2.8e-7},"list_pricing":{"input_cost_per_token":8e-8,"output_cost_per_token":2.8e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":4},{"id":"qwen3-8b","object":"model","created":1790948154,"owned_by":"qwen","mode":"chat","context_length":41000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":8e-8,"output_cost_per_token":2.5e-7,"input_cost_per_image_token":0.0,"cache_read_input_token_cost":4e-8,"cache_creation_input_token_cost":0.0},"pricing_endpoint":"greenference/qwen3-8b","regions":[{"code":"eu","name":"Europe"}],"alias_of":null,"endpoints":[{"id":"greenference/qwen3-8b","object":"model","created":1790948154,"owned_by":"greenference","model_name":"qwen3-8b","context_length":41000,"max_input_tokens":null,"max_output_tokens":32768,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":8e-8,"output_cost_per_token":2.5e-7,"input_cost_per_image_token":0.0,"cache_read_input_token_cost":4e-8,"cache_creation_input_token_cost":0.0},"list_pricing":{"input_cost_per_token":8e-8,"output_cost_per_token":2.5e-7,"input_cost_per_image_token":0.0,"cache_read_input_token_cost":4e-8,"cache_creation_input_token_cost":0.0},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":1},{"id":"qwen3.5-9b","object":"model","created":1790948154,"owned_by":"qwen","mode":"chat","context_length":262144,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":4e-8,"output_cost_per_token":6.5e-8,"input_cost_per_image_token":0.0,"cache_read_input_token_cost":2e-8,"cache_creation_input_token_cost":0.0},"pricing_endpoint":"greenference/qwen3.5-9b","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"greenference/qwen3.5-9b","object":"model","created":1790948154,"owned_by":"greenference","model_name":"qwen3.5-9b","context_length":262144,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"Qwen3.5-9B is a multimodal foundation model from the Qwen3.5 family, designed to deliver strong reasoning, coding, and visual understanding in an efficient 9B-parameter architecture.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4e-8,"output_cost_per_token":6.5e-8,"input_cost_per_image_token":0.0,"cache_read_input_token_cost":2e-8,"cache_creation_input_token_cost":0.0},"list_pricing":{"input_cost_per_token":4e-8,"output_cost_per_token":6.5e-8,"input_cost_per_image_token":0.0,"cache_read_input_token_cost":2e-8,"cache_creation_input_token_cost":0.0},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"tensorx/qwen/qwen3.5-9b","object":"model","created":1787003349,"owned_by":"tensorx","model_name":"qwen/qwen3.5-9b","context_length":262144,"max_input_tokens":262144,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"Served by TensorX at fp8 quantization.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":2e-7,"cache_read_input_token_cost":3.75e-8},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":2e-7,"cache_read_input_token_cost":3.75e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"ionos/Qwen/Qwen3.5-9B","object":"model","created":1786647205,"owned_by":"ionos","model_name":"Qwen/Qwen3.5-9B","context_length":262144,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"Qwen3.5-9B is a multimodal foundation model from the Qwen3.5 family, designed to deliver strong reasoning, coding, and visual understanding in an efficient 9B-parameter architecture.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.1014004306475685e-7,"output_cost_per_token":1.6521006459713525e-7},"list_pricing":{"input_cost_per_token":1.1014004306475685e-7,"output_cost_per_token":1.6521006459713525e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"flexai/Qwen3.5-9B@eu","object":"model","created":1786610410,"owned_by":"flexai","model_name":"Qwen3.5-9B","context_length":262144,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"Qwen3.5-9B is a multimodal foundation model from the Qwen3.5 family, designed to deliver strong reasoning, coding, and visual understanding in an efficient 9B-parameter architecture.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":1.5e-7,"cache_read_input_token_cost":1.5e-8},"list_pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":1.5e-7,"cache_read_input_token_cost":1.5e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"flexai/Qwen3.5-9B","object":"model","created":1786610410,"owned_by":"flexai","model_name":"Qwen3.5-9B","context_length":262144,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"Qwen3.5-9B is a multimodal foundation model from the Qwen3.5 family, designed to deliver strong reasoning, coding, and visual understanding in an efficient 9B-parameter architecture.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":1.5e-7,"cache_read_input_token_cost":1.5e-8},"list_pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":1.5e-7,"cache_read_input_token_cost":1.5e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"ovhcloud/Qwen3.5-9B","object":"model","created":1780673223,"owned_by":"ovhcloud","model_name":"Qwen3.5-9B","context_length":262144,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"Qwen3.5-9B is a multimodal foundation model from the Qwen3.5 family, designed to deliver strong reasoning, coding, and visual understanding in an efficient 9B-parameter architecture.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.2e-7,"output_cost_per_token":1.8e-7},"list_pricing":{"input_cost_per_token":1.2e-7,"output_cost_per_token":1.8e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"deepinfra/Qwen/Qwen3.5-9B","object":"model","created":1773152396,"owned_by":"deepinfra","model_name":"Qwen/Qwen3.5-9B","context_length":262144,"max_input_tokens":262144,"max_output_tokens":81920,"quantization":"bf16","retirement_date":"2026-10-21","description":"Qwen3.5-9B is a multimodal foundation model from the Qwen3.5 family, designed to deliver strong reasoning, coding, and visual understanding in an efficient 9B-parameter architecture.","source":null,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.0000000000000001e-7,"output_cost_per_token":1.5e-7},"list_pricing":{"input_cost_per_token":1.0000000000000001e-7,"output_cost_per_token":1.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"together_ai/Qwen/Qwen3.5-9B","object":"model","created":1773152396,"owned_by":"together_ai","model_name":"Qwen/Qwen3.5-9B","context_length":262144,"max_input_tokens":262144,"max_output_tokens":null,"quantization":null,"retirement_date":"2026-10-21","description":"Qwen3.5-9B is a multimodal foundation model from the Qwen3.5 family, designed to deliver strong reasoning, coding, and visual understanding in an efficient 9B-parameter architecture.","source":null,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.7000000000000001e-7,"output_cost_per_token":2.5e-7},"list_pricing":{"input_cost_per_token":1.7000000000000001e-7,"output_cost_per_token":2.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":8},{"id":"qwen3.6-27b","object":"model","created":1790948154,"owned_by":"qwen","mode":"chat","context_length":262144,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":1.35e-6,"input_cost_per_image_token":0.0,"cache_read_input_token_cost":7.5e-8,"cache_creation_input_token_cost":0.0},"pricing_endpoint":"greenference/qwen3.6-27b","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"greenference/qwen3.6-27b","object":"model","created":1790948154,"owned_by":"greenference","model_name":"qwen3.6-27b","context_length":262144,"max_input_tokens":null,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"Qwen3.6 27B is a dense 27-billion-parameter language model from the Qwen Team at Alibaba, released in April 2026.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":1.35e-6,"input_cost_per_image_token":0.0,"cache_read_input_token_cost":7.5e-8,"cache_creation_input_token_cost":0.0},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":1.35e-6,"input_cost_per_image_token":0.0,"cache_read_input_token_cost":7.5e-8,"cache_creation_input_token_cost":0.0},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"flexai/Qwen3.6-27B-FP8","object":"model","created":1786610410,"owned_by":"flexai","model_name":"Qwen3.6-27B-FP8","context_length":262144,"max_input_tokens":null,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"Qwen3.6 27B is a dense 27-billion-parameter language model from the Qwen Team at Alibaba, released in April 2026.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.5e-7,"output_cost_per_token":2e-6,"cache_read_input_token_cost":2.5e-8},"list_pricing":{"input_cost_per_token":2.5e-7,"output_cost_per_token":2e-6,"cache_read_input_token_cost":2.5e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"groq/qwen/qwen3.6-27b","object":"model","created":1782119040,"owned_by":"groq","model_name":"qwen/qwen3.6-27b","context_length":131072,"max_input_tokens":null,"max_output_tokens":16384,"quantization":null,"retirement_date":null,"description":"Qwen3.6 27B is a dense 27-billion-parameter language model from the Qwen Team at Alibaba, released in April 2026.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6e-7,"output_cost_per_token":3e-6,"cache_read_input_token_cost":3e-7},"list_pricing":{"input_cost_per_token":6e-7,"output_cost_per_token":3e-6,"cache_read_input_token_cost":3e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":null,"alias_of":null},{"id":"ovhcloud/Qwen3.6-27B","object":"model","created":1780673223,"owned_by":"ovhcloud","model_name":"Qwen3.6-27B","context_length":262144,"max_input_tokens":null,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"Qwen3.6 27B is a dense 27-billion-parameter language model from the Qwen Team at Alibaba, released in April 2026.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4.7e-7,"output_cost_per_token":3.19e-6},"list_pricing":{"input_cost_per_token":4.7e-7,"output_cost_per_token":3.19e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"deepinfra/Qwen/Qwen3.6-27B","object":"model","created":1777255064,"owned_by":"deepinfra","model_name":"Qwen/Qwen3.6-27B","context_length":262144,"max_input_tokens":262144,"max_output_tokens":81920,"quantization":"fp8","retirement_date":null,"description":"Qwen3.6 27B is a dense 27-billion-parameter language model from the Qwen Team at Alibaba, released in April 2026.","source":null,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.2e-7,"output_cost_per_token":3.2000000000000003e-6},"list_pricing":{"input_cost_per_token":3.2e-7,"output_cost_per_token":3.2000000000000003e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"qwen/qwen3.6-27b","object":"model","created":1777255064,"owned_by":"qwen","model_name":"qwen3.6-27b","context_length":262144,"max_input_tokens":260096,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"The Qwen3.6 27B native vision-language dense model builds upon the 3.5-27B version, with key improvements in agentic coding capabilities and enhanced STEM reasoning and inference skills. In the vision modality, it demonstrates significant advances in spatial intelligence, object localization, and detection, while video understanding, document OCR, and visual agent capabilities continue to improve steadily.","source":null,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.8999999999999997e-7,"output_cost_per_token":2.34e-6},"list_pricing":{"input_cost_per_token":6e-7,"output_cost_per_token":3.6000000000000003e-6},"discount":0.35,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":6},{"id":"claude-sonnet-5.5","object":"model","created":1790917997,"owned_by":"anthropic","mode":"chat","context_length":1000000,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"provider_specific_entry":{"us":1.1},"cache_read_input_token_cost":1e-7,"input_cost_per_token_batches":1e-6,"output_cost_per_token_batches":5e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":2.5e-6,"cache_read_input_token_cost_batches":5e-8,"cache_creation_input_token_cost_above_1hr":4e-6},"pricing_endpoint":"anthropic/claude-sonnet-5-5","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"databricks/databricks-claude-sonnet-5-5@eu","object":"model","created":1790917997,"owned_by":"databricks","model_name":"databricks-claude-sonnet-5-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Sonnet 5.5 is Anthropic's model for building features, fixing bugs, and creating documents. It supports a 1 million token context window and up to 128,000 output tokens. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"input_dbu_cost_per_token":0.000028571,"output_dbu_cost_per_token":0.00014286,"cache_read_input_token_cost":2e-7,"cache_creation_input_token_cost":2.5e-6,"cache_creation_input_token_cost_above_1hr":4e-6},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"input_dbu_cost_per_token":0.000028571,"output_dbu_cost_per_token":0.00014286,"cache_read_input_token_cost":2e-7,"cache_creation_input_token_cost":2.5e-6,"cache_creation_input_token_cost_above_1hr":4e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"databricks/databricks-claude-sonnet-5-5","object":"model","created":1790917997,"owned_by":"databricks","model_name":"databricks-claude-sonnet-5-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Sonnet 5.5 is Anthropic's model for building features, fixing bugs, and creating documents. It supports a 1 million token context window and up to 128,000 output tokens. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"input_dbu_cost_per_token":0.000028571,"output_dbu_cost_per_token":0.00014286,"cache_read_input_token_cost":2e-7,"cache_creation_input_token_cost":2.5e-6,"cache_creation_input_token_cost_above_1hr":4e-6},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"input_dbu_cost_per_token":0.000028571,"output_dbu_cost_per_token":0.00014286,"cache_read_input_token_cost":2e-7,"cache_creation_input_token_cost":2.5e-6,"cache_creation_input_token_cost_above_1hr":4e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"deepinfra/anthropic/claude-sonnet-5-5","object":"model","created":1790780828,"owned_by":"deepinfra","model_name":"anthropic/claude-sonnet-5-5","context_length":1000000,"max_input_tokens":null,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null},{"id":"amazon/anthropic.claude-sonnet-5-5@eu","object":"model","created":1790618686,"owned_by":"amazon","model_name":"anthropic.claude-sonnet-5-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.2e-6,"output_cost_per_token":0.000011000000000000001,"cache_read_input_token_cost":1.1e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":2.7500000000000004e-6,"cache_creation_input_token_cost_above_1hr":4.4e-6},"list_pricing":{"input_cost_per_token":2.2e-6,"output_cost_per_token":0.000011000000000000001,"cache_read_input_token_cost":1.1e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":2.7500000000000004e-6,"cache_creation_input_token_cost_above_1hr":4.4e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/anthropic.claude-sonnet-5-5","object":"model","created":1790618686,"owned_by":"amazon","model_name":"anthropic.claude-sonnet-5-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"cache_read_input_token_cost":1e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":2.5e-6,"cache_creation_input_token_cost_above_1hr":4e-6},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"cache_read_input_token_cost":1e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":2.5e-6,"cache_creation_input_token_cost_above_1hr":4e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/anthropic.claude-sonnet-5-5@us","object":"model","created":1790618686,"owned_by":"amazon","model_name":"anthropic.claude-sonnet-5-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.2e-6,"output_cost_per_token":0.000011000000000000001,"cache_read_input_token_cost":1.1e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":2.7500000000000004e-6,"cache_creation_input_token_cost_above_1hr":4.4e-6},"list_pricing":{"input_cost_per_token":2.2e-6,"output_cost_per_token":0.000011000000000000001,"cache_read_input_token_cost":1.1e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":2.7500000000000004e-6,"cache_creation_input_token_cost_above_1hr":4.4e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"anthropic/claude-sonnet-5-5","object":"model","created":1790618686,"owned_by":"anthropic","model_name":"claude-sonnet-5-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"provider_specific_entry":{"us":1.1},"cache_read_input_token_cost":1e-7,"input_cost_per_token_batches":1e-6,"output_cost_per_token_batches":5e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":2.5e-6,"cache_read_input_token_cost_batches":5e-8,"cache_creation_input_token_cost_above_1hr":4e-6},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"provider_specific_entry":{"us":1.1},"cache_read_input_token_cost":1e-7,"input_cost_per_token_batches":1e-6,"output_cost_per_token_batches":5e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":2.5e-6,"cache_read_input_token_cost_batches":5e-8,"cache_creation_input_token_cost_above_1hr":4e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null},{"id":"vertex/claude-sonnet-5-5@eu","object":"model","created":1790618686,"owned_by":"vertex","model_name":"claude-sonnet-5-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.2e-6,"output_cost_per_token":0.000011000000000000001,"cache_read_input_token_cost":1.1e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":2.7500000000000004e-6,"cache_creation_input_token_cost_above_1hr":4.4e-6},"list_pricing":{"input_cost_per_token":2.2e-6,"output_cost_per_token":0.000011000000000000001,"cache_read_input_token_cost":1.1e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":2.7500000000000004e-6,"cache_creation_input_token_cost_above_1hr":4.4e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"vertex/claude-sonnet-5-5","object":"model","created":1790618686,"owned_by":"vertex","model_name":"claude-sonnet-5-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"cache_read_input_token_cost":1e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":2.5e-6,"cache_creation_input_token_cost_above_1hr":4e-6},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"cache_read_input_token_cost":1e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":2.5e-6,"cache_creation_input_token_cost_above_1hr":4e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"vertex/claude-sonnet-5-5@us","object":"model","created":1790618686,"owned_by":"vertex","model_name":"claude-sonnet-5-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.2e-6,"output_cost_per_token":0.000011000000000000001,"cache_read_input_token_cost":1.1e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":2.7500000000000004e-6,"cache_creation_input_token_cost_above_1hr":4.4e-6},"list_pricing":{"input_cost_per_token":2.2e-6,"output_cost_per_token":0.000011000000000000001,"cache_read_input_token_cost":1.1e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":2.7500000000000004e-6,"cache_creation_input_token_cost_above_1hr":4.4e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":10},{"id":"~claude-sonnet-latest","object":"model","created":1790917997,"owned_by":"anthropic","mode":"chat","context_length":1000000,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"provider_specific_entry":{"us":1.1},"cache_read_input_token_cost":1e-7,"input_cost_per_token_batches":1e-6,"output_cost_per_token_batches":5e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":2.5e-6,"cache_read_input_token_cost_batches":5e-8,"cache_creation_input_token_cost_above_1hr":4e-6},"pricing_endpoint":"anthropic/claude-sonnet-5-5","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":"claude-sonnet-5.5","endpoints":[{"id":"databricks/databricks-claude-sonnet-5-5@eu","object":"model","created":1790917997,"owned_by":"databricks","model_name":"databricks-claude-sonnet-5-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Sonnet 5.5 is Anthropic's model for building features, fixing bugs, and creating documents. It supports a 1 million token context window and up to 128,000 output tokens. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"input_dbu_cost_per_token":0.000028571,"output_dbu_cost_per_token":0.00014286,"cache_read_input_token_cost":2e-7,"cache_creation_input_token_cost":2.5e-6,"cache_creation_input_token_cost_above_1hr":4e-6},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"input_dbu_cost_per_token":0.000028571,"output_dbu_cost_per_token":0.00014286,"cache_read_input_token_cost":2e-7,"cache_creation_input_token_cost":2.5e-6,"cache_creation_input_token_cost_above_1hr":4e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"databricks/databricks-claude-sonnet-5-5","object":"model","created":1790917997,"owned_by":"databricks","model_name":"databricks-claude-sonnet-5-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Sonnet 5.5 is Anthropic's model for building features, fixing bugs, and creating documents. It supports a 1 million token context window and up to 128,000 output tokens. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"input_dbu_cost_per_token":0.000028571,"output_dbu_cost_per_token":0.00014286,"cache_read_input_token_cost":2e-7,"cache_creation_input_token_cost":2.5e-6,"cache_creation_input_token_cost_above_1hr":4e-6},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"input_dbu_cost_per_token":0.000028571,"output_dbu_cost_per_token":0.00014286,"cache_read_input_token_cost":2e-7,"cache_creation_input_token_cost":2.5e-6,"cache_creation_input_token_cost_above_1hr":4e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"deepinfra/anthropic/claude-sonnet-5-5","object":"model","created":1790780828,"owned_by":"deepinfra","model_name":"anthropic/claude-sonnet-5-5","context_length":1000000,"max_input_tokens":null,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null},{"id":"amazon/anthropic.claude-sonnet-5-5@eu","object":"model","created":1790618686,"owned_by":"amazon","model_name":"anthropic.claude-sonnet-5-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.2e-6,"output_cost_per_token":0.000011000000000000001,"cache_read_input_token_cost":1.1e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":2.7500000000000004e-6,"cache_creation_input_token_cost_above_1hr":4.4e-6},"list_pricing":{"input_cost_per_token":2.2e-6,"output_cost_per_token":0.000011000000000000001,"cache_read_input_token_cost":1.1e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":2.7500000000000004e-6,"cache_creation_input_token_cost_above_1hr":4.4e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/anthropic.claude-sonnet-5-5","object":"model","created":1790618686,"owned_by":"amazon","model_name":"anthropic.claude-sonnet-5-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"cache_read_input_token_cost":1e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":2.5e-6,"cache_creation_input_token_cost_above_1hr":4e-6},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"cache_read_input_token_cost":1e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":2.5e-6,"cache_creation_input_token_cost_above_1hr":4e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/anthropic.claude-sonnet-5-5@us","object":"model","created":1790618686,"owned_by":"amazon","model_name":"anthropic.claude-sonnet-5-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.2e-6,"output_cost_per_token":0.000011000000000000001,"cache_read_input_token_cost":1.1e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":2.7500000000000004e-6,"cache_creation_input_token_cost_above_1hr":4.4e-6},"list_pricing":{"input_cost_per_token":2.2e-6,"output_cost_per_token":0.000011000000000000001,"cache_read_input_token_cost":1.1e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":2.7500000000000004e-6,"cache_creation_input_token_cost_above_1hr":4.4e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"anthropic/claude-sonnet-5-5","object":"model","created":1790618686,"owned_by":"anthropic","model_name":"claude-sonnet-5-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"provider_specific_entry":{"us":1.1},"cache_read_input_token_cost":1e-7,"input_cost_per_token_batches":1e-6,"output_cost_per_token_batches":5e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":2.5e-6,"cache_read_input_token_cost_batches":5e-8,"cache_creation_input_token_cost_above_1hr":4e-6},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"provider_specific_entry":{"us":1.1},"cache_read_input_token_cost":1e-7,"input_cost_per_token_batches":1e-6,"output_cost_per_token_batches":5e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":2.5e-6,"cache_read_input_token_cost_batches":5e-8,"cache_creation_input_token_cost_above_1hr":4e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null},{"id":"vertex/claude-sonnet-5-5@eu","object":"model","created":1790618686,"owned_by":"vertex","model_name":"claude-sonnet-5-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.2e-6,"output_cost_per_token":0.000011000000000000001,"cache_read_input_token_cost":1.1e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":2.7500000000000004e-6,"cache_creation_input_token_cost_above_1hr":4.4e-6},"list_pricing":{"input_cost_per_token":2.2e-6,"output_cost_per_token":0.000011000000000000001,"cache_read_input_token_cost":1.1e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":2.7500000000000004e-6,"cache_creation_input_token_cost_above_1hr":4.4e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"vertex/claude-sonnet-5-5","object":"model","created":1790618686,"owned_by":"vertex","model_name":"claude-sonnet-5-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"cache_read_input_token_cost":1e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":2.5e-6,"cache_creation_input_token_cost_above_1hr":4e-6},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"cache_read_input_token_cost":1e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":2.5e-6,"cache_creation_input_token_cost_above_1hr":4e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"vertex/claude-sonnet-5-5@us","object":"model","created":1790618686,"owned_by":"vertex","model_name":"claude-sonnet-5-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.2e-6,"output_cost_per_token":0.000011000000000000001,"cache_read_input_token_cost":1.1e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":2.7500000000000004e-6,"cache_creation_input_token_cost_above_1hr":4.4e-6},"list_pricing":{"input_cost_per_token":2.2e-6,"output_cost_per_token":0.000011000000000000001,"cache_read_input_token_cost":1.1e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":2.7500000000000004e-6,"cache_creation_input_token_cost_above_1hr":4.4e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":10},{"id":"deepseek-flash","object":"model","created":1790867221,"owned_by":"deepseek","mode":"chat","context_length":1000000,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":3e-9},"pricing_endpoint":"tencent/deepseek/deepseek-flash","regions":[{"code":"ap","name":"Asia"}],"alias_of":null,"endpoints":[{"id":"tencent/deepseek/deepseek-flash","object":"model","created":1790867221,"owned_by":"tencent","model_name":"deepseek/deepseek-flash","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":384000,"quantization":null,"retirement_date":null,"description":"This model always redirects to the latest model in the DeepSeek Flash family.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":3e-9},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":3e-9},"discount":null,"discount_ends_at":null,"regions":[{"code":"ap","name":"Asia"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"deepseek-v4-flash-vision-exp","object":"model","created":1790867221,"owned_by":"deepseek","mode":"chat","context_length":1048576,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":3e-9},"pricing_endpoint":"tencent/deepseek/deepseek-v4-flash-vision-exp","regions":[{"code":"ap","name":"Asia"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"tencent/deepseek/deepseek-v4-flash-vision-exp","object":"model","created":1790867221,"owned_by":"tencent","model_name":"deepseek/deepseek-v4-flash-vision-exp","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":384000,"quantization":null,"retirement_date":null,"description":"DeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of DeepSeek V4 Flash 0731 from DeepSeek, adding image understanding while matching the base model on text capabilities including agents,...","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":3e-9},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":3e-9},"discount":null,"discount_ends_at":null,"regions":[{"code":"ap","name":"Asia"}],"zero_data_retention":true,"alias_of":null},{"id":"deepinfra/deepseek-ai/DeepSeek-V4-Flash-Vision-Exp","object":"model","created":1787311563,"owned_by":"deepinfra","model_name":"deepseek-ai/DeepSeek-V4-Flash-Vision-Exp","context_length":1048576,"max_input_tokens":null,"max_output_tokens":262144,"quantization":"fp8","retirement_date":null,"description":"DeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of DeepSeek V4 Flash 0731 from DeepSeek, adding image understanding while matching the base model on text capabilities including agents,...","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4.3999999999999997e-7,"output_cost_per_token":1.32e-6,"cache_read_input_token_cost":1.3999999199999998e-8},"list_pricing":{"input_cost_per_token":4.3999999999999997e-7,"output_cost_per_token":1.32e-6,"cache_read_input_token_cost":1.3999999199999998e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"deepseek-v4-pro-0813","object":"model","created":1790867221,"owned_by":"deepseek","mode":"chat","context_length":1048576,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":4.2900000000000004e-7,"output_cost_per_token":1.2870000000000001e-6,"cache_read_input_token_cost":4.290000000000001e-8},"pricing_endpoint":"qwen/deepseek-v4-pro-0813","regions":[{"code":"ap","name":"Asia"},{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"tencent/deepseek-v4-pro-0813","object":"model","created":1790867221,"owned_by":"tencent","model_name":"deepseek-v4-pro-0813","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":384000,"quantization":null,"retirement_date":null,"description":"DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":6.6e-7,"output_cost_per_token":1.98e-6,"cache_read_input_token_cost":2.2e-8,"input_cost_per_token_cache_hit":4.4e-8,"cache_creation_input_token_cost":0.0},"list_pricing":{"input_cost_per_token":6.6e-7,"output_cost_per_token":1.98e-6,"cache_read_input_token_cost":2.2e-8,"input_cost_per_token_cache_hit":4.4e-8,"cache_creation_input_token_cost":0.0},"discount":null,"discount_ends_at":null,"regions":[{"code":"ap","name":"Asia"}],"zero_data_retention":true,"alias_of":null},{"id":"tensorx/deepseek/deepseek-v4-pro-0813","object":"model","created":1787980172,"owned_by":"tensorx","model_name":"deepseek/deepseek-v4-pro-0813","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":64000,"quantization":null,"retirement_date":null,"description":"DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":4e-6,"cache_read_input_token_cost":5e-7},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":4e-6,"cache_read_input_token_cost":5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"cloudflare/@cf/deepseek-ai/deepseek-v4-pro-0813","object":"model","created":1786549364,"owned_by":"cloudflare","model_name":"@cf/deepseek-ai/deepseek-v4-pro-0813","context_length":1048576,"max_input_tokens":null,"max_output_tokens":393216,"quantization":null,"retirement_date":null,"description":"DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.32e-6,"output_cost_per_token":3.96e-6,"cache_read_input_token_cost":4.4e-8},"list_pricing":{"input_cost_per_token":1.32e-6,"output_cost_per_token":3.96e-6,"cache_read_input_token_cost":4.4e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"deepinfra/deepseek-ai/DeepSeek-V4-Pro-0813","object":"model","created":1786549364,"owned_by":"deepinfra","model_name":"deepseek-ai/DeepSeek-V4-Pro-0813","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":393216,"quantization":"fp8","retirement_date":null,"description":"DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.2999999999999998e-6,"output_cost_per_token":2.5999999999999997e-6,"cache_read_input_token_cost":1.0000000399999998e-7},"list_pricing":{"input_cost_per_token":1.2999999999999998e-6,"output_cost_per_token":2.5999999999999997e-6,"cache_read_input_token_cost":1.0000000399999998e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"nebius/deepseek-ai/DeepSeek-V4-Pro-0813","object":"model","created":1786549364,"owned_by":"nebius","model_name":"deepseek-ai/DeepSeek-V4-Pro-0813","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":393216,"quantization":"fp8","retirement_date":null,"description":"DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.32e-6,"output_cost_per_token":3.96e-6,"cache_read_input_token_cost":1.32e-6},"list_pricing":{"input_cost_per_token":1.32e-6,"output_cost_per_token":3.96e-6,"cache_read_input_token_cost":1.32e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"qwen/deepseek-v4-pro-0813","object":"model","created":1786549364,"owned_by":"qwen","model_name":"deepseek-v4-pro-0813","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":393216,"quantization":null,"retirement_date":null,"description":"A flagship Mixture-of-Experts (MoE) large language model with 1.6 trillion total parameters and 49 billion activated parameters. It natively supports context windows of up to 1 million tokens. Trained on extensive high-quality data, the model delivers strong performance in mathematical and logical reasoning, complex reasoning, professional code generation, and in-depth long-document analysis, and is suitable for demanding scenarios such as advanced scientific research, complex enterprise workflows, and sophisticated agentic applications.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4.2900000000000004e-7,"output_cost_per_token":1.2870000000000001e-6,"cache_read_input_token_cost":4.290000000000001e-8},"list_pricing":{"input_cost_per_token":6.6e-7,"output_cost_per_token":1.98e-6,"cache_read_input_token_cost":6.600000000000001e-8},"discount":0.35,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null},{"id":"together_ai/deepseek-ai/DeepSeek-V4-Pro-0813","object":"model","created":1786549364,"owned_by":"together_ai","model_name":"deepseek-ai/DeepSeek-V4-Pro-0813","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":393216,"quantization":null,"retirement_date":null,"description":"DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.32e-6,"output_cost_per_token":3.96e-6,"cache_read_input_token_cost":1.2999999999999997e-7},"list_pricing":{"input_cost_per_token":1.32e-6,"output_cost_per_token":3.96e-6,"cache_read_input_token_cost":1.2999999999999997e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":7},{"id":"glm-5.3-flashx","object":"model","created":1790867221,"owned_by":"zai","mode":"chat","context_length":1048576,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.7e-7,"output_cost_per_token":1.25e-6,"cache_read_input_token_cost":7.5e-8,"input_cost_per_token_cache_hit":7.5e-8,"cache_creation_input_token_cost":0.0},"pricing_endpoint":"tencent/glm-5.3-flashx","regions":[{"code":"ap","name":"Asia"}],"alias_of":null,"endpoints":[{"id":"tencent/glm-5.3-flashx","object":"model","created":1790867221,"owned_by":"tencent","model_name":"glm-5.3-flashx","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GLM-5.3-FlashX is the high-speed variant of Z.ai's GLM-5.3-Flash, a native multimodal model delivering inference speeds of up to 200 tokens/s.","source":null,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.7e-7,"output_cost_per_token":1.25e-6,"cache_read_input_token_cost":7.5e-8,"input_cost_per_token_cache_hit":7.5e-8,"cache_creation_input_token_cost":0.0},"list_pricing":{"input_cost_per_token":3.7e-7,"output_cost_per_token":1.25e-6,"cache_read_input_token_cost":7.5e-8,"input_cost_per_token_cache_hit":7.5e-8,"cache_creation_input_token_cost":0.0},"discount":null,"discount_ends_at":null,"regions":[{"code":"ap","name":"Asia"}],"zero_data_retention":true,"alias_of":null},{"id":"zai/glm-5.3-flashx","object":"model","created":1789744020,"owned_by":"zai","model_name":"glm-5.3-flashx","context_length":1048576,"max_input_tokens":null,"max_output_tokens":131072,"quantization":"fp8","retirement_date":"2098-12-31","description":"GLM-5.3-FlashX is the high-speed variant of Z.ai's GLM-5.3-Flash, a native multimodal model delivering inference speeds of up to 200 tokens/s.","source":null,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.7e-7,"output_cost_per_token":1.25e-6,"cache_read_input_token_cost":7.5e-8},"list_pricing":{"input_cost_per_token":3.7e-7,"output_cost_per_token":1.25e-6,"cache_read_input_token_cost":7.5e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"ap","name":"Asia"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"hy-mt2-lite","object":"model","created":1790867221,"owned_by":"meta","mode":"chat","context_length":8000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4.4e-8,"output_cost_per_token":1.77e-7},"pricing_endpoint":"tencent/hy-mt2-lite","regions":[{"code":"ap","name":"Asia"}],"alias_of":null,"endpoints":[{"id":"tencent/hy-mt2-lite","object":"model","created":1790867221,"owned_by":"tencent","model_name":"hy-mt2-lite","context_length":8000,"max_input_tokens":4000,"max_output_tokens":4000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4.4e-8,"output_cost_per_token":1.77e-7},"list_pricing":{"input_cost_per_token":4.4e-8,"output_cost_per_token":1.77e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"ap","name":"Asia"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"hy-mt2-plus","object":"model","created":1790867221,"owned_by":"meta","mode":"chat","context_length":8000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":7.4e-8,"output_cost_per_token":2.95e-7},"pricing_endpoint":"tencent/hy-mt2-plus","regions":[{"code":"ap","name":"Asia"}],"alias_of":null,"endpoints":[{"id":"tencent/hy-mt2-plus","object":"model","created":1790867221,"owned_by":"tencent","model_name":"hy-mt2-plus","context_length":8000,"max_input_tokens":4000,"max_output_tokens":4000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":7.4e-8,"output_cost_per_token":2.95e-7},"list_pricing":{"input_cost_per_token":7.4e-8,"output_cost_per_token":2.95e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"ap","name":"Asia"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"hy-mt2-pro","object":"model","created":1790867221,"owned_by":"meta","mode":"chat","context_length":8000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":7.4e-8,"output_cost_per_token":2.95e-7},"pricing_endpoint":"tencent/hy-mt2-pro","regions":[{"code":"ap","name":"Asia"}],"alias_of":null,"endpoints":[{"id":"tencent/hy-mt2-pro","object":"model","created":1790867221,"owned_by":"tencent","model_name":"hy-mt2-pro","context_length":8000,"max_input_tokens":4000,"max_output_tokens":4000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":7.4e-8,"output_cost_per_token":2.95e-7},"list_pricing":{"input_cost_per_token":7.4e-8,"output_cost_per_token":2.95e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"ap","name":"Asia"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"hy3","object":"model","created":1790867221,"owned_by":"tencent","mode":"chat","context_length":262144,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.3e-7,"output_cost_per_token":5.3e-7,"cache_read_input_token_cost":3.3e-8},"pricing_endpoint":"deepinfra/tencent/Hy3","regions":[{"code":"ap","name":"Asia"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"tencent/hy3","object":"model","created":1790867221,"owned_by":"tencent","model_name":"hy3","context_length":256000,"max_input_tokens":192000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.32e-7,"output_cost_per_token":5.28e-7,"cache_read_input_token_cost":3.3e-8},"list_pricing":{"input_cost_per_token":1.32e-7,"output_cost_per_token":5.28e-7,"cache_read_input_token_cost":3.3e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"ap","name":"Asia"}],"zero_data_retention":true,"alias_of":null},{"id":"deepinfra/tencent/Hy3","object":"model","created":1783344048,"owned_by":"deepinfra","model_name":"tencent/Hy3","context_length":262144,"max_input_tokens":null,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It supports a configurable reasoning effort:...","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.3e-7,"output_cost_per_token":5.3e-7,"cache_read_input_token_cost":3.3e-8},"list_pricing":{"input_cost_per_token":1.3e-7,"output_cost_per_token":5.3e-7,"cache_read_input_token_cost":3.3e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"hy4-preview","object":"model","created":1790867221,"owned_by":"tencent","mode":"chat","context_length":1048576,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":8.34e-7,"output_cost_per_token":2.5010000000000003e-6,"cache_read_input_token_cost":4.199999814e-8},"pricing_endpoint":"deepinfra/tencent/Hy4-preview","regions":[{"code":"ap","name":"Asia"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"tencent/hy4-preview","object":"model","created":1790867221,"owned_by":"tencent","model_name":"hy4-preview","context_length":1000000,"max_input_tokens":960000,"max_output_tokens":64000,"quantization":null,"retirement_date":null,"description":"The official release of Hy4 delivers comprehensive and substantial improvements over Hy4 Preview, with particularly strong gains in agentic capabilities and performance across a wide range of long-horizon, real-world productivity...","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":8.34e-7,"output_cost_per_token":2.501e-6,"cache_read_input_token_cost":4.2e-8,"input_cost_per_token_cache_hit":4.2e-8},"list_pricing":{"input_cost_per_token":8.34e-7,"output_cost_per_token":2.501e-6,"cache_read_input_token_cost":4.2e-8,"input_cost_per_token_cache_hit":4.2e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"ap","name":"Asia"}],"zero_data_retention":true,"alias_of":null},{"id":"deepinfra/tencent/Hy4-preview","object":"model","created":1787897375,"owned_by":"deepinfra","model_name":"tencent/Hy4-preview","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":131072,"quantization":"fp4","retirement_date":null,"description":"The official release of Hy4 delivers comprehensive and substantial improvements over Hy4 Preview, with particularly strong gains in agentic capabilities and performance across a wide range of long-horizon, real-world productivity...","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":8.34e-7,"output_cost_per_token":2.5010000000000003e-6,"cache_read_input_token_cost":4.199999814e-8},"list_pricing":{"input_cost_per_token":8.34e-7,"output_cost_per_token":2.5010000000000003e-6,"cache_read_input_token_cost":4.199999814e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"kimi-k2.7-code-highspeed","object":"model","created":1790867221,"owned_by":"moonshot","mode":"chat","context_length":262144,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.9e-6,"output_cost_per_token":8e-6,"cache_read_input_token_cost":3.8e-7,"input_cost_per_token_cache_hit":3.8e-7,"cache_creation_input_token_cost":0.0},"pricing_endpoint":"tencent/kimi-k2.7-code-highspeed","regions":[{"code":"ap","name":"Asia"}],"alias_of":null,"endpoints":[{"id":"tencent/kimi-k2.7-code-highspeed","object":"model","created":1790867221,"owned_by":"tencent","model_name":"kimi-k2.7-code-highspeed","context_length":256000,"max_input_tokens":256000,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.9e-6,"output_cost_per_token":8e-6,"cache_read_input_token_cost":3.8e-7,"input_cost_per_token_cache_hit":3.8e-7,"cache_creation_input_token_cost":0.0},"list_pricing":{"input_cost_per_token":1.9e-6,"output_cost_per_token":8e-6,"cache_read_input_token_cost":3.8e-7,"input_cost_per_token_cache_hit":3.8e-7,"cache_creation_input_token_cost":0.0},"discount":null,"discount_ends_at":null,"regions":[{"code":"ap","name":"Asia"}],"zero_data_retention":true,"alias_of":null},{"id":"moonshot/kimi-k2.7-code-highspeed","object":"model","created":1788215842,"owned_by":"moonshot","model_name":"kimi-k2.7-code-highspeed","context_length":262144,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.8999999999999998e-6,"output_cost_per_token":8e-6,"cache_read_input_token_cost":3.8e-7},"list_pricing":{"input_cost_per_token":1.8999999999999998e-6,"output_cost_per_token":8e-6,"cache_read_input_token_cost":3.8e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"ap","name":"Asia"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":2},{"id":"kimi-k2.8-preview","object":"model","created":1790867221,"owned_by":"moonshot","mode":"chat","context_length":1000000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":4e-6,"cache_read_input_token_cost":2.5e-7,"input_cost_per_token_cache_hit":2.5e-7,"cache_creation_input_token_cost":0.0},"pricing_endpoint":"tencent/kimi-k2.8-preview","regions":[{"code":"ap","name":"Asia"}],"alias_of":null,"endpoints":[{"id":"tencent/kimi-k2.8-preview","object":"model","created":1790867221,"owned_by":"tencent","model_name":"kimi-k2.8-preview","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":4e-6,"cache_read_input_token_cost":2.5e-7,"input_cost_per_token_cache_hit":2.5e-7,"cache_creation_input_token_cost":0.0},"list_pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":4e-6,"cache_read_input_token_cost":2.5e-7,"input_cost_per_token_cache_hit":2.5e-7,"cache_creation_input_token_cost":0.0},"discount":null,"discount_ends_at":null,"regions":[{"code":"ap","name":"Asia"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"mimo-v2.5-pro","object":"model","created":1790867221,"owned_by":"xiaomi","mode":"chat","context_length":1048576,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4.35e-7,"output_cost_per_token":8.7e-7,"cache_read_input_token_cost":3.6e-9},"pricing_endpoint":"tencent/mimo-v2.5-pro","regions":[{"code":"ap","name":"Asia"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"tencent/mimo-v2.5-pro","object":"model","created":1790867221,"owned_by":"tencent","model_name":"mimo-v2.5-pro","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4.35e-7,"output_cost_per_token":8.7e-7,"cache_read_input_token_cost":3.6e-9},"list_pricing":{"input_cost_per_token":4.35e-7,"output_cost_per_token":8.7e-7,"cache_read_input_token_cost":3.6e-9},"discount":null,"discount_ends_at":null,"regions":[{"code":"ap","name":"Asia"}],"zero_data_retention":true,"alias_of":null},{"id":"deepinfra/XiaomiMiMo/MiMo-V2.5-Pro","object":"model","created":1776874273,"owned_by":"deepinfra","model_name":"XiaomiMiMo/MiMo-V2.5-Pro","context_length":1048576,"max_input_tokens":null,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"MiMo-V2.5-Pro is Xiaomi’s flagship model, delivering strong performance in general agentic capabilities, complex software engineering, and long-horizon tasks, with top rankings on benchmarks such as ClawEval, GDPVal, and SWE-bench Pro....","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":2.9999999999999997e-6,"cache_read_input_token_cost":1.9999999999999996e-7},"list_pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":2.9999999999999997e-6,"cache_read_input_token_cost":1.9999999999999996e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"mimo-v2.6-flash","object":"model","created":1790867221,"owned_by":"xiaomi","mode":"chat","context_length":1048576,"capabilities":{"input_modalities":["text","image","video","audio"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.4e-7,"output_cost_per_token":2.8e-7,"cache_read_input_token_cost":2.8e-9},"pricing_endpoint":"xiaomi/mimo-v2.6-flash","regions":[{"code":"ap","name":"Asia"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"tencent/mimo-v2.6-flash","object":"model","created":1790867221,"owned_by":"tencent","model_name":"mimo-v2.6-flash","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"MiMo-V2.6-Flash is an open-source foundation model developed by Xiaomi.","source":null,"capabilities":{"input_modalities":["text","image","video","audio"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.4e-7,"output_cost_per_token":2.8e-7,"cache_read_input_token_cost":2.8e-9},"list_pricing":{"input_cost_per_token":1.4e-7,"output_cost_per_token":2.8e-7,"cache_read_input_token_cost":2.8e-9},"discount":null,"discount_ends_at":null,"regions":[{"code":"ap","name":"Asia"}],"zero_data_retention":true,"alias_of":null},{"id":"deepinfra/XiaomiMiMo/MiMo-V2.6-Flash","object":"model","created":1790021264,"owned_by":"deepinfra","model_name":"XiaomiMiMo/MiMo-V2.6-Flash","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":131072,"quantization":"fp8","retirement_date":null,"description":"MiMo-V2.6-Flash is an open-source foundation model developed by Xiaomi.","source":null,"capabilities":{"input_modalities":["text","image","video","audio"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.4e-7,"output_cost_per_token":2.8e-7,"cache_read_input_token_cost":2.8000000000000003e-9},"list_pricing":{"input_cost_per_token":1.4e-7,"output_cost_per_token":2.8e-7,"cache_read_input_token_cost":2.8000000000000003e-9},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"xiaomi/mimo-v2.6-flash","object":"model","created":1790021264,"owned_by":"xiaomi","model_name":"mimo-v2.6-flash","context_length":1048576,"max_input_tokens":null,"max_output_tokens":131072,"quantization":"fp8","retirement_date":null,"description":"MiMo-V2.6-Flash is an open-source foundation model developed by Xiaomi.","source":null,"capabilities":{"input_modalities":["text","image","video","audio"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.4e-7,"output_cost_per_token":2.8e-7,"cache_read_input_token_cost":2.8e-9},"list_pricing":{"input_cost_per_token":1.4e-7,"output_cost_per_token":2.8e-7,"cache_read_input_token_cost":2.8e-9},"discount":null,"discount_ends_at":null,"regions":[{"code":"ap","name":"Asia"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":3},{"id":"mimo-v2.6-pro","object":"model","created":1790867221,"owned_by":"xiaomi","mode":"chat","context_length":1048576,"capabilities":{"input_modalities":["text","image","video","audio"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4.3e-7,"output_cost_per_token":8.7e-7,"cache_read_input_token_cost":3.5999987000000004e-9},"pricing_endpoint":"deepinfra/XiaomiMiMo/MiMo-V2.6-Pro","regions":[{"code":"ap","name":"Asia"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"tencent/mimo-v2.6-pro","object":"model","created":1790867221,"owned_by":"tencent","model_name":"mimo-v2.6-pro","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"MiMo-V2.6-Pro is the flagship foundation model developed by Xiaomi.","source":null,"capabilities":{"input_modalities":["text","image","video","audio"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4.35e-7,"output_cost_per_token":8.7e-7,"cache_read_input_token_cost":3.6e-9},"list_pricing":{"input_cost_per_token":4.35e-7,"output_cost_per_token":8.7e-7,"cache_read_input_token_cost":3.6e-9},"discount":null,"discount_ends_at":null,"regions":[{"code":"ap","name":"Asia"}],"zero_data_retention":true,"alias_of":null},{"id":"deepinfra/XiaomiMiMo/MiMo-V2.6-Pro","object":"model","created":1790021259,"owned_by":"deepinfra","model_name":"XiaomiMiMo/MiMo-V2.6-Pro","context_length":1048576,"max_input_tokens":null,"max_output_tokens":131072,"quantization":"fp8","retirement_date":null,"description":"MiMo-V2.6-Pro is the flagship foundation model developed by Xiaomi.","source":null,"capabilities":{"input_modalities":["text","image","video","audio"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4.3e-7,"output_cost_per_token":8.7e-7,"cache_read_input_token_cost":3.5999987000000004e-9},"list_pricing":{"input_cost_per_token":4.3e-7,"output_cost_per_token":8.7e-7,"cache_read_input_token_cost":3.5999987000000004e-9},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"xiaomi/mimo-v2.6-pro","object":"model","created":1790021259,"owned_by":"xiaomi","model_name":"mimo-v2.6-pro","context_length":1048576,"max_input_tokens":null,"max_output_tokens":131072,"quantization":"fp8","retirement_date":null,"description":"MiMo-V2.6-Pro is the flagship foundation model developed by Xiaomi.","source":null,"capabilities":{"input_modalities":["text","image","video","audio"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4.35e-7,"output_cost_per_token":8.7e-7,"cache_read_input_token_cost":3.6e-9},"list_pricing":{"input_cost_per_token":4.35e-7,"output_cost_per_token":8.7e-7,"cache_read_input_token_cost":3.6e-9},"discount":null,"discount_ends_at":null,"regions":[{"code":"ap","name":"Asia"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":3},{"id":"minimax-m2.7","object":"model","created":1790867221,"owned_by":"minimax","mode":"chat","context_length":204800,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1.2e-6,"cache_read_input_token_cost":6e-8},"pricing_endpoint":"minimax/MiniMax-M2.7","regions":[{"code":"ap","name":"Asia"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"tencent/minimax-m2.7","object":"model","created":1790867221,"owned_by":"tencent","model_name":"minimax-m2.7","context_length":200000,"max_input_tokens":200000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1.2e-6,"cache_read_input_token_cost":6e-8},"list_pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1.2e-6,"cache_read_input_token_cost":6e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"ap","name":"Asia"}],"zero_data_retention":true,"alias_of":null},{"id":"deepinfra/MiniMaxAI/MiniMax-M2.7","object":"model","created":1773836697,"owned_by":"deepinfra","model_name":"MiniMaxAI/MiniMax-M2.7","context_length":196608,"max_input_tokens":null,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement. Built to actively participate in its own evolution, M2.7 integrates advanced agentic capabilities through multi-agent...","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.8e-7,"output_cost_per_token":1.7e-6,"cache_read_input_token_cost":7e-8},"list_pricing":{"input_cost_per_token":3.8e-7,"output_cost_per_token":1.7e-6,"cache_read_input_token_cost":7e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"minimax/MiniMax-M2.7","object":"model","created":1773836697,"owned_by":"minimax","model_name":"MiniMax-M2.7","context_length":204800,"max_input_tokens":null,"max_output_tokens":196608,"quantization":null,"retirement_date":"2026-11-05","description":"MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1.2e-6,"cache_read_input_token_cost":6e-8},"list_pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1.2e-6,"cache_read_input_token_cost":6e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"ap","name":"Asia"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":3},{"id":"~deepseek-pro-latest","object":"model","created":1790867221,"owned_by":"deepseek","mode":"chat","context_length":1048576,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":4.2900000000000004e-7,"output_cost_per_token":1.2870000000000001e-6,"cache_read_input_token_cost":4.290000000000001e-8},"pricing_endpoint":"qwen/deepseek-v4-pro-0813","regions":[{"code":"ap","name":"Asia"},{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":"deepseek-v4-pro-0813","endpoints":[{"id":"tencent/deepseek-v4-pro-0813","object":"model","created":1790867221,"owned_by":"tencent","model_name":"deepseek-v4-pro-0813","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":384000,"quantization":null,"retirement_date":null,"description":"DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":6.6e-7,"output_cost_per_token":1.98e-6,"cache_read_input_token_cost":2.2e-8,"input_cost_per_token_cache_hit":4.4e-8,"cache_creation_input_token_cost":0.0},"list_pricing":{"input_cost_per_token":6.6e-7,"output_cost_per_token":1.98e-6,"cache_read_input_token_cost":2.2e-8,"input_cost_per_token_cache_hit":4.4e-8,"cache_creation_input_token_cost":0.0},"discount":null,"discount_ends_at":null,"regions":[{"code":"ap","name":"Asia"}],"zero_data_retention":true,"alias_of":null},{"id":"tensorx/deepseek/deepseek-v4-pro-0813","object":"model","created":1787980172,"owned_by":"tensorx","model_name":"deepseek/deepseek-v4-pro-0813","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":64000,"quantization":null,"retirement_date":null,"description":"DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":4e-6,"cache_read_input_token_cost":5e-7},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":4e-6,"cache_read_input_token_cost":5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"cloudflare/@cf/deepseek-ai/deepseek-v4-pro-0813","object":"model","created":1786549364,"owned_by":"cloudflare","model_name":"@cf/deepseek-ai/deepseek-v4-pro-0813","context_length":1048576,"max_input_tokens":null,"max_output_tokens":393216,"quantization":null,"retirement_date":null,"description":"DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.32e-6,"output_cost_per_token":3.96e-6,"cache_read_input_token_cost":4.4e-8},"list_pricing":{"input_cost_per_token":1.32e-6,"output_cost_per_token":3.96e-6,"cache_read_input_token_cost":4.4e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"deepinfra/deepseek-ai/DeepSeek-V4-Pro-0813","object":"model","created":1786549364,"owned_by":"deepinfra","model_name":"deepseek-ai/DeepSeek-V4-Pro-0813","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":393216,"quantization":"fp8","retirement_date":null,"description":"DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.2999999999999998e-6,"output_cost_per_token":2.5999999999999997e-6,"cache_read_input_token_cost":1.0000000399999998e-7},"list_pricing":{"input_cost_per_token":1.2999999999999998e-6,"output_cost_per_token":2.5999999999999997e-6,"cache_read_input_token_cost":1.0000000399999998e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"nebius/deepseek-ai/DeepSeek-V4-Pro-0813","object":"model","created":1786549364,"owned_by":"nebius","model_name":"deepseek-ai/DeepSeek-V4-Pro-0813","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":393216,"quantization":"fp8","retirement_date":null,"description":"DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.32e-6,"output_cost_per_token":3.96e-6,"cache_read_input_token_cost":1.32e-6},"list_pricing":{"input_cost_per_token":1.32e-6,"output_cost_per_token":3.96e-6,"cache_read_input_token_cost":1.32e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"qwen/deepseek-v4-pro-0813","object":"model","created":1786549364,"owned_by":"qwen","model_name":"deepseek-v4-pro-0813","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":393216,"quantization":null,"retirement_date":null,"description":"A flagship Mixture-of-Experts (MoE) large language model with 1.6 trillion total parameters and 49 billion activated parameters. It natively supports context windows of up to 1 million tokens. Trained on extensive high-quality data, the model delivers strong performance in mathematical and logical reasoning, complex reasoning, professional code generation, and in-depth long-document analysis, and is suitable for demanding scenarios such as advanced scientific research, complex enterprise workflows, and sophisticated agentic applications.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4.2900000000000004e-7,"output_cost_per_token":1.2870000000000001e-6,"cache_read_input_token_cost":4.290000000000001e-8},"list_pricing":{"input_cost_per_token":6.6e-7,"output_cost_per_token":1.98e-6,"cache_read_input_token_cost":6.600000000000001e-8},"discount":0.35,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null},{"id":"together_ai/deepseek-ai/DeepSeek-V4-Pro-0813","object":"model","created":1786549364,"owned_by":"together_ai","model_name":"deepseek-ai/DeepSeek-V4-Pro-0813","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":393216,"quantization":null,"retirement_date":null,"description":"DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.32e-6,"output_cost_per_token":3.96e-6,"cache_read_input_token_cost":1.2999999999999997e-7},"list_pricing":{"input_cost_per_token":1.32e-6,"output_cost_per_token":3.96e-6,"cache_read_input_token_cost":1.2999999999999997e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":7},{"id":"deep-research-pro-preview-12-2025","object":"model","created":1790725775,"owned_by":"google","mode":"chat","context_length":1048576,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_image":0.0011,"input_cost_per_token":2e-6,"output_cost_per_token":0.000012,"search_context_cost_per_query":{"search_context_size_low":0.035,"search_context_size_high":0.035,"search_context_size_medium":0.035}},"pricing_endpoint":"google/deep-research-pro-preview-12-2025","regions":[{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"google/deep-research-pro-preview-12-2025","object":"model","created":1790725775,"owned_by":"google","model_name":"deep-research-pro-preview-12-2025","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_image":0.0011,"input_cost_per_token":2e-6,"output_cost_per_token":0.000012,"search_context_cost_per_query":{"search_context_size_low":0.035,"search_context_size_high":0.035,"search_context_size_medium":0.035}},"list_pricing":{"input_cost_per_image":0.0011,"input_cost_per_token":2e-6,"output_cost_per_token":0.000012,"search_context_cost_per_query":{"search_context_size_low":0.035,"search_context_size_high":0.035,"search_context_size_medium":0.035}},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":1},{"id":"qwen3.8-flash-next","object":"model","created":1790658829,"owned_by":"qwen","mode":"chat","context_length":262144,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":4.7e-7,"cache_read_input_token_cost":2.25e-8},"pricing_endpoint":"flexai/Qwen3.8-Flash-Next","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"flexai/Qwen3.8-Flash-Next","object":"model","created":1790658829,"owned_by":"flexai","model_name":"Qwen3.8-Flash-Next","context_length":262144,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":4.7e-7,"cache_read_input_token_cost":2.25e-8},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":4.7e-7,"cache_read_input_token_cost":2.25e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"tensorx/qwen/qwen3.8-flash-next","object":"model","created":1787929919,"owned_by":"tensorx","model_name":"qwen/qwen3.8-flash-next","context_length":262144,"max_input_tokens":262144,"max_output_tokens":64000,"quantization":null,"retirement_date":null,"description":"Served by TensorX at fp8 quantization.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":5e-8},"list_pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":5e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"c4ai-aya-expanse-32b","object":"model","created":1790399645,"owned_by":"cohere","mode":"chat","context_length":128000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":1.5e-6},"pricing_endpoint":"cohere/c4ai-aya-expanse-32b","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"cohere/c4ai-aya-expanse-32b","object":"model","created":1790399645,"owned_by":"cohere","model_name":"c4ai-aya-expanse-32b","context_length":128000,"max_input_tokens":128000,"max_output_tokens":4000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":1.5e-6},"list_pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":1.5e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":1},{"id":"claude-opus-5.5","object":"model","created":1790399645,"owned_by":"anthropic","mode":"chat","context_length":1000000,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4e-6,"output_cost_per_token":0.00002,"provider_specific_entry":{"us":1.1,"fast":2.0},"cache_read_input_token_cost":2e-7,"input_cost_per_token_batches":2e-6,"output_cost_per_token_batches":0.00001,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":5e-6,"cache_read_input_token_cost_batches":1e-7,"cache_creation_input_token_cost_above_1hr":8e-6},"pricing_endpoint":"anthropic/claude-opus-5-5","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"databricks/databricks-claude-opus-5-5@eu","object":"model","created":1790399645,"owned_by":"databricks","model_name":"databricks-claude-opus-5-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Opus 5.5 is Anthropic's most intelligent model for complex reasoning, coding, and agentic workflows. It uses adaptive thinking to dynamically allocate reasoning effort and supports large-context tasks such as deep document analysis and multi-step tool use. This model is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4e-6,"output_cost_per_token":0.00002,"input_dbu_cost_per_token":0.000057143,"output_dbu_cost_per_token":0.000285714,"cache_read_input_token_cost":4e-7,"cache_creation_input_token_cost":5e-6,"cache_creation_input_token_cost_above_1hr":8e-6},"list_pricing":{"input_cost_per_token":4e-6,"output_cost_per_token":0.00002,"input_dbu_cost_per_token":0.000057143,"output_dbu_cost_per_token":0.000285714,"cache_read_input_token_cost":4e-7,"cache_creation_input_token_cost":5e-6,"cache_creation_input_token_cost_above_1hr":8e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"databricks/databricks-claude-opus-5-5","object":"model","created":1790399645,"owned_by":"databricks","model_name":"databricks-claude-opus-5-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Opus 5.5 is Anthropic's most intelligent model for complex reasoning, coding, and agentic workflows. It uses adaptive thinking to dynamically allocate reasoning effort and supports large-context tasks such as deep document analysis and multi-step tool use. This model is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4e-6,"output_cost_per_token":0.00002,"input_dbu_cost_per_token":0.000057143,"output_dbu_cost_per_token":0.000285714,"cache_read_input_token_cost":4e-7,"cache_creation_input_token_cost":5e-6,"cache_creation_input_token_cost_above_1hr":8e-6},"list_pricing":{"input_cost_per_token":4e-6,"output_cost_per_token":0.00002,"input_dbu_cost_per_token":0.000057143,"output_dbu_cost_per_token":0.000285714,"cache_read_input_token_cost":4e-7,"cache_creation_input_token_cost":5e-6,"cache_creation_input_token_cost_above_1hr":8e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"deepinfra/anthropic/claude-opus-5-5","object":"model","created":1790184068,"owned_by":"deepinfra","model_name":"anthropic/claude-opus-5-5","context_length":1000000,"max_input_tokens":null,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4e-6,"output_cost_per_token":0.00002,"cache_read_input_token_cost":2.0000000000000002e-7},"list_pricing":{"input_cost_per_token":4e-6,"output_cost_per_token":0.00002,"cache_read_input_token_cost":2.0000000000000002e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null},{"id":"amazon/anthropic.claude-opus-5-5@eu","object":"model","created":1790094732,"owned_by":"amazon","model_name":"anthropic.claude-opus-5-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4.4e-6,"output_cost_per_token":0.000022000000000000003,"cache_read_input_token_cost":2.2e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":5.500000000000001e-6,"cache_creation_input_token_cost_above_1hr":8.8e-6},"list_pricing":{"input_cost_per_token":4.4e-6,"output_cost_per_token":0.000022000000000000003,"cache_read_input_token_cost":2.2e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":5.500000000000001e-6,"cache_creation_input_token_cost_above_1hr":8.8e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/anthropic.claude-opus-5-5","object":"model","created":1790094732,"owned_by":"amazon","model_name":"anthropic.claude-opus-5-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4e-6,"output_cost_per_token":0.00002,"cache_read_input_token_cost":2e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":5e-6,"cache_creation_input_token_cost_above_1hr":8e-6},"list_pricing":{"input_cost_per_token":4e-6,"output_cost_per_token":0.00002,"cache_read_input_token_cost":2e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":5e-6,"cache_creation_input_token_cost_above_1hr":8e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/anthropic.claude-opus-5-5@us","object":"model","created":1790094732,"owned_by":"amazon","model_name":"anthropic.claude-opus-5-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4.4e-6,"output_cost_per_token":0.000022000000000000003,"cache_read_input_token_cost":2.2e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":5.500000000000001e-6,"cache_creation_input_token_cost_above_1hr":8.8e-6},"list_pricing":{"input_cost_per_token":4.4e-6,"output_cost_per_token":0.000022000000000000003,"cache_read_input_token_cost":2.2e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":5.500000000000001e-6,"cache_creation_input_token_cost_above_1hr":8.8e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"anthropic/claude-opus-5-5","object":"model","created":1790094732,"owned_by":"anthropic","model_name":"claude-opus-5-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4e-6,"output_cost_per_token":0.00002,"provider_specific_entry":{"us":1.1,"fast":2.0},"cache_read_input_token_cost":2e-7,"input_cost_per_token_batches":2e-6,"output_cost_per_token_batches":0.00001,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":5e-6,"cache_read_input_token_cost_batches":1e-7,"cache_creation_input_token_cost_above_1hr":8e-6},"list_pricing":{"input_cost_per_token":4e-6,"output_cost_per_token":0.00002,"provider_specific_entry":{"us":1.1,"fast":2.0},"cache_read_input_token_cost":2e-7,"input_cost_per_token_batches":2e-6,"output_cost_per_token_batches":0.00001,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":5e-6,"cache_read_input_token_cost_batches":1e-7,"cache_creation_input_token_cost_above_1hr":8e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null},{"id":"vertex/claude-opus-5-5@eu","object":"model","created":1790094732,"owned_by":"vertex","model_name":"claude-opus-5-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4.4e-6,"output_cost_per_token":0.000022000000000000003,"cache_read_input_token_cost":2.2e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":5.500000000000001e-6,"cache_creation_input_token_cost_above_1hr":8.8e-6},"list_pricing":{"input_cost_per_token":4.4e-6,"output_cost_per_token":0.000022000000000000003,"cache_read_input_token_cost":2.2e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":5.500000000000001e-6,"cache_creation_input_token_cost_above_1hr":8.8e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"vertex/claude-opus-5-5","object":"model","created":1790094732,"owned_by":"vertex","model_name":"claude-opus-5-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4e-6,"output_cost_per_token":0.00002,"cache_read_input_token_cost":2e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":5e-6,"cache_creation_input_token_cost_above_1hr":8e-6},"list_pricing":{"input_cost_per_token":4e-6,"output_cost_per_token":0.00002,"cache_read_input_token_cost":2e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":5e-6,"cache_creation_input_token_cost_above_1hr":8e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"vertex/claude-opus-5-5@us","object":"model","created":1790094732,"owned_by":"vertex","model_name":"claude-opus-5-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4.4e-6,"output_cost_per_token":0.000022000000000000003,"cache_read_input_token_cost":2.2e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":5.500000000000001e-6,"cache_creation_input_token_cost_above_1hr":8.8e-6},"list_pricing":{"input_cost_per_token":4.4e-6,"output_cost_per_token":0.000022000000000000003,"cache_read_input_token_cost":2.2e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":5.500000000000001e-6,"cache_creation_input_token_cost_above_1hr":8.8e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":10},{"id":"gpt-6-luna","object":"model","created":1790399645,"owned_by":"openai","mode":"chat","context_length":1050000,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":5e-7,"input_cost_per_token_flex":5e-8,"output_cost_per_token_flex":2.5e-7,"cache_read_input_token_cost":1e-8,"input_cost_per_token_batches":5e-8,"input_cost_per_token_priority":2e-7,"output_cost_per_token_batches":2.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"input_cost_per_token_decisions":1e-7,"output_cost_per_token_priority":1e-6,"cache_creation_input_token_cost":1.25e-7,"output_cost_per_token_decisions":0.0,"cache_read_input_token_cost_flex":5e-9,"cache_read_input_token_cost_batches":5e-9,"cache_creation_input_token_cost_flex":6.25e-8,"cache_read_input_token_cost_priority":2e-8,"cache_read_input_token_cost_decisions":1e-8,"input_cost_per_token_above_272k_tokens":2e-7,"output_cost_per_token_above_272k_tokens":7.5e-7,"cache_creation_input_token_cost_priority":2.5e-7,"cache_creation_input_token_cost_decisions":1.25e-7,"cache_creation_input_token_cost_above_12hr":2.5e-7,"input_cost_per_token_above_272k_tokens_flex":1e-7,"output_cost_per_token_above_272k_tokens_flex":3.75e-7,"cache_read_input_token_cost_above_272k_tokens":2e-8,"cache_creation_input_token_cost_above_12hr_flex":1.25e-7,"input_cost_per_token_above_272k_tokens_priority":4e-7,"input_cost_per_token_above_272k_tokens_decisions":2e-7,"output_cost_per_token_above_272k_tokens_priority":1.5e-6,"cache_creation_input_token_cost_above_272k_tokens":2.5e-7,"output_cost_per_token_above_272k_tokens_decisions":0.0,"cache_read_input_token_cost_above_272k_tokens_flex":1e-8,"cache_creation_input_token_cost_above_12hr_priority":5e-7,"cache_creation_input_token_cost_above_272k_tokens_flex":1.25e-7,"cache_read_input_token_cost_above_272k_tokens_priority":4e-8,"cache_read_input_token_cost_above_272k_tokens_decisions":2e-8,"cache_creation_input_token_cost_above_272k_tokens_priority":5e-7,"cache_creation_input_token_cost_above_272k_tokens_decisions":2.5e-7,"cache_creation_input_token_cost_above_12hr_above_272k_tokens":5e-7,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_flex":2.5e-7,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_priority":1e-6},"pricing_endpoint":"openai/gpt-6-luna","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"databricks/databricks-gpt-6-luna@eu","object":"model","created":1790399645,"owned_by":"databricks","model_name":"databricks-gpt-6-luna","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 family, bringing strong reasoning and agentic capability at the lowest cost in the lineup. This model supports multimodal (text and image) inputs and a long context window. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":5e-7,"input_dbu_cost_per_token":1.429e-6,"output_dbu_cost_per_token":7.143e-6,"cache_read_input_token_cost":1e-8,"cache_creation_input_token_cost":1.25e-7,"input_cost_per_token_above_272k_tokens":2e-7,"output_cost_per_token_above_272k_tokens":7.5e-7,"cache_creation_input_token_cost_priority":2.5e-7,"cache_read_input_token_cost_above_272k_tokens":2e-8,"input_cost_per_token_above_272k_tokens_priority":4e-7,"output_cost_per_token_above_272k_tokens_priority":1.5e-6,"cache_creation_input_token_cost_above_272k_tokens":2.5e-7,"cache_read_input_token_cost_above_272k_tokens_priority":4e-8,"cache_creation_input_token_cost_above_272k_tokens_priority":5e-7},"list_pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":5e-7,"input_dbu_cost_per_token":1.429e-6,"output_dbu_cost_per_token":7.143e-6,"cache_read_input_token_cost":1e-8,"cache_creation_input_token_cost":1.25e-7,"input_cost_per_token_above_272k_tokens":2e-7,"output_cost_per_token_above_272k_tokens":7.5e-7,"cache_creation_input_token_cost_priority":2.5e-7,"cache_read_input_token_cost_above_272k_tokens":2e-8,"input_cost_per_token_above_272k_tokens_priority":4e-7,"output_cost_per_token_above_272k_tokens_priority":1.5e-6,"cache_creation_input_token_cost_above_272k_tokens":2.5e-7,"cache_read_input_token_cost_above_272k_tokens_priority":4e-8,"cache_creation_input_token_cost_above_272k_tokens_priority":5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"databricks/databricks-gpt-6-luna","object":"model","created":1790399645,"owned_by":"databricks","model_name":"databricks-gpt-6-luna","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 family, bringing strong reasoning and agentic capability at the lowest cost in the lineup. This model supports multimodal (text and image) inputs and a long context window. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":5e-7,"input_dbu_cost_per_token":1.429e-6,"output_dbu_cost_per_token":7.143e-6,"cache_read_input_token_cost":1e-8,"cache_creation_input_token_cost":1.25e-7,"input_cost_per_token_above_272k_tokens":2e-7,"output_cost_per_token_above_272k_tokens":7.5e-7,"cache_creation_input_token_cost_priority":2.5e-7,"cache_read_input_token_cost_above_272k_tokens":2e-8,"input_cost_per_token_above_272k_tokens_priority":4e-7,"output_cost_per_token_above_272k_tokens_priority":1.5e-6,"cache_creation_input_token_cost_above_272k_tokens":2.5e-7,"cache_read_input_token_cost_above_272k_tokens_priority":4e-8,"cache_creation_input_token_cost_above_272k_tokens_priority":5e-7},"list_pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":5e-7,"input_dbu_cost_per_token":1.429e-6,"output_dbu_cost_per_token":7.143e-6,"cache_read_input_token_cost":1e-8,"cache_creation_input_token_cost":1.25e-7,"input_cost_per_token_above_272k_tokens":2e-7,"output_cost_per_token_above_272k_tokens":7.5e-7,"cache_creation_input_token_cost_priority":2.5e-7,"cache_read_input_token_cost_above_272k_tokens":2e-8,"input_cost_per_token_above_272k_tokens_priority":4e-7,"output_cost_per_token_above_272k_tokens_priority":1.5e-6,"cache_creation_input_token_cost_above_272k_tokens":2.5e-7,"cache_read_input_token_cost_above_272k_tokens_priority":4e-8,"cache_creation_input_token_cost_above_272k_tokens_priority":5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"azure/gpt-6-luna@eu","object":"model","created":1790188180,"owned_by":"azure","model_name":"gpt-6-luna","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.2e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":1.2e-8,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":1.5e-7,"input_cost_per_token_above_272k_tokens":2.4e-7,"output_cost_per_token_above_272k_tokens":9e-7,"cache_read_input_token_cost_above_272k_tokens":2.4e-8,"cache_creation_input_token_cost_above_272k_tokens":3e-7},"list_pricing":{"input_cost_per_token":1.2e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":1.2e-8,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":1.5e-7,"input_cost_per_token_above_272k_tokens":2.4e-7,"output_cost_per_token_above_272k_tokens":9e-7,"cache_read_input_token_cost_above_272k_tokens":2.4e-8,"cache_creation_input_token_cost_above_272k_tokens":3e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"azure/gpt-6-luna","object":"model","created":1790188180,"owned_by":"azure","model_name":"gpt-6-luna","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":1e-8,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":1.25e-7,"input_cost_per_token_above_272k_tokens":2e-7,"output_cost_per_token_above_272k_tokens":7.5e-7,"cache_read_input_token_cost_above_272k_tokens":2e-8,"cache_creation_input_token_cost_above_272k_tokens":2.5e-7},"list_pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":1e-8,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":1.25e-7,"input_cost_per_token_above_272k_tokens":2e-7,"output_cost_per_token_above_272k_tokens":7.5e-7,"cache_read_input_token_cost_above_272k_tokens":2e-8,"cache_creation_input_token_cost_above_272k_tokens":2.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"azure/gpt-6-luna@us","object":"model","created":1790188180,"owned_by":"azure","model_name":"gpt-6-luna","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.1e-7,"output_cost_per_token":5.5e-7,"cache_read_input_token_cost":1.1000000000000001e-8,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":1.375e-7,"input_cost_per_token_above_272k_tokens":2.2e-7,"output_cost_per_token_above_272k_tokens":8.25e-7,"cache_read_input_token_cost_above_272k_tokens":2.2000000000000002e-8,"cache_creation_input_token_cost_above_272k_tokens":2.75e-7},"list_pricing":{"input_cost_per_token":1.1e-7,"output_cost_per_token":5.5e-7,"cache_read_input_token_cost":1.1000000000000001e-8,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":1.375e-7,"input_cost_per_token_above_272k_tokens":2.2e-7,"output_cost_per_token_above_272k_tokens":8.25e-7,"cache_read_input_token_cost_above_272k_tokens":2.2000000000000002e-8,"cache_creation_input_token_cost_above_272k_tokens":2.75e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/openai.gpt-6-luna","object":"model","created":1790184068,"owned_by":"amazon","model_name":"openai.gpt-6-luna","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":1e-8,"cache_creation_input_token_cost":1.25e-7,"input_cost_per_token_above_272k_tokens":2e-7,"output_cost_per_token_above_272k_tokens":7.5e-7,"cache_read_input_token_cost_above_272k_tokens":2e-8,"cache_creation_input_token_cost_above_272k_tokens":2.5e-7},"list_pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":1e-8,"cache_creation_input_token_cost":1.25e-7,"input_cost_per_token_above_272k_tokens":2e-7,"output_cost_per_token_above_272k_tokens":7.5e-7,"cache_read_input_token_cost_above_272k_tokens":2e-8,"cache_creation_input_token_cost_above_272k_tokens":2.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"amazon/openai.gpt-6-luna@us","object":"model","created":1790184068,"owned_by":"amazon","model_name":"openai.gpt-6-luna","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":1e-8,"cache_creation_input_token_cost":1.25e-7,"input_cost_per_token_above_272k_tokens":2e-7,"output_cost_per_token_above_272k_tokens":7.5e-7,"cache_read_input_token_cost_above_272k_tokens":2e-8,"cache_creation_input_token_cost_above_272k_tokens":2.5e-7},"list_pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":1e-8,"cache_creation_input_token_cost":1.25e-7,"input_cost_per_token_above_272k_tokens":2e-7,"output_cost_per_token_above_272k_tokens":7.5e-7,"cache_read_input_token_cost_above_272k_tokens":2e-8,"cache_creation_input_token_cost_above_272k_tokens":2.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null},{"id":"openai/gpt-6-luna","object":"model","created":1790100786,"owned_by":"openai","model_name":"gpt-6-luna","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol.","source":null,"capabilities":{"input_modalities":["file","image","text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":5e-7,"input_cost_per_token_flex":5e-8,"output_cost_per_token_flex":2.5e-7,"cache_read_input_token_cost":1e-8,"input_cost_per_token_batches":5e-8,"input_cost_per_token_priority":2e-7,"output_cost_per_token_batches":2.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"input_cost_per_token_decisions":1e-7,"output_cost_per_token_priority":1e-6,"cache_creation_input_token_cost":1.25e-7,"output_cost_per_token_decisions":0.0,"cache_read_input_token_cost_flex":5e-9,"cache_read_input_token_cost_batches":5e-9,"cache_creation_input_token_cost_flex":6.25e-8,"cache_read_input_token_cost_priority":2e-8,"cache_read_input_token_cost_decisions":1e-8,"input_cost_per_token_above_272k_tokens":2e-7,"output_cost_per_token_above_272k_tokens":7.5e-7,"cache_creation_input_token_cost_priority":2.5e-7,"cache_creation_input_token_cost_decisions":1.25e-7,"cache_creation_input_token_cost_above_12hr":2.5e-7,"input_cost_per_token_above_272k_tokens_flex":1e-7,"output_cost_per_token_above_272k_tokens_flex":3.75e-7,"cache_read_input_token_cost_above_272k_tokens":2e-8,"cache_creation_input_token_cost_above_12hr_flex":1.25e-7,"input_cost_per_token_above_272k_tokens_priority":4e-7,"input_cost_per_token_above_272k_tokens_decisions":2e-7,"output_cost_per_token_above_272k_tokens_priority":1.5e-6,"cache_creation_input_token_cost_above_272k_tokens":2.5e-7,"output_cost_per_token_above_272k_tokens_decisions":0.0,"cache_read_input_token_cost_above_272k_tokens_flex":1e-8,"cache_creation_input_token_cost_above_12hr_priority":5e-7,"cache_creation_input_token_cost_above_272k_tokens_flex":1.25e-7,"cache_read_input_token_cost_above_272k_tokens_priority":4e-8,"cache_read_input_token_cost_above_272k_tokens_decisions":2e-8,"cache_creation_input_token_cost_above_272k_tokens_priority":5e-7,"cache_creation_input_token_cost_above_272k_tokens_decisions":2.5e-7,"cache_creation_input_token_cost_above_12hr_above_272k_tokens":5e-7,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_flex":2.5e-7,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_priority":1e-6},"list_pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":5e-7,"input_cost_per_token_flex":5e-8,"output_cost_per_token_flex":2.5e-7,"cache_read_input_token_cost":1e-8,"input_cost_per_token_batches":5e-8,"input_cost_per_token_priority":2e-7,"output_cost_per_token_batches":2.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"input_cost_per_token_decisions":1e-7,"output_cost_per_token_priority":1e-6,"cache_creation_input_token_cost":1.25e-7,"output_cost_per_token_decisions":0.0,"cache_read_input_token_cost_flex":5e-9,"cache_read_input_token_cost_batches":5e-9,"cache_creation_input_token_cost_flex":6.25e-8,"cache_read_input_token_cost_priority":2e-8,"cache_read_input_token_cost_decisions":1e-8,"input_cost_per_token_above_272k_tokens":2e-7,"output_cost_per_token_above_272k_tokens":7.5e-7,"cache_creation_input_token_cost_priority":2.5e-7,"cache_creation_input_token_cost_decisions":1.25e-7,"cache_creation_input_token_cost_above_12hr":2.5e-7,"input_cost_per_token_above_272k_tokens_flex":1e-7,"output_cost_per_token_above_272k_tokens_flex":3.75e-7,"cache_read_input_token_cost_above_272k_tokens":2e-8,"cache_creation_input_token_cost_above_12hr_flex":1.25e-7,"input_cost_per_token_above_272k_tokens_priority":4e-7,"input_cost_per_token_above_272k_tokens_decisions":2e-7,"output_cost_per_token_above_272k_tokens_priority":1.5e-6,"cache_creation_input_token_cost_above_272k_tokens":2.5e-7,"output_cost_per_token_above_272k_tokens_decisions":0.0,"cache_read_input_token_cost_above_272k_tokens_flex":1e-8,"cache_creation_input_token_cost_above_12hr_priority":5e-7,"cache_creation_input_token_cost_above_272k_tokens_flex":1.25e-7,"cache_read_input_token_cost_above_272k_tokens_priority":4e-8,"cache_read_input_token_cost_above_272k_tokens_decisions":2e-8,"cache_creation_input_token_cost_above_272k_tokens_priority":5e-7,"cache_creation_input_token_cost_above_272k_tokens_decisions":2.5e-7,"cache_creation_input_token_cost_above_12hr_above_272k_tokens":5e-7,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_flex":2.5e-7,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_priority":1e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":8},{"id":"gpt-6-sol","object":"model","created":1790399645,"owned_by":"openai","mode":"chat","context_length":1050000,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"input_cost_per_token_flex":1e-6,"output_cost_per_token_flex":5e-6,"cache_read_input_token_cost":2e-7,"input_cost_per_token_batches":1e-6,"input_cost_per_token_priority":4e-6,"output_cost_per_token_batches":5e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"output_cost_per_token_priority":0.00002,"cache_creation_input_token_cost":2.5e-6,"cache_read_input_token_cost_flex":1e-7,"cache_read_input_token_cost_batches":1e-7,"cache_creation_input_token_cost_flex":1.25e-6,"cache_read_input_token_cost_priority":4e-7,"input_cost_per_token_above_272k_tokens":4e-6,"output_cost_per_token_above_272k_tokens":0.000015,"cache_creation_input_token_cost_priority":5e-6,"cache_creation_input_token_cost_above_12hr":5e-6,"input_cost_per_token_above_272k_tokens_flex":2e-6,"output_cost_per_token_above_272k_tokens_flex":7.5e-6,"cache_read_input_token_cost_above_272k_tokens":4e-7,"cache_creation_input_token_cost_above_12hr_flex":2.5e-6,"input_cost_per_token_above_272k_tokens_priority":8e-6,"output_cost_per_token_above_272k_tokens_priority":0.00003,"cache_creation_input_token_cost_above_272k_tokens":5e-6,"cache_read_input_token_cost_above_272k_tokens_flex":2e-7,"cache_creation_input_token_cost_above_12hr_priority":0.00001,"cache_creation_input_token_cost_above_272k_tokens_flex":2.5e-6,"cache_read_input_token_cost_above_272k_tokens_priority":8e-7,"cache_creation_input_token_cost_above_272k_tokens_priority":0.00001,"cache_creation_input_token_cost_above_12hr_above_272k_tokens":0.00001,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_flex":5e-6,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_priority":0.00002},"pricing_endpoint":"openai/gpt-6-sol","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"databricks/databricks-gpt-6-sol@eu","object":"model","created":1790399645,"owned_by":"databricks","model_name":"databricks-gpt-6-sol","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-6 Sol is OpenAI's flagship model in the GPT-6 family, delivering state-of-the-art performance on agentic coding, long-horizon reasoning, and complex tool use. This model supports multimodal (text and image) inputs and a long context window. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"input_dbu_cost_per_token":0.000028571,"output_dbu_cost_per_token":0.00014286,"cache_read_input_token_cost":2e-7,"cache_creation_input_token_cost":2.5e-6,"input_cost_per_token_above_272k_tokens":4e-6,"output_cost_per_token_above_272k_tokens":0.000015,"cache_creation_input_token_cost_priority":5e-6,"cache_read_input_token_cost_above_272k_tokens":4e-7,"input_cost_per_token_above_272k_tokens_priority":8e-6,"output_cost_per_token_above_272k_tokens_priority":0.00003,"cache_creation_input_token_cost_above_272k_tokens":5e-6,"cache_read_input_token_cost_above_272k_tokens_priority":8e-7,"cache_creation_input_token_cost_above_272k_tokens_priority":0.00001},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"input_dbu_cost_per_token":0.000028571,"output_dbu_cost_per_token":0.00014286,"cache_read_input_token_cost":2e-7,"cache_creation_input_token_cost":2.5e-6,"input_cost_per_token_above_272k_tokens":4e-6,"output_cost_per_token_above_272k_tokens":0.000015,"cache_creation_input_token_cost_priority":5e-6,"cache_read_input_token_cost_above_272k_tokens":4e-7,"input_cost_per_token_above_272k_tokens_priority":8e-6,"output_cost_per_token_above_272k_tokens_priority":0.00003,"cache_creation_input_token_cost_above_272k_tokens":5e-6,"cache_read_input_token_cost_above_272k_tokens_priority":8e-7,"cache_creation_input_token_cost_above_272k_tokens_priority":0.00001},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"databricks/databricks-gpt-6-sol","object":"model","created":1790399645,"owned_by":"databricks","model_name":"databricks-gpt-6-sol","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-6 Sol is OpenAI's flagship model in the GPT-6 family, delivering state-of-the-art performance on agentic coding, long-horizon reasoning, and complex tool use. This model supports multimodal (text and image) inputs and a long context window. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"input_dbu_cost_per_token":0.000028571,"output_dbu_cost_per_token":0.00014286,"cache_read_input_token_cost":2e-7,"cache_creation_input_token_cost":2.5e-6,"input_cost_per_token_above_272k_tokens":4e-6,"output_cost_per_token_above_272k_tokens":0.000015,"cache_creation_input_token_cost_priority":5e-6,"cache_read_input_token_cost_above_272k_tokens":4e-7,"input_cost_per_token_above_272k_tokens_priority":8e-6,"output_cost_per_token_above_272k_tokens_priority":0.00003,"cache_creation_input_token_cost_above_272k_tokens":5e-6,"cache_read_input_token_cost_above_272k_tokens_priority":8e-7,"cache_creation_input_token_cost_above_272k_tokens_priority":0.00001},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"input_dbu_cost_per_token":0.000028571,"output_dbu_cost_per_token":0.00014286,"cache_read_input_token_cost":2e-7,"cache_creation_input_token_cost":2.5e-6,"input_cost_per_token_above_272k_tokens":4e-6,"output_cost_per_token_above_272k_tokens":0.000015,"cache_creation_input_token_cost_priority":5e-6,"cache_read_input_token_cost_above_272k_tokens":4e-7,"input_cost_per_token_above_272k_tokens_priority":8e-6,"output_cost_per_token_above_272k_tokens_priority":0.00003,"cache_creation_input_token_cost_above_272k_tokens":5e-6,"cache_read_input_token_cost_above_272k_tokens_priority":8e-7,"cache_creation_input_token_cost_above_272k_tokens_priority":0.00001},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"azure/gpt-6-sol@eu","object":"model","created":1790188180,"owned_by":"azure","model_name":"gpt-6-sol","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT-6 Luna tier.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2.4e-6,"output_cost_per_token":0.000012,"input_cost_per_token_flex":1.2e-6,"output_cost_per_token_flex":6e-6,"cache_read_input_token_cost":2.4e-7,"input_cost_per_token_priority":4.8e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.000024,"cache_creation_input_token_cost":3e-6,"cache_read_input_token_cost_flex":1.2e-7,"cache_creation_input_token_cost_flex":1.5e-6,"cache_read_input_token_cost_priority":4.8e-7,"input_cost_per_token_above_272k_tokens":4.8e-6,"output_cost_per_token_above_272k_tokens":0.000018,"cache_creation_input_token_cost_priority":6e-6,"input_cost_per_token_above_272k_tokens_flex":2.4e-6,"output_cost_per_token_above_272k_tokens_flex":9e-6,"cache_read_input_token_cost_above_272k_tokens":4.8e-7,"input_cost_per_token_above_272k_tokens_priority":9.6e-6,"output_cost_per_token_above_272k_tokens_priority":0.000036,"cache_creation_input_token_cost_above_272k_tokens":6e-6,"cache_read_input_token_cost_above_272k_tokens_flex":2.4e-7,"cache_creation_input_token_cost_above_272k_tokens_flex":3e-6,"cache_read_input_token_cost_above_272k_tokens_priority":9.6e-7,"cache_creation_input_token_cost_above_272k_tokens_priority":0.000012},"list_pricing":{"input_cost_per_token":2.4e-6,"output_cost_per_token":0.000012,"input_cost_per_token_flex":1.2e-6,"output_cost_per_token_flex":6e-6,"cache_read_input_token_cost":2.4e-7,"input_cost_per_token_priority":4.8e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.000024,"cache_creation_input_token_cost":3e-6,"cache_read_input_token_cost_flex":1.2e-7,"cache_creation_input_token_cost_flex":1.5e-6,"cache_read_input_token_cost_priority":4.8e-7,"input_cost_per_token_above_272k_tokens":4.8e-6,"output_cost_per_token_above_272k_tokens":0.000018,"cache_creation_input_token_cost_priority":6e-6,"input_cost_per_token_above_272k_tokens_flex":2.4e-6,"output_cost_per_token_above_272k_tokens_flex":9e-6,"cache_read_input_token_cost_above_272k_tokens":4.8e-7,"input_cost_per_token_above_272k_tokens_priority":9.6e-6,"output_cost_per_token_above_272k_tokens_priority":0.000036,"cache_creation_input_token_cost_above_272k_tokens":6e-6,"cache_read_input_token_cost_above_272k_tokens_flex":2.4e-7,"cache_creation_input_token_cost_above_272k_tokens_flex":3e-6,"cache_read_input_token_cost_above_272k_tokens_priority":9.6e-7,"cache_creation_input_token_cost_above_272k_tokens_priority":0.000012},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"azure/gpt-6-sol","object":"model","created":1790188180,"owned_by":"azure","model_name":"gpt-6-sol","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT-6 Luna tier.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"input_cost_per_token_flex":1e-6,"output_cost_per_token_flex":5e-6,"cache_read_input_token_cost":2e-7,"input_cost_per_token_priority":4e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.00002,"cache_creation_input_token_cost":2.5e-6,"cache_read_input_token_cost_flex":1e-7,"cache_creation_input_token_cost_flex":1.25e-6,"cache_read_input_token_cost_priority":4e-7,"input_cost_per_token_above_272k_tokens":4e-6,"output_cost_per_token_above_272k_tokens":0.000015,"cache_creation_input_token_cost_priority":5e-6,"input_cost_per_token_above_272k_tokens_flex":2e-6,"output_cost_per_token_above_272k_tokens_flex":7.5e-6,"cache_read_input_token_cost_above_272k_tokens":4e-7,"input_cost_per_token_above_272k_tokens_priority":8e-6,"output_cost_per_token_above_272k_tokens_priority":0.00003,"cache_creation_input_token_cost_above_272k_tokens":5e-6,"cache_read_input_token_cost_above_272k_tokens_flex":2e-7,"cache_creation_input_token_cost_above_272k_tokens_flex":2.5e-6,"cache_read_input_token_cost_above_272k_tokens_priority":8e-7,"cache_creation_input_token_cost_above_272k_tokens_priority":0.00001},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"input_cost_per_token_flex":1e-6,"output_cost_per_token_flex":5e-6,"cache_read_input_token_cost":2e-7,"input_cost_per_token_priority":4e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.00002,"cache_creation_input_token_cost":2.5e-6,"cache_read_input_token_cost_flex":1e-7,"cache_creation_input_token_cost_flex":1.25e-6,"cache_read_input_token_cost_priority":4e-7,"input_cost_per_token_above_272k_tokens":4e-6,"output_cost_per_token_above_272k_tokens":0.000015,"cache_creation_input_token_cost_priority":5e-6,"input_cost_per_token_above_272k_tokens_flex":2e-6,"output_cost_per_token_above_272k_tokens_flex":7.5e-6,"cache_read_input_token_cost_above_272k_tokens":4e-7,"input_cost_per_token_above_272k_tokens_priority":8e-6,"output_cost_per_token_above_272k_tokens_priority":0.00003,"cache_creation_input_token_cost_above_272k_tokens":5e-6,"cache_read_input_token_cost_above_272k_tokens_flex":2e-7,"cache_creation_input_token_cost_above_272k_tokens_flex":2.5e-6,"cache_read_input_token_cost_above_272k_tokens_priority":8e-7,"cache_creation_input_token_cost_above_272k_tokens_priority":0.00001},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"azure/gpt-6-sol@us","object":"model","created":1790188180,"owned_by":"azure","model_name":"gpt-6-sol","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT-6 Luna tier.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2.2e-6,"output_cost_per_token":0.000011000000000000001,"input_cost_per_token_flex":1.1e-6,"output_cost_per_token_flex":5.500000000000001e-6,"cache_read_input_token_cost":2.2e-7,"input_cost_per_token_priority":4.4e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.000022000000000000003,"cache_creation_input_token_cost":2.7500000000000004e-6,"cache_read_input_token_cost_flex":1.1e-7,"cache_creation_input_token_cost_flex":1.3750000000000002e-6,"cache_read_input_token_cost_priority":4.4e-7,"input_cost_per_token_above_272k_tokens":4.4e-6,"output_cost_per_token_above_272k_tokens":0.0000165,"cache_creation_input_token_cost_priority":5.500000000000001e-6,"input_cost_per_token_above_272k_tokens_flex":2.2e-6,"output_cost_per_token_above_272k_tokens_flex":8.25e-6,"cache_read_input_token_cost_above_272k_tokens":4.4e-7,"input_cost_per_token_above_272k_tokens_priority":8.8e-6,"output_cost_per_token_above_272k_tokens_priority":0.000033,"cache_creation_input_token_cost_above_272k_tokens":5.500000000000001e-6,"cache_read_input_token_cost_above_272k_tokens_flex":2.2e-7,"cache_creation_input_token_cost_above_272k_tokens_flex":2.7500000000000004e-6,"cache_read_input_token_cost_above_272k_tokens_priority":8.8e-7,"cache_creation_input_token_cost_above_272k_tokens_priority":0.000011000000000000001},"list_pricing":{"input_cost_per_token":2.2e-6,"output_cost_per_token":0.000011000000000000001,"input_cost_per_token_flex":1.1e-6,"output_cost_per_token_flex":5.500000000000001e-6,"cache_read_input_token_cost":2.2e-7,"input_cost_per_token_priority":4.4e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.000022000000000000003,"cache_creation_input_token_cost":2.7500000000000004e-6,"cache_read_input_token_cost_flex":1.1e-7,"cache_creation_input_token_cost_flex":1.3750000000000002e-6,"cache_read_input_token_cost_priority":4.4e-7,"input_cost_per_token_above_272k_tokens":4.4e-6,"output_cost_per_token_above_272k_tokens":0.0000165,"cache_creation_input_token_cost_priority":5.500000000000001e-6,"input_cost_per_token_above_272k_tokens_flex":2.2e-6,"output_cost_per_token_above_272k_tokens_flex":8.25e-6,"cache_read_input_token_cost_above_272k_tokens":4.4e-7,"input_cost_per_token_above_272k_tokens_priority":8.8e-6,"output_cost_per_token_above_272k_tokens_priority":0.000033,"cache_creation_input_token_cost_above_272k_tokens":5.500000000000001e-6,"cache_read_input_token_cost_above_272k_tokens_flex":2.2e-7,"cache_creation_input_token_cost_above_272k_tokens_flex":2.7500000000000004e-6,"cache_read_input_token_cost_above_272k_tokens_priority":8.8e-7,"cache_creation_input_token_cost_above_272k_tokens_priority":0.000011000000000000001},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/openai.gpt-6-sol","object":"model","created":1790184068,"owned_by":"amazon","model_name":"openai.gpt-6-sol","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"cache_read_input_token_cost":2e-7,"cache_creation_input_token_cost":2.5e-6,"input_cost_per_token_above_272k_tokens":4e-6,"output_cost_per_token_above_272k_tokens":0.000015,"cache_read_input_token_cost_above_272k_tokens":4e-7,"cache_creation_input_token_cost_above_272k_tokens":5e-6},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"cache_read_input_token_cost":2e-7,"cache_creation_input_token_cost":2.5e-6,"input_cost_per_token_above_272k_tokens":4e-6,"output_cost_per_token_above_272k_tokens":0.000015,"cache_read_input_token_cost_above_272k_tokens":4e-7,"cache_creation_input_token_cost_above_272k_tokens":5e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"amazon/openai.gpt-6-sol@us","object":"model","created":1790184068,"owned_by":"amazon","model_name":"openai.gpt-6-sol","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"cache_read_input_token_cost":2e-7,"cache_creation_input_token_cost":2.5e-6,"input_cost_per_token_above_272k_tokens":4e-6,"output_cost_per_token_above_272k_tokens":0.000015,"cache_read_input_token_cost_above_272k_tokens":4e-7,"cache_creation_input_token_cost_above_272k_tokens":5e-6},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"cache_read_input_token_cost":2e-7,"cache_creation_input_token_cost":2.5e-6,"input_cost_per_token_above_272k_tokens":4e-6,"output_cost_per_token_above_272k_tokens":0.000015,"cache_read_input_token_cost_above_272k_tokens":4e-7,"cache_creation_input_token_cost_above_272k_tokens":5e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null},{"id":"openai/gpt-6-sol","object":"model","created":1790100775,"owned_by":"openai","model_name":"gpt-6-sol","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT-6 Luna tier.","source":null,"capabilities":{"input_modalities":["file","image","text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"input_cost_per_token_flex":1e-6,"output_cost_per_token_flex":5e-6,"cache_read_input_token_cost":2e-7,"input_cost_per_token_batches":1e-6,"input_cost_per_token_priority":4e-6,"output_cost_per_token_batches":5e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"output_cost_per_token_priority":0.00002,"cache_creation_input_token_cost":2.5e-6,"cache_read_input_token_cost_flex":1e-7,"cache_read_input_token_cost_batches":1e-7,"cache_creation_input_token_cost_flex":1.25e-6,"cache_read_input_token_cost_priority":4e-7,"input_cost_per_token_above_272k_tokens":4e-6,"output_cost_per_token_above_272k_tokens":0.000015,"cache_creation_input_token_cost_priority":5e-6,"cache_creation_input_token_cost_above_12hr":5e-6,"input_cost_per_token_above_272k_tokens_flex":2e-6,"output_cost_per_token_above_272k_tokens_flex":7.5e-6,"cache_read_input_token_cost_above_272k_tokens":4e-7,"cache_creation_input_token_cost_above_12hr_flex":2.5e-6,"input_cost_per_token_above_272k_tokens_priority":8e-6,"output_cost_per_token_above_272k_tokens_priority":0.00003,"cache_creation_input_token_cost_above_272k_tokens":5e-6,"cache_read_input_token_cost_above_272k_tokens_flex":2e-7,"cache_creation_input_token_cost_above_12hr_priority":0.00001,"cache_creation_input_token_cost_above_272k_tokens_flex":2.5e-6,"cache_read_input_token_cost_above_272k_tokens_priority":8e-7,"cache_creation_input_token_cost_above_272k_tokens_priority":0.00001,"cache_creation_input_token_cost_above_12hr_above_272k_tokens":0.00001,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_flex":5e-6,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_priority":0.00002},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"input_cost_per_token_flex":1e-6,"output_cost_per_token_flex":5e-6,"cache_read_input_token_cost":2e-7,"input_cost_per_token_batches":1e-6,"input_cost_per_token_priority":4e-6,"output_cost_per_token_batches":5e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"output_cost_per_token_priority":0.00002,"cache_creation_input_token_cost":2.5e-6,"cache_read_input_token_cost_flex":1e-7,"cache_read_input_token_cost_batches":1e-7,"cache_creation_input_token_cost_flex":1.25e-6,"cache_read_input_token_cost_priority":4e-7,"input_cost_per_token_above_272k_tokens":4e-6,"output_cost_per_token_above_272k_tokens":0.000015,"cache_creation_input_token_cost_priority":5e-6,"cache_creation_input_token_cost_above_12hr":5e-6,"input_cost_per_token_above_272k_tokens_flex":2e-6,"output_cost_per_token_above_272k_tokens_flex":7.5e-6,"cache_read_input_token_cost_above_272k_tokens":4e-7,"cache_creation_input_token_cost_above_12hr_flex":2.5e-6,"input_cost_per_token_above_272k_tokens_priority":8e-6,"output_cost_per_token_above_272k_tokens_priority":0.00003,"cache_creation_input_token_cost_above_272k_tokens":5e-6,"cache_read_input_token_cost_above_272k_tokens_flex":2e-7,"cache_creation_input_token_cost_above_12hr_priority":0.00001,"cache_creation_input_token_cost_above_272k_tokens_flex":2.5e-6,"cache_read_input_token_cost_above_272k_tokens_priority":8e-7,"cache_creation_input_token_cost_above_272k_tokens_priority":0.00001,"cache_creation_input_token_cost_above_12hr_above_272k_tokens":0.00001,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_flex":5e-6,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_priority":0.00002},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":8},{"id":"~claude-opus-latest","object":"model","created":1790399645,"owned_by":"anthropic","mode":"chat","context_length":1000000,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4e-6,"output_cost_per_token":0.00002,"provider_specific_entry":{"us":1.1,"fast":2.0},"cache_read_input_token_cost":2e-7,"input_cost_per_token_batches":2e-6,"output_cost_per_token_batches":0.00001,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":5e-6,"cache_read_input_token_cost_batches":1e-7,"cache_creation_input_token_cost_above_1hr":8e-6},"pricing_endpoint":"anthropic/claude-opus-5-5","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":"claude-opus-5.5","endpoints":[{"id":"databricks/databricks-claude-opus-5-5@eu","object":"model","created":1790399645,"owned_by":"databricks","model_name":"databricks-claude-opus-5-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Opus 5.5 is Anthropic's most intelligent model for complex reasoning, coding, and agentic workflows. It uses adaptive thinking to dynamically allocate reasoning effort and supports large-context tasks such as deep document analysis and multi-step tool use. This model is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4e-6,"output_cost_per_token":0.00002,"input_dbu_cost_per_token":0.000057143,"output_dbu_cost_per_token":0.000285714,"cache_read_input_token_cost":4e-7,"cache_creation_input_token_cost":5e-6,"cache_creation_input_token_cost_above_1hr":8e-6},"list_pricing":{"input_cost_per_token":4e-6,"output_cost_per_token":0.00002,"input_dbu_cost_per_token":0.000057143,"output_dbu_cost_per_token":0.000285714,"cache_read_input_token_cost":4e-7,"cache_creation_input_token_cost":5e-6,"cache_creation_input_token_cost_above_1hr":8e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"databricks/databricks-claude-opus-5-5","object":"model","created":1790399645,"owned_by":"databricks","model_name":"databricks-claude-opus-5-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Opus 5.5 is Anthropic's most intelligent model for complex reasoning, coding, and agentic workflows. It uses adaptive thinking to dynamically allocate reasoning effort and supports large-context tasks such as deep document analysis and multi-step tool use. This model is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4e-6,"output_cost_per_token":0.00002,"input_dbu_cost_per_token":0.000057143,"output_dbu_cost_per_token":0.000285714,"cache_read_input_token_cost":4e-7,"cache_creation_input_token_cost":5e-6,"cache_creation_input_token_cost_above_1hr":8e-6},"list_pricing":{"input_cost_per_token":4e-6,"output_cost_per_token":0.00002,"input_dbu_cost_per_token":0.000057143,"output_dbu_cost_per_token":0.000285714,"cache_read_input_token_cost":4e-7,"cache_creation_input_token_cost":5e-6,"cache_creation_input_token_cost_above_1hr":8e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"deepinfra/anthropic/claude-opus-5-5","object":"model","created":1790184068,"owned_by":"deepinfra","model_name":"anthropic/claude-opus-5-5","context_length":1000000,"max_input_tokens":null,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4e-6,"output_cost_per_token":0.00002,"cache_read_input_token_cost":2.0000000000000002e-7},"list_pricing":{"input_cost_per_token":4e-6,"output_cost_per_token":0.00002,"cache_read_input_token_cost":2.0000000000000002e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null},{"id":"amazon/anthropic.claude-opus-5-5@eu","object":"model","created":1790094732,"owned_by":"amazon","model_name":"anthropic.claude-opus-5-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4.4e-6,"output_cost_per_token":0.000022000000000000003,"cache_read_input_token_cost":2.2e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":5.500000000000001e-6,"cache_creation_input_token_cost_above_1hr":8.8e-6},"list_pricing":{"input_cost_per_token":4.4e-6,"output_cost_per_token":0.000022000000000000003,"cache_read_input_token_cost":2.2e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":5.500000000000001e-6,"cache_creation_input_token_cost_above_1hr":8.8e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/anthropic.claude-opus-5-5","object":"model","created":1790094732,"owned_by":"amazon","model_name":"anthropic.claude-opus-5-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4e-6,"output_cost_per_token":0.00002,"cache_read_input_token_cost":2e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":5e-6,"cache_creation_input_token_cost_above_1hr":8e-6},"list_pricing":{"input_cost_per_token":4e-6,"output_cost_per_token":0.00002,"cache_read_input_token_cost":2e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":5e-6,"cache_creation_input_token_cost_above_1hr":8e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/anthropic.claude-opus-5-5@us","object":"model","created":1790094732,"owned_by":"amazon","model_name":"anthropic.claude-opus-5-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4.4e-6,"output_cost_per_token":0.000022000000000000003,"cache_read_input_token_cost":2.2e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":5.500000000000001e-6,"cache_creation_input_token_cost_above_1hr":8.8e-6},"list_pricing":{"input_cost_per_token":4.4e-6,"output_cost_per_token":0.000022000000000000003,"cache_read_input_token_cost":2.2e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":5.500000000000001e-6,"cache_creation_input_token_cost_above_1hr":8.8e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"anthropic/claude-opus-5-5","object":"model","created":1790094732,"owned_by":"anthropic","model_name":"claude-opus-5-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4e-6,"output_cost_per_token":0.00002,"provider_specific_entry":{"us":1.1,"fast":2.0},"cache_read_input_token_cost":2e-7,"input_cost_per_token_batches":2e-6,"output_cost_per_token_batches":0.00001,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":5e-6,"cache_read_input_token_cost_batches":1e-7,"cache_creation_input_token_cost_above_1hr":8e-6},"list_pricing":{"input_cost_per_token":4e-6,"output_cost_per_token":0.00002,"provider_specific_entry":{"us":1.1,"fast":2.0},"cache_read_input_token_cost":2e-7,"input_cost_per_token_batches":2e-6,"output_cost_per_token_batches":0.00001,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":5e-6,"cache_read_input_token_cost_batches":1e-7,"cache_creation_input_token_cost_above_1hr":8e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null},{"id":"vertex/claude-opus-5-5@eu","object":"model","created":1790094732,"owned_by":"vertex","model_name":"claude-opus-5-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4.4e-6,"output_cost_per_token":0.000022000000000000003,"cache_read_input_token_cost":2.2e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":5.500000000000001e-6,"cache_creation_input_token_cost_above_1hr":8.8e-6},"list_pricing":{"input_cost_per_token":4.4e-6,"output_cost_per_token":0.000022000000000000003,"cache_read_input_token_cost":2.2e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":5.500000000000001e-6,"cache_creation_input_token_cost_above_1hr":8.8e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"vertex/claude-opus-5-5","object":"model","created":1790094732,"owned_by":"vertex","model_name":"claude-opus-5-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4e-6,"output_cost_per_token":0.00002,"cache_read_input_token_cost":2e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":5e-6,"cache_creation_input_token_cost_above_1hr":8e-6},"list_pricing":{"input_cost_per_token":4e-6,"output_cost_per_token":0.00002,"cache_read_input_token_cost":2e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":5e-6,"cache_creation_input_token_cost_above_1hr":8e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"vertex/claude-opus-5-5@us","object":"model","created":1790094732,"owned_by":"vertex","model_name":"claude-opus-5-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4.4e-6,"output_cost_per_token":0.000022000000000000003,"cache_read_input_token_cost":2.2e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":5.500000000000001e-6,"cache_creation_input_token_cost_above_1hr":8.8e-6},"list_pricing":{"input_cost_per_token":4.4e-6,"output_cost_per_token":0.000022000000000000003,"cache_read_input_token_cost":2.2e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":5.500000000000001e-6,"cache_creation_input_token_cost_above_1hr":8.8e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":10},{"id":"~gpt-luna-latest","object":"model","created":1790399645,"owned_by":"openai","mode":"chat","context_length":1050000,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":5e-7,"input_cost_per_token_flex":5e-8,"output_cost_per_token_flex":2.5e-7,"cache_read_input_token_cost":1e-8,"input_cost_per_token_batches":5e-8,"input_cost_per_token_priority":2e-7,"output_cost_per_token_batches":2.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"input_cost_per_token_decisions":1e-7,"output_cost_per_token_priority":1e-6,"cache_creation_input_token_cost":1.25e-7,"output_cost_per_token_decisions":0.0,"cache_read_input_token_cost_flex":5e-9,"cache_read_input_token_cost_batches":5e-9,"cache_creation_input_token_cost_flex":6.25e-8,"cache_read_input_token_cost_priority":2e-8,"cache_read_input_token_cost_decisions":1e-8,"input_cost_per_token_above_272k_tokens":2e-7,"output_cost_per_token_above_272k_tokens":7.5e-7,"cache_creation_input_token_cost_priority":2.5e-7,"cache_creation_input_token_cost_decisions":1.25e-7,"cache_creation_input_token_cost_above_12hr":2.5e-7,"input_cost_per_token_above_272k_tokens_flex":1e-7,"output_cost_per_token_above_272k_tokens_flex":3.75e-7,"cache_read_input_token_cost_above_272k_tokens":2e-8,"cache_creation_input_token_cost_above_12hr_flex":1.25e-7,"input_cost_per_token_above_272k_tokens_priority":4e-7,"input_cost_per_token_above_272k_tokens_decisions":2e-7,"output_cost_per_token_above_272k_tokens_priority":1.5e-6,"cache_creation_input_token_cost_above_272k_tokens":2.5e-7,"output_cost_per_token_above_272k_tokens_decisions":0.0,"cache_read_input_token_cost_above_272k_tokens_flex":1e-8,"cache_creation_input_token_cost_above_12hr_priority":5e-7,"cache_creation_input_token_cost_above_272k_tokens_flex":1.25e-7,"cache_read_input_token_cost_above_272k_tokens_priority":4e-8,"cache_read_input_token_cost_above_272k_tokens_decisions":2e-8,"cache_creation_input_token_cost_above_272k_tokens_priority":5e-7,"cache_creation_input_token_cost_above_272k_tokens_decisions":2.5e-7,"cache_creation_input_token_cost_above_12hr_above_272k_tokens":5e-7,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_flex":2.5e-7,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_priority":1e-6},"pricing_endpoint":"openai/gpt-6-luna","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":"gpt-6-luna","endpoints":[{"id":"databricks/databricks-gpt-6-luna@eu","object":"model","created":1790399645,"owned_by":"databricks","model_name":"databricks-gpt-6-luna","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 family, bringing strong reasoning and agentic capability at the lowest cost in the lineup. This model supports multimodal (text and image) inputs and a long context window. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":5e-7,"input_dbu_cost_per_token":1.429e-6,"output_dbu_cost_per_token":7.143e-6,"cache_read_input_token_cost":1e-8,"cache_creation_input_token_cost":1.25e-7,"input_cost_per_token_above_272k_tokens":2e-7,"output_cost_per_token_above_272k_tokens":7.5e-7,"cache_creation_input_token_cost_priority":2.5e-7,"cache_read_input_token_cost_above_272k_tokens":2e-8,"input_cost_per_token_above_272k_tokens_priority":4e-7,"output_cost_per_token_above_272k_tokens_priority":1.5e-6,"cache_creation_input_token_cost_above_272k_tokens":2.5e-7,"cache_read_input_token_cost_above_272k_tokens_priority":4e-8,"cache_creation_input_token_cost_above_272k_tokens_priority":5e-7},"list_pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":5e-7,"input_dbu_cost_per_token":1.429e-6,"output_dbu_cost_per_token":7.143e-6,"cache_read_input_token_cost":1e-8,"cache_creation_input_token_cost":1.25e-7,"input_cost_per_token_above_272k_tokens":2e-7,"output_cost_per_token_above_272k_tokens":7.5e-7,"cache_creation_input_token_cost_priority":2.5e-7,"cache_read_input_token_cost_above_272k_tokens":2e-8,"input_cost_per_token_above_272k_tokens_priority":4e-7,"output_cost_per_token_above_272k_tokens_priority":1.5e-6,"cache_creation_input_token_cost_above_272k_tokens":2.5e-7,"cache_read_input_token_cost_above_272k_tokens_priority":4e-8,"cache_creation_input_token_cost_above_272k_tokens_priority":5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"databricks/databricks-gpt-6-luna","object":"model","created":1790399645,"owned_by":"databricks","model_name":"databricks-gpt-6-luna","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 family, bringing strong reasoning and agentic capability at the lowest cost in the lineup. This model supports multimodal (text and image) inputs and a long context window. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":5e-7,"input_dbu_cost_per_token":1.429e-6,"output_dbu_cost_per_token":7.143e-6,"cache_read_input_token_cost":1e-8,"cache_creation_input_token_cost":1.25e-7,"input_cost_per_token_above_272k_tokens":2e-7,"output_cost_per_token_above_272k_tokens":7.5e-7,"cache_creation_input_token_cost_priority":2.5e-7,"cache_read_input_token_cost_above_272k_tokens":2e-8,"input_cost_per_token_above_272k_tokens_priority":4e-7,"output_cost_per_token_above_272k_tokens_priority":1.5e-6,"cache_creation_input_token_cost_above_272k_tokens":2.5e-7,"cache_read_input_token_cost_above_272k_tokens_priority":4e-8,"cache_creation_input_token_cost_above_272k_tokens_priority":5e-7},"list_pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":5e-7,"input_dbu_cost_per_token":1.429e-6,"output_dbu_cost_per_token":7.143e-6,"cache_read_input_token_cost":1e-8,"cache_creation_input_token_cost":1.25e-7,"input_cost_per_token_above_272k_tokens":2e-7,"output_cost_per_token_above_272k_tokens":7.5e-7,"cache_creation_input_token_cost_priority":2.5e-7,"cache_read_input_token_cost_above_272k_tokens":2e-8,"input_cost_per_token_above_272k_tokens_priority":4e-7,"output_cost_per_token_above_272k_tokens_priority":1.5e-6,"cache_creation_input_token_cost_above_272k_tokens":2.5e-7,"cache_read_input_token_cost_above_272k_tokens_priority":4e-8,"cache_creation_input_token_cost_above_272k_tokens_priority":5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"azure/gpt-6-luna@eu","object":"model","created":1790188180,"owned_by":"azure","model_name":"gpt-6-luna","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.2e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":1.2e-8,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":1.5e-7,"input_cost_per_token_above_272k_tokens":2.4e-7,"output_cost_per_token_above_272k_tokens":9e-7,"cache_read_input_token_cost_above_272k_tokens":2.4e-8,"cache_creation_input_token_cost_above_272k_tokens":3e-7},"list_pricing":{"input_cost_per_token":1.2e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":1.2e-8,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":1.5e-7,"input_cost_per_token_above_272k_tokens":2.4e-7,"output_cost_per_token_above_272k_tokens":9e-7,"cache_read_input_token_cost_above_272k_tokens":2.4e-8,"cache_creation_input_token_cost_above_272k_tokens":3e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"azure/gpt-6-luna","object":"model","created":1790188180,"owned_by":"azure","model_name":"gpt-6-luna","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":1e-8,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":1.25e-7,"input_cost_per_token_above_272k_tokens":2e-7,"output_cost_per_token_above_272k_tokens":7.5e-7,"cache_read_input_token_cost_above_272k_tokens":2e-8,"cache_creation_input_token_cost_above_272k_tokens":2.5e-7},"list_pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":1e-8,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":1.25e-7,"input_cost_per_token_above_272k_tokens":2e-7,"output_cost_per_token_above_272k_tokens":7.5e-7,"cache_read_input_token_cost_above_272k_tokens":2e-8,"cache_creation_input_token_cost_above_272k_tokens":2.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"azure/gpt-6-luna@us","object":"model","created":1790188180,"owned_by":"azure","model_name":"gpt-6-luna","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.1e-7,"output_cost_per_token":5.5e-7,"cache_read_input_token_cost":1.1000000000000001e-8,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":1.375e-7,"input_cost_per_token_above_272k_tokens":2.2e-7,"output_cost_per_token_above_272k_tokens":8.25e-7,"cache_read_input_token_cost_above_272k_tokens":2.2000000000000002e-8,"cache_creation_input_token_cost_above_272k_tokens":2.75e-7},"list_pricing":{"input_cost_per_token":1.1e-7,"output_cost_per_token":5.5e-7,"cache_read_input_token_cost":1.1000000000000001e-8,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":1.375e-7,"input_cost_per_token_above_272k_tokens":2.2e-7,"output_cost_per_token_above_272k_tokens":8.25e-7,"cache_read_input_token_cost_above_272k_tokens":2.2000000000000002e-8,"cache_creation_input_token_cost_above_272k_tokens":2.75e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/openai.gpt-6-luna","object":"model","created":1790184068,"owned_by":"amazon","model_name":"openai.gpt-6-luna","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":1e-8,"cache_creation_input_token_cost":1.25e-7,"input_cost_per_token_above_272k_tokens":2e-7,"output_cost_per_token_above_272k_tokens":7.5e-7,"cache_read_input_token_cost_above_272k_tokens":2e-8,"cache_creation_input_token_cost_above_272k_tokens":2.5e-7},"list_pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":1e-8,"cache_creation_input_token_cost":1.25e-7,"input_cost_per_token_above_272k_tokens":2e-7,"output_cost_per_token_above_272k_tokens":7.5e-7,"cache_read_input_token_cost_above_272k_tokens":2e-8,"cache_creation_input_token_cost_above_272k_tokens":2.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"amazon/openai.gpt-6-luna@us","object":"model","created":1790184068,"owned_by":"amazon","model_name":"openai.gpt-6-luna","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":1e-8,"cache_creation_input_token_cost":1.25e-7,"input_cost_per_token_above_272k_tokens":2e-7,"output_cost_per_token_above_272k_tokens":7.5e-7,"cache_read_input_token_cost_above_272k_tokens":2e-8,"cache_creation_input_token_cost_above_272k_tokens":2.5e-7},"list_pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":1e-8,"cache_creation_input_token_cost":1.25e-7,"input_cost_per_token_above_272k_tokens":2e-7,"output_cost_per_token_above_272k_tokens":7.5e-7,"cache_read_input_token_cost_above_272k_tokens":2e-8,"cache_creation_input_token_cost_above_272k_tokens":2.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null},{"id":"openai/gpt-6-luna","object":"model","created":1790100786,"owned_by":"openai","model_name":"gpt-6-luna","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol.","source":null,"capabilities":{"input_modalities":["file","image","text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":5e-7,"input_cost_per_token_flex":5e-8,"output_cost_per_token_flex":2.5e-7,"cache_read_input_token_cost":1e-8,"input_cost_per_token_batches":5e-8,"input_cost_per_token_priority":2e-7,"output_cost_per_token_batches":2.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"input_cost_per_token_decisions":1e-7,"output_cost_per_token_priority":1e-6,"cache_creation_input_token_cost":1.25e-7,"output_cost_per_token_decisions":0.0,"cache_read_input_token_cost_flex":5e-9,"cache_read_input_token_cost_batches":5e-9,"cache_creation_input_token_cost_flex":6.25e-8,"cache_read_input_token_cost_priority":2e-8,"cache_read_input_token_cost_decisions":1e-8,"input_cost_per_token_above_272k_tokens":2e-7,"output_cost_per_token_above_272k_tokens":7.5e-7,"cache_creation_input_token_cost_priority":2.5e-7,"cache_creation_input_token_cost_decisions":1.25e-7,"cache_creation_input_token_cost_above_12hr":2.5e-7,"input_cost_per_token_above_272k_tokens_flex":1e-7,"output_cost_per_token_above_272k_tokens_flex":3.75e-7,"cache_read_input_token_cost_above_272k_tokens":2e-8,"cache_creation_input_token_cost_above_12hr_flex":1.25e-7,"input_cost_per_token_above_272k_tokens_priority":4e-7,"input_cost_per_token_above_272k_tokens_decisions":2e-7,"output_cost_per_token_above_272k_tokens_priority":1.5e-6,"cache_creation_input_token_cost_above_272k_tokens":2.5e-7,"output_cost_per_token_above_272k_tokens_decisions":0.0,"cache_read_input_token_cost_above_272k_tokens_flex":1e-8,"cache_creation_input_token_cost_above_12hr_priority":5e-7,"cache_creation_input_token_cost_above_272k_tokens_flex":1.25e-7,"cache_read_input_token_cost_above_272k_tokens_priority":4e-8,"cache_read_input_token_cost_above_272k_tokens_decisions":2e-8,"cache_creation_input_token_cost_above_272k_tokens_priority":5e-7,"cache_creation_input_token_cost_above_272k_tokens_decisions":2.5e-7,"cache_creation_input_token_cost_above_12hr_above_272k_tokens":5e-7,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_flex":2.5e-7,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_priority":1e-6},"list_pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":5e-7,"input_cost_per_token_flex":5e-8,"output_cost_per_token_flex":2.5e-7,"cache_read_input_token_cost":1e-8,"input_cost_per_token_batches":5e-8,"input_cost_per_token_priority":2e-7,"output_cost_per_token_batches":2.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"input_cost_per_token_decisions":1e-7,"output_cost_per_token_priority":1e-6,"cache_creation_input_token_cost":1.25e-7,"output_cost_per_token_decisions":0.0,"cache_read_input_token_cost_flex":5e-9,"cache_read_input_token_cost_batches":5e-9,"cache_creation_input_token_cost_flex":6.25e-8,"cache_read_input_token_cost_priority":2e-8,"cache_read_input_token_cost_decisions":1e-8,"input_cost_per_token_above_272k_tokens":2e-7,"output_cost_per_token_above_272k_tokens":7.5e-7,"cache_creation_input_token_cost_priority":2.5e-7,"cache_creation_input_token_cost_decisions":1.25e-7,"cache_creation_input_token_cost_above_12hr":2.5e-7,"input_cost_per_token_above_272k_tokens_flex":1e-7,"output_cost_per_token_above_272k_tokens_flex":3.75e-7,"cache_read_input_token_cost_above_272k_tokens":2e-8,"cache_creation_input_token_cost_above_12hr_flex":1.25e-7,"input_cost_per_token_above_272k_tokens_priority":4e-7,"input_cost_per_token_above_272k_tokens_decisions":2e-7,"output_cost_per_token_above_272k_tokens_priority":1.5e-6,"cache_creation_input_token_cost_above_272k_tokens":2.5e-7,"output_cost_per_token_above_272k_tokens_decisions":0.0,"cache_read_input_token_cost_above_272k_tokens_flex":1e-8,"cache_creation_input_token_cost_above_12hr_priority":5e-7,"cache_creation_input_token_cost_above_272k_tokens_flex":1.25e-7,"cache_read_input_token_cost_above_272k_tokens_priority":4e-8,"cache_read_input_token_cost_above_272k_tokens_decisions":2e-8,"cache_creation_input_token_cost_above_272k_tokens_priority":5e-7,"cache_creation_input_token_cost_above_272k_tokens_decisions":2.5e-7,"cache_creation_input_token_cost_above_12hr_above_272k_tokens":5e-7,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_flex":2.5e-7,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_priority":1e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":8},{"id":"gpt-5.4","object":"model","created":1790262417,"owned_by":"openai","mode":"chat","context_length":1050000,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2.5e-6,"output_cost_per_token":0.000015,"input_dbu_cost_per_token":0.000035714,"output_dbu_cost_per_token":0.000214286,"cache_read_input_token_cost":2.5e-7,"input_cost_per_token_priority":5e-6,"output_cost_per_token_priority":0.00003,"cache_creation_input_token_cost":2.5e-6,"input_cost_per_token_above_272k_tokens":5e-6,"output_cost_per_token_above_272k_tokens":0.0000225,"cache_creation_input_token_cost_priority":5e-6,"cache_read_input_token_cost_above_272k_tokens":5e-7,"input_cost_per_token_above_272k_tokens_priority":5e-6,"output_cost_per_token_above_272k_tokens_priority":0.00003,"cache_read_input_token_cost_above_272k_tokens_priority":5e-7},"pricing_endpoint":"databricks/databricks-gpt-5-4","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"amazon/openai.gpt-5.4","object":"model","created":1790262417,"owned_by":"amazon","model_name":"openai.gpt-5.4","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.75e-6,"output_cost_per_token":0.0000165,"cache_read_input_token_cost":2.75e-7,"input_cost_per_token_above_272k_tokens":5.5e-6,"output_cost_per_token_above_272k_tokens":0.00002475,"cache_read_input_token_cost_above_272k_tokens":5.5e-7},"list_pricing":{"input_cost_per_token":2.75e-6,"output_cost_per_token":0.0000165,"cache_read_input_token_cost":2.75e-7,"input_cost_per_token_above_272k_tokens":5.5e-6,"output_cost_per_token_above_272k_tokens":0.00002475,"cache_read_input_token_cost_above_272k_tokens":5.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"amazon/openai.gpt-5.4@us","object":"model","created":1790262417,"owned_by":"amazon","model_name":"openai.gpt-5.4","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.75e-6,"output_cost_per_token":0.0000165,"cache_read_input_token_cost":2.75e-7,"input_cost_per_token_above_272k_tokens":5.5e-6,"output_cost_per_token_above_272k_tokens":0.00002475,"cache_read_input_token_cost_above_272k_tokens":5.5e-7},"list_pricing":{"input_cost_per_token":2.75e-6,"output_cost_per_token":0.0000165,"cache_read_input_token_cost":2.75e-7,"input_cost_per_token_above_272k_tokens":5.5e-6,"output_cost_per_token_above_272k_tokens":0.00002475,"cache_read_input_token_cost_above_272k_tokens":5.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null},{"id":"azure/gpt-5.4@eu","object":"model","created":1784832896,"owned_by":"azure","model_name":"gpt-5.4","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2.7500000000000004e-6,"output_cost_per_token":0.0000165,"input_cost_per_token_flex":1.3750000000000002e-6,"output_cost_per_token_flex":8.25e-6,"cache_read_input_token_cost":2.75e-7,"input_cost_per_token_priority":5.500000000000001e-6,"output_cost_per_token_priority":0.000033,"cache_read_input_token_cost_priority":5.5e-7,"input_cost_per_token_above_272k_tokens":5.500000000000001e-6,"output_cost_per_token_above_272k_tokens":0.000024750000000000002,"input_cost_per_token_above_272k_tokens_flex":2.7500000000000004e-6,"output_cost_per_token_above_272k_tokens_flex":0.000012375000000000001,"cache_read_input_token_cost_above_272k_tokens":5.5e-7,"input_cost_per_token_above_272k_tokens_priority":0.000011000000000000001,"output_cost_per_token_above_272k_tokens_priority":0.000049500000000000004,"cache_read_input_token_cost_above_272k_tokens_flex":2.75e-7,"cache_read_input_token_cost_above_272k_tokens_priority":1.1e-6},"list_pricing":{"input_cost_per_token":2.7500000000000004e-6,"output_cost_per_token":0.0000165,"input_cost_per_token_flex":1.3750000000000002e-6,"output_cost_per_token_flex":8.25e-6,"cache_read_input_token_cost":2.75e-7,"input_cost_per_token_priority":5.500000000000001e-6,"output_cost_per_token_priority":0.000033,"cache_read_input_token_cost_priority":5.5e-7,"input_cost_per_token_above_272k_tokens":5.500000000000001e-6,"output_cost_per_token_above_272k_tokens":0.000024750000000000002,"input_cost_per_token_above_272k_tokens_flex":2.7500000000000004e-6,"output_cost_per_token_above_272k_tokens_flex":0.000012375000000000001,"cache_read_input_token_cost_above_272k_tokens":5.5e-7,"input_cost_per_token_above_272k_tokens_priority":0.000011000000000000001,"output_cost_per_token_above_272k_tokens_priority":0.000049500000000000004,"cache_read_input_token_cost_above_272k_tokens_flex":2.75e-7,"cache_read_input_token_cost_above_272k_tokens_priority":1.1e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"azure/gpt-5.4","object":"model","created":1784832896,"owned_by":"azure","model_name":"gpt-5.4","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2.5e-6,"output_cost_per_token":0.000015,"input_cost_per_token_flex":1.25e-6,"output_cost_per_token_flex":7.5e-6,"cache_read_input_token_cost":2.5e-7,"input_cost_per_token_priority":5e-6,"output_cost_per_token_priority":0.00003,"cache_read_input_token_cost_priority":5e-7,"input_cost_per_token_above_272k_tokens":5e-6,"output_cost_per_token_above_272k_tokens":0.0000225,"input_cost_per_token_above_272k_tokens_flex":2.5e-6,"output_cost_per_token_above_272k_tokens_flex":0.00001125,"cache_read_input_token_cost_above_272k_tokens":5e-7,"input_cost_per_token_above_272k_tokens_priority":0.00001,"output_cost_per_token_above_272k_tokens_priority":0.000045,"cache_read_input_token_cost_above_272k_tokens_flex":2.5e-7,"cache_read_input_token_cost_above_272k_tokens_priority":1e-6},"list_pricing":{"input_cost_per_token":2.5e-6,"output_cost_per_token":0.000015,"input_cost_per_token_flex":1.25e-6,"output_cost_per_token_flex":7.5e-6,"cache_read_input_token_cost":2.5e-7,"input_cost_per_token_priority":5e-6,"output_cost_per_token_priority":0.00003,"cache_read_input_token_cost_priority":5e-7,"input_cost_per_token_above_272k_tokens":5e-6,"output_cost_per_token_above_272k_tokens":0.0000225,"input_cost_per_token_above_272k_tokens_flex":2.5e-6,"output_cost_per_token_above_272k_tokens_flex":0.00001125,"cache_read_input_token_cost_above_272k_tokens":5e-7,"input_cost_per_token_above_272k_tokens_priority":0.00001,"output_cost_per_token_above_272k_tokens_priority":0.000045,"cache_read_input_token_cost_above_272k_tokens_flex":2.5e-7,"cache_read_input_token_cost_above_272k_tokens_priority":1e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"azure/gpt-5.4@us","object":"model","created":1784832896,"owned_by":"azure","model_name":"gpt-5.4","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2.7500000000000004e-6,"output_cost_per_token":0.0000165,"input_cost_per_token_flex":1.3750000000000002e-6,"output_cost_per_token_flex":8.25e-6,"cache_read_input_token_cost":2.75e-7,"input_cost_per_token_priority":5.500000000000001e-6,"output_cost_per_token_priority":0.000033,"cache_read_input_token_cost_priority":5.5e-7,"input_cost_per_token_above_272k_tokens":5.500000000000001e-6,"output_cost_per_token_above_272k_tokens":0.000024750000000000002,"input_cost_per_token_above_272k_tokens_flex":2.7500000000000004e-6,"output_cost_per_token_above_272k_tokens_flex":0.000012375000000000001,"cache_read_input_token_cost_above_272k_tokens":5.5e-7,"input_cost_per_token_above_272k_tokens_priority":0.000011000000000000001,"output_cost_per_token_above_272k_tokens_priority":0.000049500000000000004,"cache_read_input_token_cost_above_272k_tokens_flex":2.75e-7,"cache_read_input_token_cost_above_272k_tokens_priority":1.1e-6},"list_pricing":{"input_cost_per_token":2.7500000000000004e-6,"output_cost_per_token":0.0000165,"input_cost_per_token_flex":1.3750000000000002e-6,"output_cost_per_token_flex":8.25e-6,"cache_read_input_token_cost":2.75e-7,"input_cost_per_token_priority":5.500000000000001e-6,"output_cost_per_token_priority":0.000033,"cache_read_input_token_cost_priority":5.5e-7,"input_cost_per_token_above_272k_tokens":5.500000000000001e-6,"output_cost_per_token_above_272k_tokens":0.000024750000000000002,"input_cost_per_token_above_272k_tokens_flex":2.7500000000000004e-6,"output_cost_per_token_above_272k_tokens_flex":0.000012375000000000001,"cache_read_input_token_cost_above_272k_tokens":5.5e-7,"input_cost_per_token_above_272k_tokens_priority":0.000011000000000000001,"output_cost_per_token_above_272k_tokens_priority":0.000049500000000000004,"cache_read_input_token_cost_above_272k_tokens_flex":2.75e-7,"cache_read_input_token_cost_above_272k_tokens_priority":1.1e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"databricks/databricks-gpt-5-4@eu","object":"model","created":1781107711,"owned_by":"databricks","model_name":"databricks-gpt-5-4","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5.4 is a general purpose large language model with reasoning capabilities developed by OpenAI. It delivers improved performance on complex tasks with enhanced accuracy and more deliberate scaffolded reasoning. This model supports multimodal inputs and features a 400K total token context window with 128K maximum output tokens. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2.5e-6,"output_cost_per_token":0.000015,"input_dbu_cost_per_token":0.000035714,"output_dbu_cost_per_token":0.000214286,"cache_read_input_token_cost":2.5e-7,"input_cost_per_token_priority":5e-6,"output_cost_per_token_priority":0.00003,"cache_creation_input_token_cost":2.5e-6,"input_cost_per_token_above_272k_tokens":5e-6,"output_cost_per_token_above_272k_tokens":0.0000225,"cache_creation_input_token_cost_priority":5e-6,"cache_read_input_token_cost_above_272k_tokens":5e-7,"input_cost_per_token_above_272k_tokens_priority":5e-6,"output_cost_per_token_above_272k_tokens_priority":0.00003,"cache_read_input_token_cost_above_272k_tokens_priority":5e-7},"list_pricing":{"input_cost_per_token":2.5e-6,"output_cost_per_token":0.000015,"input_dbu_cost_per_token":0.000035714,"output_dbu_cost_per_token":0.000214286,"cache_read_input_token_cost":2.5e-7,"input_cost_per_token_priority":5e-6,"output_cost_per_token_priority":0.00003,"cache_creation_input_token_cost":2.5e-6,"input_cost_per_token_above_272k_tokens":5e-6,"output_cost_per_token_above_272k_tokens":0.0000225,"cache_creation_input_token_cost_priority":5e-6,"cache_read_input_token_cost_above_272k_tokens":5e-7,"input_cost_per_token_above_272k_tokens_priority":5e-6,"output_cost_per_token_above_272k_tokens_priority":0.00003,"cache_read_input_token_cost_above_272k_tokens_priority":5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"databricks/databricks-gpt-5-4","object":"model","created":1781107711,"owned_by":"databricks","model_name":"databricks-gpt-5-4","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5.4 is a general purpose large language model with reasoning capabilities developed by OpenAI. It delivers improved performance on complex tasks with enhanced accuracy and more deliberate scaffolded reasoning. This model supports multimodal inputs and features a 400K total token context window with 128K maximum output tokens. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2.5e-6,"output_cost_per_token":0.000015,"input_dbu_cost_per_token":0.000035714,"output_dbu_cost_per_token":0.000214286,"cache_read_input_token_cost":2.5e-7,"input_cost_per_token_priority":5e-6,"output_cost_per_token_priority":0.00003,"cache_creation_input_token_cost":2.5e-6,"input_cost_per_token_above_272k_tokens":5e-6,"output_cost_per_token_above_272k_tokens":0.0000225,"cache_creation_input_token_cost_priority":5e-6,"cache_read_input_token_cost_above_272k_tokens":5e-7,"input_cost_per_token_above_272k_tokens_priority":5e-6,"output_cost_per_token_above_272k_tokens_priority":0.00003,"cache_read_input_token_cost_above_272k_tokens_priority":5e-7},"list_pricing":{"input_cost_per_token":2.5e-6,"output_cost_per_token":0.000015,"input_dbu_cost_per_token":0.000035714,"output_dbu_cost_per_token":0.000214286,"cache_read_input_token_cost":2.5e-7,"input_cost_per_token_priority":5e-6,"output_cost_per_token_priority":0.00003,"cache_creation_input_token_cost":2.5e-6,"input_cost_per_token_above_272k_tokens":5e-6,"output_cost_per_token_above_272k_tokens":0.0000225,"cache_creation_input_token_cost_priority":5e-6,"cache_read_input_token_cost_above_272k_tokens":5e-7,"input_cost_per_token_above_272k_tokens_priority":5e-6,"output_cost_per_token_above_272k_tokens_priority":0.00003,"cache_read_input_token_cost_above_272k_tokens_priority":5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"openai/gpt-5.4","object":"model","created":1772734352,"owned_by":"openai","model_name":"gpt-5.4","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2.5e-6,"output_cost_per_token":0.000015,"input_cost_per_token_flex":1.25e-6,"output_cost_per_token_flex":7.5e-6,"cache_read_input_token_cost":2.5e-7,"input_cost_per_token_batches":1.25e-6,"input_cost_per_token_priority":5e-6,"output_cost_per_token_batches":7.5e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"output_cost_per_token_priority":0.00003,"cache_read_input_token_cost_flex":1.3e-7,"cache_read_input_token_cost_batches":1.3e-7,"cache_read_input_token_cost_priority":5e-7,"input_cost_per_token_above_272k_tokens":5e-6,"output_cost_per_token_above_272k_tokens":0.0000225,"input_cost_per_token_above_272k_tokens_flex":2.5e-6,"output_cost_per_token_above_272k_tokens_flex":0.00001125,"cache_read_input_token_cost_above_272k_tokens":5e-7,"cache_read_input_token_cost_above_272k_tokens_flex":2.5e-7},"list_pricing":{"input_cost_per_token":2.5e-6,"output_cost_per_token":0.000015,"input_cost_per_token_flex":1.25e-6,"output_cost_per_token_flex":7.5e-6,"cache_read_input_token_cost":2.5e-7,"input_cost_per_token_batches":1.25e-6,"input_cost_per_token_priority":5e-6,"output_cost_per_token_batches":7.5e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"output_cost_per_token_priority":0.00003,"cache_read_input_token_cost_flex":1.3e-7,"cache_read_input_token_cost_batches":1.3e-7,"cache_read_input_token_cost_priority":5e-7,"input_cost_per_token_above_272k_tokens":5e-6,"output_cost_per_token_above_272k_tokens":0.0000225,"input_cost_per_token_above_272k_tokens_flex":2.5e-6,"output_cost_per_token_above_272k_tokens_flex":0.00001125,"cache_read_input_token_cost_above_272k_tokens":5e-7,"cache_read_input_token_cost_above_272k_tokens_flex":2.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":8},{"id":"gpt-5.5","object":"model","created":1790262417,"owned_by":"openai","mode":"chat","context_length":1050000,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":5e-6,"output_cost_per_token":0.00003,"input_dbu_cost_per_token":0.000071429,"output_dbu_cost_per_token":0.000428571,"cache_read_input_token_cost":5e-7,"input_cost_per_token_priority":0.0000125,"output_cost_per_token_priority":0.000075,"cache_creation_input_token_cost":5e-6,"input_cost_per_token_above_272k_tokens":0.00001,"output_cost_per_token_above_272k_tokens":0.000045,"cache_creation_input_token_cost_priority":0.0000125,"cache_read_input_token_cost_above_272k_tokens":1e-6,"input_cost_per_token_above_272k_tokens_priority":0.0000125,"output_cost_per_token_above_272k_tokens_priority":0.000075,"cache_read_input_token_cost_above_272k_tokens_priority":1.25e-6},"pricing_endpoint":"databricks/databricks-gpt-5-5","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"amazon/openai.gpt-5.5","object":"model","created":1790262417,"owned_by":"amazon","model_name":"openai.gpt-5.5","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5.5e-6,"output_cost_per_token":0.000033,"cache_read_input_token_cost":5.5e-7,"input_cost_per_token_above_272k_tokens":0.000011,"output_cost_per_token_above_272k_tokens":0.0000495,"cache_read_input_token_cost_above_272k_tokens":1.1e-6},"list_pricing":{"input_cost_per_token":5.5e-6,"output_cost_per_token":0.000033,"cache_read_input_token_cost":5.5e-7,"input_cost_per_token_above_272k_tokens":0.000011,"output_cost_per_token_above_272k_tokens":0.0000495,"cache_read_input_token_cost_above_272k_tokens":1.1e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"amazon/openai.gpt-5.5@us","object":"model","created":1790262417,"owned_by":"amazon","model_name":"openai.gpt-5.5","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5.5e-6,"output_cost_per_token":0.000033,"cache_read_input_token_cost":5.5e-7,"input_cost_per_token_above_272k_tokens":0.000011,"output_cost_per_token_above_272k_tokens":0.0000495,"cache_read_input_token_cost_above_272k_tokens":1.1e-6},"list_pricing":{"input_cost_per_token":5.5e-6,"output_cost_per_token":0.000033,"cache_read_input_token_cost":5.5e-7,"input_cost_per_token_above_272k_tokens":0.000011,"output_cost_per_token_above_272k_tokens":0.0000495,"cache_read_input_token_cost_above_272k_tokens":1.1e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null},{"id":"azure/gpt-5.5@eu","object":"model","created":1785276709,"owned_by":"azure","model_name":"gpt-5.5","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":5.500000000000001e-6,"output_cost_per_token":0.000033,"input_cost_per_token_flex":2.7500000000000004e-6,"cache_read_input_token_cost":5.500000000000001e-7,"input_cost_per_token_priority":0.000013750000000000002,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.0000825,"cache_creation_input_token_cost":6.875000000000001e-6,"cache_read_input_token_cost_flex":2.75e-7,"cache_read_input_token_cost_priority":1.3750000000000002e-6,"input_cost_per_token_above_272k_tokens":0.000011000000000000001,"output_cost_per_token_above_272k_tokens":0.000049500000000000004,"input_cost_per_token_above_272k_tokens_flex":5.500000000000001e-6,"cache_read_input_token_cost_above_272k_tokens":1.1000000000000003e-6,"input_cost_per_token_above_272k_tokens_priority":0.000022000000000000003,"output_cost_per_token_above_272k_tokens_priority":0.00009900000000000001,"cache_creation_input_token_cost_above_272k_tokens":0.000013750000000000002,"cache_read_input_token_cost_above_272k_tokens_priority":2.2e-6},"list_pricing":{"input_cost_per_token":5.500000000000001e-6,"output_cost_per_token":0.000033,"input_cost_per_token_flex":2.7500000000000004e-6,"cache_read_input_token_cost":5.500000000000001e-7,"input_cost_per_token_priority":0.000013750000000000002,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.0000825,"cache_creation_input_token_cost":6.875000000000001e-6,"cache_read_input_token_cost_flex":2.75e-7,"cache_read_input_token_cost_priority":1.3750000000000002e-6,"input_cost_per_token_above_272k_tokens":0.000011000000000000001,"output_cost_per_token_above_272k_tokens":0.000049500000000000004,"input_cost_per_token_above_272k_tokens_flex":5.500000000000001e-6,"cache_read_input_token_cost_above_272k_tokens":1.1000000000000003e-6,"input_cost_per_token_above_272k_tokens_priority":0.000022000000000000003,"output_cost_per_token_above_272k_tokens_priority":0.00009900000000000001,"cache_creation_input_token_cost_above_272k_tokens":0.000013750000000000002,"cache_read_input_token_cost_above_272k_tokens_priority":2.2e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"azure/gpt-5.5","object":"model","created":1785276709,"owned_by":"azure","model_name":"gpt-5.5","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":5e-6,"output_cost_per_token":0.00003,"input_cost_per_token_flex":2.5e-6,"cache_read_input_token_cost":5.000000000000001e-7,"input_cost_per_token_priority":0.0000125,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.000075,"cache_creation_input_token_cost":6.25e-6,"cache_read_input_token_cost_flex":2.5e-7,"cache_read_input_token_cost_priority":1.25e-6,"input_cost_per_token_above_272k_tokens":0.00001,"output_cost_per_token_above_272k_tokens":0.000045,"input_cost_per_token_above_272k_tokens_flex":5e-6,"cache_read_input_token_cost_above_272k_tokens":1.0000000000000002e-6,"input_cost_per_token_above_272k_tokens_priority":0.00002,"output_cost_per_token_above_272k_tokens_priority":0.00009,"cache_creation_input_token_cost_above_272k_tokens":0.0000125,"cache_read_input_token_cost_above_272k_tokens_priority":2e-6},"list_pricing":{"input_cost_per_token":5e-6,"output_cost_per_token":0.00003,"input_cost_per_token_flex":2.5e-6,"cache_read_input_token_cost":5.000000000000001e-7,"input_cost_per_token_priority":0.0000125,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.000075,"cache_creation_input_token_cost":6.25e-6,"cache_read_input_token_cost_flex":2.5e-7,"cache_read_input_token_cost_priority":1.25e-6,"input_cost_per_token_above_272k_tokens":0.00001,"output_cost_per_token_above_272k_tokens":0.000045,"input_cost_per_token_above_272k_tokens_flex":5e-6,"cache_read_input_token_cost_above_272k_tokens":1.0000000000000002e-6,"input_cost_per_token_above_272k_tokens_priority":0.00002,"output_cost_per_token_above_272k_tokens_priority":0.00009,"cache_creation_input_token_cost_above_272k_tokens":0.0000125,"cache_read_input_token_cost_above_272k_tokens_priority":2e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"azure/gpt-5.5@us","object":"model","created":1785276709,"owned_by":"azure","model_name":"gpt-5.5","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":5.500000000000001e-6,"output_cost_per_token":0.000033,"input_cost_per_token_flex":2.7500000000000004e-6,"cache_read_input_token_cost":5.500000000000001e-7,"input_cost_per_token_priority":0.000013750000000000002,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.0000825,"cache_creation_input_token_cost":6.875000000000001e-6,"cache_read_input_token_cost_flex":2.75e-7,"cache_read_input_token_cost_priority":1.3750000000000002e-6,"input_cost_per_token_above_272k_tokens":0.000011000000000000001,"output_cost_per_token_above_272k_tokens":0.000049500000000000004,"input_cost_per_token_above_272k_tokens_flex":5.500000000000001e-6,"cache_read_input_token_cost_above_272k_tokens":1.1000000000000003e-6,"input_cost_per_token_above_272k_tokens_priority":0.000022000000000000003,"output_cost_per_token_above_272k_tokens_priority":0.00009900000000000001,"cache_creation_input_token_cost_above_272k_tokens":0.000013750000000000002,"cache_read_input_token_cost_above_272k_tokens_priority":2.2e-6},"list_pricing":{"input_cost_per_token":5.500000000000001e-6,"output_cost_per_token":0.000033,"input_cost_per_token_flex":2.7500000000000004e-6,"cache_read_input_token_cost":5.500000000000001e-7,"input_cost_per_token_priority":0.000013750000000000002,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.0000825,"cache_creation_input_token_cost":6.875000000000001e-6,"cache_read_input_token_cost_flex":2.75e-7,"cache_read_input_token_cost_priority":1.3750000000000002e-6,"input_cost_per_token_above_272k_tokens":0.000011000000000000001,"output_cost_per_token_above_272k_tokens":0.000049500000000000004,"input_cost_per_token_above_272k_tokens_flex":5.500000000000001e-6,"cache_read_input_token_cost_above_272k_tokens":1.1000000000000003e-6,"input_cost_per_token_above_272k_tokens_priority":0.000022000000000000003,"output_cost_per_token_above_272k_tokens_priority":0.00009900000000000001,"cache_creation_input_token_cost_above_272k_tokens":0.000013750000000000002,"cache_read_input_token_cost_above_272k_tokens_priority":2.2e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"databricks/databricks-gpt-5-5@eu","object":"model","created":1781107530,"owned_by":"databricks","model_name":"databricks-gpt-5-5","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5.5 is OpenAI's strongest frontier model for agentic work in enterprise, complex document reasoning, and long-horizon coding agents. GPT-5.5 also now powers Codex, OpenAI's coding agent. This model supports multimodal inputs and features a 400K total token context window with 128K maximum output tokens. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["file","image","text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":5e-6,"output_cost_per_token":0.00003,"input_dbu_cost_per_token":0.000071429,"output_dbu_cost_per_token":0.000428571,"cache_read_input_token_cost":5e-7,"input_cost_per_token_priority":0.0000125,"output_cost_per_token_priority":0.000075,"cache_creation_input_token_cost":5e-6,"input_cost_per_token_above_272k_tokens":0.00001,"output_cost_per_token_above_272k_tokens":0.000045,"cache_creation_input_token_cost_priority":0.0000125,"cache_read_input_token_cost_above_272k_tokens":1e-6,"input_cost_per_token_above_272k_tokens_priority":0.0000125,"output_cost_per_token_above_272k_tokens_priority":0.000075,"cache_read_input_token_cost_above_272k_tokens_priority":1.25e-6},"list_pricing":{"input_cost_per_token":5e-6,"output_cost_per_token":0.00003,"input_dbu_cost_per_token":0.000071429,"output_dbu_cost_per_token":0.000428571,"cache_read_input_token_cost":5e-7,"input_cost_per_token_priority":0.0000125,"output_cost_per_token_priority":0.000075,"cache_creation_input_token_cost":5e-6,"input_cost_per_token_above_272k_tokens":0.00001,"output_cost_per_token_above_272k_tokens":0.000045,"cache_creation_input_token_cost_priority":0.0000125,"cache_read_input_token_cost_above_272k_tokens":1e-6,"input_cost_per_token_above_272k_tokens_priority":0.0000125,"output_cost_per_token_above_272k_tokens_priority":0.000075,"cache_read_input_token_cost_above_272k_tokens_priority":1.25e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"databricks/databricks-gpt-5-5","object":"model","created":1781107530,"owned_by":"databricks","model_name":"databricks-gpt-5-5","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5.5 is OpenAI's strongest frontier model for agentic work in enterprise, complex document reasoning, and long-horizon coding agents. GPT-5.5 also now powers Codex, OpenAI's coding agent. This model supports multimodal inputs and features a 400K total token context window with 128K maximum output tokens. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["file","image","text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":5e-6,"output_cost_per_token":0.00003,"input_dbu_cost_per_token":0.000071429,"output_dbu_cost_per_token":0.000428571,"cache_read_input_token_cost":5e-7,"input_cost_per_token_priority":0.0000125,"output_cost_per_token_priority":0.000075,"cache_creation_input_token_cost":5e-6,"input_cost_per_token_above_272k_tokens":0.00001,"output_cost_per_token_above_272k_tokens":0.000045,"cache_creation_input_token_cost_priority":0.0000125,"cache_read_input_token_cost_above_272k_tokens":1e-6,"input_cost_per_token_above_272k_tokens_priority":0.0000125,"output_cost_per_token_above_272k_tokens_priority":0.000075,"cache_read_input_token_cost_above_272k_tokens_priority":1.25e-6},"list_pricing":{"input_cost_per_token":5e-6,"output_cost_per_token":0.00003,"input_dbu_cost_per_token":0.000071429,"output_dbu_cost_per_token":0.000428571,"cache_read_input_token_cost":5e-7,"input_cost_per_token_priority":0.0000125,"output_cost_per_token_priority":0.000075,"cache_creation_input_token_cost":5e-6,"input_cost_per_token_above_272k_tokens":0.00001,"output_cost_per_token_above_272k_tokens":0.000045,"cache_creation_input_token_cost_priority":0.0000125,"cache_read_input_token_cost_above_272k_tokens":1e-6,"input_cost_per_token_above_272k_tokens_priority":0.0000125,"output_cost_per_token_above_272k_tokens_priority":0.000075,"cache_read_input_token_cost_above_272k_tokens_priority":1.25e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"openai/gpt-5.5","object":"model","created":1777051893,"owned_by":"openai","model_name":"gpt-5.5","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks.","source":null,"capabilities":{"input_modalities":["file","image","text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":5e-6,"output_cost_per_token":0.00003,"input_cost_per_token_flex":2.5e-6,"output_cost_per_token_flex":0.000015,"cache_read_input_token_cost":5e-7,"input_cost_per_token_batches":2.5e-6,"input_cost_per_token_priority":0.0000125,"output_cost_per_token_batches":0.000015,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"output_cost_per_token_priority":0.000075,"cache_read_input_token_cost_flex":2.5e-7,"cache_read_input_token_cost_batches":2.5e-7,"cache_read_input_token_cost_priority":1.25e-6,"input_cost_per_token_above_272k_tokens":0.00001,"output_cost_per_token_above_272k_tokens":0.000045,"input_cost_per_token_above_272k_tokens_flex":5e-6,"output_cost_per_token_above_272k_tokens_flex":0.0000225,"cache_read_input_token_cost_above_272k_tokens":1e-6,"cache_read_input_token_cost_above_272k_tokens_flex":5e-7},"list_pricing":{"input_cost_per_token":5e-6,"output_cost_per_token":0.00003,"input_cost_per_token_flex":2.5e-6,"output_cost_per_token_flex":0.000015,"cache_read_input_token_cost":5e-7,"input_cost_per_token_batches":2.5e-6,"input_cost_per_token_priority":0.0000125,"output_cost_per_token_batches":0.000015,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"output_cost_per_token_priority":0.000075,"cache_read_input_token_cost_flex":2.5e-7,"cache_read_input_token_cost_batches":2.5e-7,"cache_read_input_token_cost_priority":1.25e-6,"input_cost_per_token_above_272k_tokens":0.00001,"output_cost_per_token_above_272k_tokens":0.000045,"input_cost_per_token_above_272k_tokens_flex":5e-6,"output_cost_per_token_above_272k_tokens_flex":0.0000225,"cache_read_input_token_cost_above_272k_tokens":1e-6,"cache_read_input_token_cost_above_272k_tokens_flex":5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":8},{"id":"deep-research-max-preview-04-2026","object":"model","created":1790226846,"owned_by":"google","mode":"chat","context_length":1048576,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.000012,"search_context_cost_per_query":{"search_context_size_low":0.035,"search_context_size_high":0.035,"search_context_size_medium":0.035}},"pricing_endpoint":"google/deep-research-max-preview-04-2026","regions":[{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"google/deep-research-max-preview-04-2026","object":"model","created":1790226846,"owned_by":"google","model_name":"deep-research-max-preview-04-2026","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.000012,"search_context_cost_per_query":{"search_context_size_low":0.035,"search_context_size_high":0.035,"search_context_size_medium":0.035}},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.000012,"search_context_cost_per_query":{"search_context_size_low":0.035,"search_context_size_high":0.035,"search_context_size_medium":0.035}},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":1},{"id":"deep-research-preview-04-2026","object":"model","created":1790226846,"owned_by":"google","mode":"chat","context_length":1048576,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.000012,"search_context_cost_per_query":{"search_context_size_low":0.035,"search_context_size_high":0.035,"search_context_size_medium":0.035}},"pricing_endpoint":"google/deep-research-preview-04-2026","regions":[{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"google/deep-research-preview-04-2026","object":"model","created":1790226846,"owned_by":"google","model_name":"deep-research-preview-04-2026","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.000012,"search_context_cost_per_query":{"search_context_size_low":0.035,"search_context_size_high":0.035,"search_context_size_medium":0.035}},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.000012,"search_context_cost_per_query":{"search_context_size_low":0.035,"search_context_size_high":0.035,"search_context_size_medium":0.035}},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":1},{"id":"tev1-4b-experimental","object":"model","created":1790226846,"owned_by":"","mode":"chat","context_length":32768,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4.2e-8,"output_cost_per_token":0.0},"pricing_endpoint":"together_ai/together/Tev1-4B-experimental","regions":[{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"together_ai/together/Tev1-4B-experimental","object":"model","created":1790226846,"owned_by":"together_ai","model_name":"together/Tev1-4B-experimental","context_length":32768,"max_input_tokens":32768,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4.2e-8,"output_cost_per_token":0.0},"list_pricing":{"input_cost_per_token":4.2e-8,"output_cost_per_token":0.0},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":1},{"id":"ember-1","object":"model","created":1790208461,"owned_by":"","mode":"chat","context_length":1048576,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"cache_read_input_token_cost":3e-7,"input_cost_per_token_priority":3.75e-6,"output_cost_per_token_priority":0.00001875,"cache_read_input_token_cost_priority":3.75e-7},"pricing_endpoint":"fireworks_ai/accounts/fireworks/models/ember-1","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"fireworks_ai/accounts/fireworks/models/ember-1","object":"model","created":1790208461,"owned_by":"fireworks_ai","model_name":"accounts/fireworks/models/ember-1","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"Ember-1 is a specialized reasoning model from Fireworks Research, built on Kimi K3.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"cache_read_input_token_cost":3e-7,"input_cost_per_token_priority":3.75e-6,"output_cost_per_token_priority":0.00001875,"cache_read_input_token_cost_priority":3.75e-7},"list_pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"cache_read_input_token_cost":3e-7,"input_cost_per_token_priority":3.75e-6,"output_cost_per_token_priority":0.00001875,"cache_read_input_token_cost_priority":3.75e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"glm-5.3-prime","object":"model","created":1790199651,"owned_by":"zai","mode":"chat","context_length":1000000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.82e-6,"output_cost_per_token":5.72e-6,"cache_read_input_token_cost":3.6400000000000003e-7},"pricing_endpoint":"qwen/glm-5.3-prime","regions":[{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"qwen/glm-5.3-prime","object":"model","created":1790199651,"owned_by":"qwen","model_name":"glm-5.3-prime","context_length":1000000,"max_input_tokens":1048576,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"GLM-5.3-Prime is the high-speed variant of GLM-5.3, inheriting its full capabilities while achieving 1.5–2× the output TPS through inference acceleration. It delivers state-of-the-art coding and agentic performance among open-source models, supports 1M context and 128K output tokens, and can produce production-grade results end-to-end — along with emergent cybersecurity capabilities such as vulnerability discovery. Designed for latency-sensitive scenarios including real-time conversation, multi-turn agent orchestration, and streaming code generation.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.82e-6,"output_cost_per_token":5.72e-6,"cache_read_input_token_cost":3.6400000000000003e-7},"list_pricing":{"input_cost_per_token":2.8e-6,"output_cost_per_token":8.8e-6,"cache_read_input_token_cost":5.6e-7},"discount":0.35,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":1},{"id":"qwen3-30b-a3b-thinking-2507-fp8","object":"model","created":1790170741,"owned_by":"qwen","mode":"chat","context_length":262144,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":2.4e-6,"cache_read_input_token_cost":3e-8},"pricing_endpoint":"flexai/Qwen3-30B-A3B-Thinking-2507-FP8","regions":[{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"flexai/Qwen3-30B-A3B-Thinking-2507-FP8","object":"model","created":1790170741,"owned_by":"flexai","model_name":"Qwen3-30B-A3B-Thinking-2507-FP8","context_length":262144,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":2.4e-6,"cache_read_input_token_cost":3e-8},"list_pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":2.4e-6,"cache_read_input_token_cost":3e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"qwen3-coder-30b-a3b-instruct-fp8","object":"model","created":1790170741,"owned_by":"qwen","mode":"chat","context_length":262144,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":7e-8,"output_cost_per_token":2.8e-7,"cache_read_input_token_cost":1.05e-8},"pricing_endpoint":"flexai/Qwen3-Coder-30B-A3B-Instruct-FP8","regions":[{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"flexai/Qwen3-Coder-30B-A3B-Instruct-FP8","object":"model","created":1790170741,"owned_by":"flexai","model_name":"Qwen3-Coder-30B-A3B-Instruct-FP8","context_length":262144,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"Qwen3-Coder-30B-A3B-Instruct is a 30.5B parameter Mixture-of-Experts (MoE) model with 128 experts (8 active per forward pass), designed for advanced code generation, repository-scale understanding, and agentic tool use.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":7e-8,"output_cost_per_token":2.8e-7,"cache_read_input_token_cost":1.05e-8},"list_pricing":{"input_cost_per_token":7e-8,"output_cost_per_token":2.8e-7,"cache_read_input_token_cost":1.05e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"gemini-3.7-flash","object":"model","created":1790140226,"owned_by":"google","mode":"chat","context_length":1048576,"capabilities":{"input_modalities":["text","image","video","audio","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":7.5e-7,"output_cost_per_token":3.75e-6,"input_cost_per_audio_token":7.5e-7,"input_cost_per_image_token":7.5e-7,"cache_read_input_token_cost":7.5e-8,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"cache_creation_input_token_cost":4.16666666666667e-8,"output_cost_per_reasoning_token":3.75e-6,"cache_read_input_audio_token_cost":7.5e-8,"google_maps_grounding_cost_per_query":0.007},"pricing_endpoint":"google/gemini-3.7-flash","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"databricks/databricks-gemini-3-7-flash@eu","object":"model","created":1790140226,"owned_by":"databricks","model_name":"databricks-gemini-3-7-flash","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"Gemini 3.7 Flash is Google's next generation fast and efficient model. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["text","image","video","audio","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":7.5e-7,"output_cost_per_token":3.75e-6,"cache_read_input_token_cost":7.5e-8,"cache_creation_input_token_cost":7.5e-7,"cache_creation_input_token_cost_priority":1.35e-6},"list_pricing":{"input_cost_per_token":7.5e-7,"output_cost_per_token":3.75e-6,"cache_read_input_token_cost":7.5e-8,"cache_creation_input_token_cost":7.5e-7,"cache_creation_input_token_cost_priority":1.35e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"databricks/databricks-gemini-3-7-flash","object":"model","created":1790140226,"owned_by":"databricks","model_name":"databricks-gemini-3-7-flash","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"Gemini 3.7 Flash is Google's next generation fast and efficient model. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["text","image","video","audio","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":7.5e-7,"output_cost_per_token":3.75e-6,"cache_read_input_token_cost":7.5e-8,"cache_creation_input_token_cost":7.5e-7,"cache_creation_input_token_cost_priority":1.35e-6},"list_pricing":{"input_cost_per_token":7.5e-7,"output_cost_per_token":3.75e-6,"cache_read_input_token_cost":7.5e-8,"cache_creation_input_token_cost":7.5e-7,"cache_creation_input_token_cost_priority":1.35e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"deepinfra/google/gemini-3.7-flash","object":"model","created":1786770560,"owned_by":"deepinfra","model_name":"google/gemini-3.7-flash","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning.","source":null,"capabilities":{"input_modalities":["text","image","audio"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":7.499999999999999e-7,"output_cost_per_token":3.75e-6},"list_pricing":{"input_cost_per_token":7.499999999999999e-7,"output_cost_per_token":3.75e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null},{"id":"google/gemini-3.7-flash","object":"model","created":1786640581,"owned_by":"google","model_name":"gemini-3.7-flash","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning.","source":null,"capabilities":{"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":7.5e-7,"output_cost_per_token":3.75e-6,"input_cost_per_audio_token":7.5e-7,"input_cost_per_image_token":7.5e-7,"cache_read_input_token_cost":7.5e-8,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"cache_creation_input_token_cost":4.16666666666667e-8,"output_cost_per_reasoning_token":3.75e-6,"cache_read_input_audio_token_cost":7.5e-8,"google_maps_grounding_cost_per_query":0.007},"list_pricing":{"input_cost_per_token":1.5e-6,"output_cost_per_token":7.5e-6,"input_cost_per_audio_token":1.5e-6,"input_cost_per_image_token":1.5e-6,"cache_read_input_token_cost":1.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.028,"search_context_size_high":0.028,"search_context_size_medium":0.028},"cache_creation_input_token_cost":8.33333333333334e-8,"output_cost_per_reasoning_token":7.5e-6,"cache_read_input_audio_token_cost":1.5e-7,"google_maps_grounding_cost_per_query":0.014},"discount":0.5,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"vertex/gemini-3.7-flash@eu","object":"model","created":1786640581,"owned_by":"vertex","model_name":"gemini-3.7-flash","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning.","source":null,"capabilities":{"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":8.25e-7,"output_cost_per_token":4.125e-6,"input_cost_per_audio_token":8.25e-7,"input_cost_per_image_token":8.25e-7,"cache_read_input_token_cost":8.25e-8,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"cache_creation_input_token_cost":4.583333333333337e-8,"output_cost_per_reasoning_token":4.125e-6,"cache_read_input_audio_token_cost":8.25e-8,"google_maps_grounding_cost_per_query":0.007700000000000001},"list_pricing":{"input_cost_per_token":1.65e-6,"output_cost_per_token":8.25e-6,"input_cost_per_audio_token":1.65e-6,"input_cost_per_image_token":1.65e-6,"cache_read_input_token_cost":1.65e-7,"search_context_cost_per_query":{"search_context_size_low":0.028,"search_context_size_high":0.028,"search_context_size_medium":0.028},"cache_creation_input_token_cost":9.166666666666675e-8,"output_cost_per_reasoning_token":8.25e-6,"cache_read_input_audio_token_cost":1.65e-7,"google_maps_grounding_cost_per_query":0.015400000000000002},"discount":0.5,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"vertex/gemini-3.7-flash","object":"model","created":1786640581,"owned_by":"vertex","model_name":"gemini-3.7-flash","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning.","source":null,"capabilities":{"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":7.5e-7,"output_cost_per_token":3.75e-6,"input_cost_per_audio_token":7.5e-7,"input_cost_per_image_token":7.5e-7,"cache_read_input_token_cost":7.5e-8,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"cache_creation_input_token_cost":4.16666666666667e-8,"output_cost_per_reasoning_token":3.75e-6,"cache_read_input_audio_token_cost":7.5e-8,"google_maps_grounding_cost_per_query":0.007},"list_pricing":{"input_cost_per_token":1.5e-6,"output_cost_per_token":7.5e-6,"input_cost_per_audio_token":1.5e-6,"input_cost_per_image_token":1.5e-6,"cache_read_input_token_cost":1.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.028,"search_context_size_high":0.028,"search_context_size_medium":0.028},"cache_creation_input_token_cost":8.33333333333334e-8,"output_cost_per_reasoning_token":7.5e-6,"cache_read_input_audio_token_cost":1.5e-7,"google_maps_grounding_cost_per_query":0.014},"discount":0.5,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"vertex/gemini-3.7-flash@us","object":"model","created":1786640581,"owned_by":"vertex","model_name":"gemini-3.7-flash","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning.","source":null,"capabilities":{"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":8.25e-7,"output_cost_per_token":4.125e-6,"input_cost_per_audio_token":8.25e-7,"input_cost_per_image_token":8.25e-7,"cache_read_input_token_cost":8.25e-8,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"cache_creation_input_token_cost":4.583333333333337e-8,"output_cost_per_reasoning_token":4.125e-6,"cache_read_input_audio_token_cost":8.25e-8,"google_maps_grounding_cost_per_query":0.007700000000000001},"list_pricing":{"input_cost_per_token":1.65e-6,"output_cost_per_token":8.25e-6,"input_cost_per_audio_token":1.65e-6,"input_cost_per_image_token":1.65e-6,"cache_read_input_token_cost":1.65e-7,"search_context_cost_per_query":{"search_context_size_low":0.028,"search_context_size_high":0.028,"search_context_size_medium":0.028},"cache_creation_input_token_cost":9.166666666666675e-8,"output_cost_per_reasoning_token":8.25e-6,"cache_read_input_audio_token_cost":1.65e-7,"google_maps_grounding_cost_per_query":0.015400000000000002},"discount":0.5,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":7},{"id":"gemini-3.8-flash","object":"model","created":1790140226,"owned_by":"google","mode":"chat","context_length":1048576,"capabilities":{"input_modalities":["text","image","video","audio","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":7.5e-7,"output_cost_per_token":3.75e-6,"input_cost_per_audio_token":7.5e-7,"input_cost_per_image_token":7.5e-7,"cache_read_input_token_cost":7.5e-8,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"cache_creation_input_token_cost":4.16666666666667e-8,"output_cost_per_reasoning_token":3.75e-6,"cache_read_input_audio_token_cost":7.5e-8,"google_maps_grounding_cost_per_query":0.007},"pricing_endpoint":"google/gemini-3.8-flash","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"databricks/databricks-gemini-3-8-flash@eu","object":"model","created":1790140226,"owned_by":"databricks","model_name":"databricks-gemini-3-8-flash","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"Gemini 3.8 Flash is Google's next generation fast and efficient model. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["text","image","video","audio","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":7.5e-7,"output_cost_per_token":3.75e-6,"cache_read_input_token_cost":7.5e-8,"cache_creation_input_token_cost":7.5e-7,"cache_creation_input_token_cost_priority":1.35e-6},"list_pricing":{"input_cost_per_token":7.5e-7,"output_cost_per_token":3.75e-6,"cache_read_input_token_cost":7.5e-8,"cache_creation_input_token_cost":7.5e-7,"cache_creation_input_token_cost_priority":1.35e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"databricks/databricks-gemini-3-8-flash","object":"model","created":1790140226,"owned_by":"databricks","model_name":"databricks-gemini-3-8-flash","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"Gemini 3.8 Flash is Google's next generation fast and efficient model. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["text","image","video","audio","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":7.5e-7,"output_cost_per_token":3.75e-6,"cache_read_input_token_cost":7.5e-8,"cache_creation_input_token_cost":7.5e-7,"cache_creation_input_token_cost_priority":1.35e-6},"list_pricing":{"input_cost_per_token":7.5e-7,"output_cost_per_token":3.75e-6,"cache_read_input_token_cost":7.5e-8,"cache_creation_input_token_cost":7.5e-7,"cache_creation_input_token_cost_priority":1.35e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"google/gemini-3.8-flash","object":"model","created":1788362056,"owned_by":"google","model_name":"gemini-3.8-flash","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.","source":null,"capabilities":{"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":7.5e-7,"output_cost_per_token":3.75e-6,"input_cost_per_audio_token":7.5e-7,"input_cost_per_image_token":7.5e-7,"cache_read_input_token_cost":7.5e-8,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"cache_creation_input_token_cost":4.16666666666667e-8,"output_cost_per_reasoning_token":3.75e-6,"cache_read_input_audio_token_cost":7.5e-8,"google_maps_grounding_cost_per_query":0.007},"list_pricing":{"input_cost_per_token":1.5e-6,"output_cost_per_token":7.5e-6,"input_cost_per_audio_token":1.5e-6,"input_cost_per_image_token":1.5e-6,"cache_read_input_token_cost":1.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.028,"search_context_size_high":0.028,"search_context_size_medium":0.028},"cache_creation_input_token_cost":8.33333333333334e-8,"output_cost_per_reasoning_token":7.5e-6,"cache_read_input_audio_token_cost":1.5e-7,"google_maps_grounding_cost_per_query":0.014},"discount":0.5,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"vertex/gemini-3.8-flash@eu","object":"model","created":1788362056,"owned_by":"vertex","model_name":"gemini-3.8-flash","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.","source":null,"capabilities":{"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":8.25e-7,"output_cost_per_token":4.125e-6,"input_cost_per_audio_token":8.25e-7,"input_cost_per_image_token":8.25e-7,"cache_read_input_token_cost":8.25e-8,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"cache_creation_input_token_cost":4.583333333333337e-8,"output_cost_per_reasoning_token":4.125e-6,"cache_read_input_audio_token_cost":8.25e-8,"google_maps_grounding_cost_per_query":0.007700000000000001},"list_pricing":{"input_cost_per_token":1.65e-6,"output_cost_per_token":8.25e-6,"input_cost_per_audio_token":1.65e-6,"input_cost_per_image_token":1.65e-6,"cache_read_input_token_cost":1.65e-7,"search_context_cost_per_query":{"search_context_size_low":0.028,"search_context_size_high":0.028,"search_context_size_medium":0.028},"cache_creation_input_token_cost":9.166666666666675e-8,"output_cost_per_reasoning_token":8.25e-6,"cache_read_input_audio_token_cost":1.65e-7,"google_maps_grounding_cost_per_query":0.015400000000000002},"discount":0.5,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"vertex/gemini-3.8-flash","object":"model","created":1788362056,"owned_by":"vertex","model_name":"gemini-3.8-flash","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.","source":null,"capabilities":{"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":7.5e-7,"output_cost_per_token":3.75e-6,"input_cost_per_audio_token":7.5e-7,"input_cost_per_image_token":7.5e-7,"cache_read_input_token_cost":7.5e-8,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"cache_creation_input_token_cost":4.16666666666667e-8,"output_cost_per_reasoning_token":3.75e-6,"cache_read_input_audio_token_cost":7.5e-8,"google_maps_grounding_cost_per_query":0.007},"list_pricing":{"input_cost_per_token":1.5e-6,"output_cost_per_token":7.5e-6,"input_cost_per_audio_token":1.5e-6,"input_cost_per_image_token":1.5e-6,"cache_read_input_token_cost":1.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.028,"search_context_size_high":0.028,"search_context_size_medium":0.028},"cache_creation_input_token_cost":8.33333333333334e-8,"output_cost_per_reasoning_token":7.5e-6,"cache_read_input_audio_token_cost":1.5e-7,"google_maps_grounding_cost_per_query":0.014},"discount":0.5,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"vertex/gemini-3.8-flash@us","object":"model","created":1788362056,"owned_by":"vertex","model_name":"gemini-3.8-flash","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.","source":null,"capabilities":{"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":8.25e-7,"output_cost_per_token":4.125e-6,"input_cost_per_audio_token":8.25e-7,"input_cost_per_image_token":8.25e-7,"cache_read_input_token_cost":8.25e-8,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"cache_creation_input_token_cost":4.583333333333337e-8,"output_cost_per_reasoning_token":4.125e-6,"cache_read_input_audio_token_cost":8.25e-8,"google_maps_grounding_cost_per_query":0.007700000000000001},"list_pricing":{"input_cost_per_token":1.65e-6,"output_cost_per_token":8.25e-6,"input_cost_per_audio_token":1.65e-6,"input_cost_per_image_token":1.65e-6,"cache_read_input_token_cost":1.65e-7,"search_context_cost_per_query":{"search_context_size_low":0.028,"search_context_size_high":0.028,"search_context_size_medium":0.028},"cache_creation_input_token_cost":9.166666666666675e-8,"output_cost_per_reasoning_token":8.25e-6,"cache_read_input_audio_token_cost":1.65e-7,"google_maps_grounding_cost_per_query":0.015400000000000002},"discount":0.5,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":6},{"id":"command-a-plus-05-2026","object":"model","created":1790102896,"owned_by":"cohere","mode":"chat","context_length":436000,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1.5e-6,"cache_read_input_token_cost":1.5e-7},"pricing_endpoint":"cohere/command-a-plus-05-2026","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"cohere/command-a-plus-05-2026","object":"model","created":1790102896,"owned_by":"cohere","model_name":"command-a-plus-05-2026","context_length":436000,"max_input_tokens":128000,"max_output_tokens":64000,"quantization":"fp8","retirement_date":null,"description":"Command A+ is Cohere's flagship model for enterprise agentic workflows.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1.5e-6,"cache_read_input_token_cost":1.5e-7},"list_pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1.5e-6,"cache_read_input_token_cost":1.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":1},{"id":"qwen3.8-omni-flash","object":"model","created":1789959954,"owned_by":"qwen","mode":"chat","context_length":1000000,"capabilities":{"input_modalities":["text","image","audio","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":9.749999999999999e-8,"output_cost_per_token":3.0550000000000003e-7,"web_search_cost_per_call":0.00037271715},"pricing_endpoint":"qwen/qwen3.8-omni-flash","regions":[{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"qwen/qwen3.8-omni-flash","object":"model","created":1789959954,"owned_by":"qwen","model_name":"qwen3.8-omni-flash","context_length":1000000,"max_input_tokens":983616,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"Qwen3.8 Omni Flash is an omni-modal reasoning model from Alibaba, the first Qwen model built around agentic capabilities with native audio-video understanding.","source":null,"capabilities":{"input_modalities":["text","image","audio","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":9.749999999999999e-8,"output_cost_per_token":3.0550000000000003e-7,"web_search_cost_per_call":0.00037271715},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":4.7e-7,"web_search_cost_per_call":0.000573411},"discount":0.35,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":1},{"id":"gpt-6-astra","object":"model","created":1789744452,"owned_by":"openai","mode":"chat","context_length":1050000,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":0.00001,"output_cost_per_token":0.00005,"input_cost_per_token_flex":5e-6,"output_cost_per_token_flex":0.000025,"cache_read_input_token_cost":1e-6,"input_cost_per_token_batches":5e-6,"input_cost_per_token_priority":0.00002,"output_cost_per_token_batches":0.000025,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"input_cost_per_token_ultrafast":0.00006,"output_cost_per_token_priority":0.0001,"cache_creation_input_token_cost":0.0000125,"output_cost_per_token_ultrafast":0.0003,"cache_read_input_token_cost_flex":5e-7,"cache_read_input_token_cost_batches":5e-7,"cache_creation_input_token_cost_flex":6.25e-6,"cache_read_input_token_cost_priority":2e-6,"cache_read_input_token_cost_ultrafast":6e-6,"input_cost_per_token_above_272k_tokens":0.00002,"output_cost_per_token_above_272k_tokens":0.000075,"cache_creation_input_token_cost_priority":0.000025,"cache_creation_input_token_cost_ultrafast":0.000075,"cache_creation_input_token_cost_above_12hr":0.000025,"input_cost_per_token_above_272k_tokens_flex":0.00001,"output_cost_per_token_above_272k_tokens_flex":0.0000375,"cache_read_input_token_cost_above_272k_tokens":2e-6,"cache_creation_input_token_cost_above_12hr_flex":0.0000125,"input_cost_per_token_above_272k_tokens_priority":0.00004,"input_cost_per_token_above_272k_tokens_ultrafast":0.00012,"output_cost_per_token_above_272k_tokens_priority":0.00015,"cache_creation_input_token_cost_above_272k_tokens":0.000025,"output_cost_per_token_above_272k_tokens_ultrafast":0.00045,"cache_read_input_token_cost_above_272k_tokens_flex":1e-6,"cache_creation_input_token_cost_above_12hr_priority":0.00005,"cache_creation_input_token_cost_above_12hr_ultrafast":0.00015,"cache_creation_input_token_cost_above_272k_tokens_flex":0.0000125,"cache_read_input_token_cost_above_272k_tokens_priority":4e-6,"cache_read_input_token_cost_above_272k_tokens_ultrafast":0.000012,"cache_creation_input_token_cost_above_272k_tokens_priority":0.00005,"cache_creation_input_token_cost_above_272k_tokens_ultrafast":0.00015,"cache_creation_input_token_cost_above_12hr_above_272k_tokens":0.00005,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_flex":0.000025,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_priority":0.0001,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_ultrafast":0.0003},"pricing_endpoint":"openai/gpt-6-astra","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"databricks/databricks-gpt-6-astra@eu","object":"model","created":1789744452,"owned_by":"databricks","model_name":"databricks-gpt-6-astra","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-6 Astra is OpenAI's frontier model for enterprise reasoning and structured document processing. It excels at complex document reasoning and parsing, while offering capable coding and agentic search performance. This model supports multimodal (text and image) inputs and a long context window. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":0.00001,"output_cost_per_token":0.00005,"input_dbu_cost_per_token":0.00014286,"output_dbu_cost_per_token":0.00071429,"cache_read_input_token_cost":1e-6,"cache_creation_input_token_cost":0.0000125,"input_cost_per_token_above_32k_tokens":0.00002,"input_cost_per_token_above_272k_tokens":0.00002,"output_cost_per_token_above_32k_tokens":0.000075,"output_cost_per_token_above_272k_tokens":0.000075,"cache_creation_input_token_cost_priority":0.000025,"cache_read_input_token_cost_above_32k_tokens":2e-6,"cache_read_input_token_cost_above_272k_tokens":2e-6,"input_cost_per_token_above_272k_tokens_priority":0.00004,"cache_creation_input_token_cost_above_32k_tokens":0.000025,"output_cost_per_token_above_272k_tokens_priority":0.00015,"cache_creation_input_token_cost_above_272k_tokens":0.000025,"cache_read_input_token_cost_above_272k_tokens_priority":4e-6,"cache_creation_input_token_cost_above_272k_tokens_priority":0.00005},"list_pricing":{"input_cost_per_token":0.00001,"output_cost_per_token":0.00005,"input_dbu_cost_per_token":0.00014286,"output_dbu_cost_per_token":0.00071429,"cache_read_input_token_cost":1e-6,"cache_creation_input_token_cost":0.0000125,"input_cost_per_token_above_32k_tokens":0.00002,"input_cost_per_token_above_272k_tokens":0.00002,"output_cost_per_token_above_32k_tokens":0.000075,"output_cost_per_token_above_272k_tokens":0.000075,"cache_creation_input_token_cost_priority":0.000025,"cache_read_input_token_cost_above_32k_tokens":2e-6,"cache_read_input_token_cost_above_272k_tokens":2e-6,"input_cost_per_token_above_272k_tokens_priority":0.00004,"cache_creation_input_token_cost_above_32k_tokens":0.000025,"output_cost_per_token_above_272k_tokens_priority":0.00015,"cache_creation_input_token_cost_above_272k_tokens":0.000025,"cache_read_input_token_cost_above_272k_tokens_priority":4e-6,"cache_creation_input_token_cost_above_272k_tokens_priority":0.00005},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"databricks/databricks-gpt-6-astra","object":"model","created":1789744452,"owned_by":"databricks","model_name":"databricks-gpt-6-astra","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-6 Astra is OpenAI's frontier model for enterprise reasoning and structured document processing. It excels at complex document reasoning and parsing, while offering capable coding and agentic search performance. This model supports multimodal (text and image) inputs and a long context window. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":0.00001,"output_cost_per_token":0.00005,"input_dbu_cost_per_token":0.00014286,"output_dbu_cost_per_token":0.00071429,"cache_read_input_token_cost":1e-6,"cache_creation_input_token_cost":0.0000125,"input_cost_per_token_above_32k_tokens":0.00002,"input_cost_per_token_above_272k_tokens":0.00002,"output_cost_per_token_above_32k_tokens":0.000075,"output_cost_per_token_above_272k_tokens":0.000075,"cache_creation_input_token_cost_priority":0.000025,"cache_read_input_token_cost_above_32k_tokens":2e-6,"cache_read_input_token_cost_above_272k_tokens":2e-6,"input_cost_per_token_above_272k_tokens_priority":0.00004,"cache_creation_input_token_cost_above_32k_tokens":0.000025,"output_cost_per_token_above_272k_tokens_priority":0.00015,"cache_creation_input_token_cost_above_272k_tokens":0.000025,"cache_read_input_token_cost_above_272k_tokens_priority":4e-6,"cache_creation_input_token_cost_above_272k_tokens_priority":0.00005},"list_pricing":{"input_cost_per_token":0.00001,"output_cost_per_token":0.00005,"input_dbu_cost_per_token":0.00014286,"output_dbu_cost_per_token":0.00071429,"cache_read_input_token_cost":1e-6,"cache_creation_input_token_cost":0.0000125,"input_cost_per_token_above_32k_tokens":0.00002,"input_cost_per_token_above_272k_tokens":0.00002,"output_cost_per_token_above_32k_tokens":0.000075,"output_cost_per_token_above_272k_tokens":0.000075,"cache_creation_input_token_cost_priority":0.000025,"cache_read_input_token_cost_above_32k_tokens":2e-6,"cache_read_input_token_cost_above_272k_tokens":2e-6,"input_cost_per_token_above_272k_tokens_priority":0.00004,"cache_creation_input_token_cost_above_32k_tokens":0.000025,"output_cost_per_token_above_272k_tokens_priority":0.00015,"cache_creation_input_token_cost_above_272k_tokens":0.000025,"cache_read_input_token_cost_above_272k_tokens_priority":4e-6,"cache_creation_input_token_cost_above_272k_tokens_priority":0.00005},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"amazon/openai.gpt-6-astra","object":"model","created":1789016966,"owned_by":"amazon","model_name":"openai.gpt-6-astra","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":0.000011,"output_cost_per_token":0.000055,"cache_read_input_token_cost":1.1e-6,"input_cost_per_token_ultrafast":0.000066,"cache_creation_input_token_cost":0.00001375,"output_cost_per_token_ultrafast":0.00033,"cache_read_input_token_cost_ultrafast":6.6e-6,"input_cost_per_token_above_272k_tokens":0.000022,"output_cost_per_token_above_272k_tokens":0.0000825,"cache_creation_input_token_cost_ultrafast":0.0000825,"cache_read_input_token_cost_above_272k_tokens":2.2e-6,"input_cost_per_token_above_272k_tokens_ultrafast":0.000132,"cache_creation_input_token_cost_above_272k_tokens":0.0000275,"output_cost_per_token_above_272k_tokens_ultrafast":0.000495,"cache_read_input_token_cost_above_272k_tokens_ultrafast":0.0000132,"cache_creation_input_token_cost_above_272k_tokens_ultrafast":0.000165},"list_pricing":{"input_cost_per_token":0.000011,"output_cost_per_token":0.000055,"cache_read_input_token_cost":1.1e-6,"input_cost_per_token_ultrafast":0.000066,"cache_creation_input_token_cost":0.00001375,"output_cost_per_token_ultrafast":0.00033,"cache_read_input_token_cost_ultrafast":6.6e-6,"input_cost_per_token_above_272k_tokens":0.000022,"output_cost_per_token_above_272k_tokens":0.0000825,"cache_creation_input_token_cost_ultrafast":0.0000825,"cache_read_input_token_cost_above_272k_tokens":2.2e-6,"input_cost_per_token_above_272k_tokens_ultrafast":0.000132,"cache_creation_input_token_cost_above_272k_tokens":0.0000275,"output_cost_per_token_above_272k_tokens_ultrafast":0.000495,"cache_read_input_token_cost_above_272k_tokens_ultrafast":0.0000132,"cache_creation_input_token_cost_above_272k_tokens_ultrafast":0.000165},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"amazon/openai.gpt-6-astra@us","object":"model","created":1789016966,"owned_by":"amazon","model_name":"openai.gpt-6-astra","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":0.000011,"output_cost_per_token":0.000055,"cache_read_input_token_cost":1.1e-6,"input_cost_per_token_ultrafast":0.000066,"cache_creation_input_token_cost":0.00001375,"output_cost_per_token_ultrafast":0.00033,"cache_read_input_token_cost_ultrafast":6.6e-6,"input_cost_per_token_above_272k_tokens":0.000022,"output_cost_per_token_above_272k_tokens":0.0000825,"cache_creation_input_token_cost_ultrafast":0.0000825,"cache_read_input_token_cost_above_272k_tokens":2.2e-6,"input_cost_per_token_above_272k_tokens_ultrafast":0.000132,"cache_creation_input_token_cost_above_272k_tokens":0.0000275,"output_cost_per_token_above_272k_tokens_ultrafast":0.000495,"cache_read_input_token_cost_above_272k_tokens_ultrafast":0.0000132,"cache_creation_input_token_cost_above_272k_tokens_ultrafast":0.000165},"list_pricing":{"input_cost_per_token":0.000011,"output_cost_per_token":0.000055,"cache_read_input_token_cost":1.1e-6,"input_cost_per_token_ultrafast":0.000066,"cache_creation_input_token_cost":0.00001375,"output_cost_per_token_ultrafast":0.00033,"cache_read_input_token_cost_ultrafast":6.6e-6,"input_cost_per_token_above_272k_tokens":0.000022,"output_cost_per_token_above_272k_tokens":0.0000825,"cache_creation_input_token_cost_ultrafast":0.0000825,"cache_read_input_token_cost_above_272k_tokens":2.2e-6,"input_cost_per_token_above_272k_tokens_ultrafast":0.000132,"cache_creation_input_token_cost_above_272k_tokens":0.0000275,"output_cost_per_token_above_272k_tokens_ultrafast":0.000495,"cache_read_input_token_cost_above_272k_tokens_ultrafast":0.0000132,"cache_creation_input_token_cost_above_272k_tokens_ultrafast":0.000165},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null},{"id":"azure/gpt-6-astra","object":"model","created":1788844167,"owned_by":"azure","model_name":"gpt-6-astra","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-6 Astra is OpenAI's flagship model for demanding end-to-end work.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":0.00001,"output_cost_per_token":0.00005,"cache_read_input_token_cost":1e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"cache_creation_input_token_cost":0.0000125,"input_cost_per_token_above_272k_tokens":0.00002,"output_cost_per_token_above_272k_tokens":0.000075,"input_cost_per_token_above_272k_tokens_flex":0.00001,"output_cost_per_token_above_272k_tokens_flex":0.0000375,"cache_read_input_token_cost_above_272k_tokens":2e-6,"cache_creation_input_token_cost_above_272k_tokens":0.000025,"cache_read_input_token_cost_above_272k_tokens_flex":1e-6,"cache_creation_input_token_cost_above_272k_tokens_flex":0.0000125},"list_pricing":{"input_cost_per_token":0.00001,"output_cost_per_token":0.00005,"cache_read_input_token_cost":1e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"cache_creation_input_token_cost":0.0000125,"input_cost_per_token_above_272k_tokens":0.00002,"output_cost_per_token_above_272k_tokens":0.000075,"input_cost_per_token_above_272k_tokens_flex":0.00001,"output_cost_per_token_above_272k_tokens_flex":0.0000375,"cache_read_input_token_cost_above_272k_tokens":2e-6,"cache_creation_input_token_cost_above_272k_tokens":0.000025,"cache_read_input_token_cost_above_272k_tokens_flex":1e-6,"cache_creation_input_token_cost_above_272k_tokens_flex":0.0000125},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"azure/gpt-6-astra@us","object":"model","created":1788844167,"owned_by":"azure","model_name":"gpt-6-astra","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-6 Astra is OpenAI's flagship model for demanding end-to-end work.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":0.000011000000000000001,"output_cost_per_token":0.00005500000000000001,"cache_read_input_token_cost":1.1e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"cache_creation_input_token_cost":0.000013750000000000002,"input_cost_per_token_above_272k_tokens":0.000022000000000000003,"output_cost_per_token_above_272k_tokens":0.0000825,"input_cost_per_token_above_272k_tokens_flex":0.000011000000000000001,"output_cost_per_token_above_272k_tokens_flex":0.00004125,"cache_read_input_token_cost_above_272k_tokens":2.2e-6,"cache_creation_input_token_cost_above_272k_tokens":0.000027500000000000004,"cache_read_input_token_cost_above_272k_tokens_flex":1.1e-6,"cache_creation_input_token_cost_above_272k_tokens_flex":0.000013750000000000002},"list_pricing":{"input_cost_per_token":0.000011000000000000001,"output_cost_per_token":0.00005500000000000001,"cache_read_input_token_cost":1.1e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"cache_creation_input_token_cost":0.000013750000000000002,"input_cost_per_token_above_272k_tokens":0.000022000000000000003,"output_cost_per_token_above_272k_tokens":0.0000825,"input_cost_per_token_above_272k_tokens_flex":0.000011000000000000001,"output_cost_per_token_above_272k_tokens_flex":0.00004125,"cache_read_input_token_cost_above_272k_tokens":2.2e-6,"cache_creation_input_token_cost_above_272k_tokens":0.000027500000000000004,"cache_read_input_token_cost_above_272k_tokens_flex":1.1e-6,"cache_creation_input_token_cost_above_272k_tokens_flex":0.000013750000000000002},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"openai/gpt-6-astra","object":"model","created":1788552838,"owned_by":"openai","model_name":"gpt-6-astra","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-6 Astra is OpenAI's flagship model for demanding end-to-end work.","source":null,"capabilities":{"input_modalities":["file","image","text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":0.00001,"output_cost_per_token":0.00005,"input_cost_per_token_flex":5e-6,"output_cost_per_token_flex":0.000025,"cache_read_input_token_cost":1e-6,"input_cost_per_token_batches":5e-6,"input_cost_per_token_priority":0.00002,"output_cost_per_token_batches":0.000025,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"input_cost_per_token_ultrafast":0.00006,"output_cost_per_token_priority":0.0001,"cache_creation_input_token_cost":0.0000125,"output_cost_per_token_ultrafast":0.0003,"cache_read_input_token_cost_flex":5e-7,"cache_read_input_token_cost_batches":5e-7,"cache_creation_input_token_cost_flex":6.25e-6,"cache_read_input_token_cost_priority":2e-6,"cache_read_input_token_cost_ultrafast":6e-6,"input_cost_per_token_above_272k_tokens":0.00002,"output_cost_per_token_above_272k_tokens":0.000075,"cache_creation_input_token_cost_priority":0.000025,"cache_creation_input_token_cost_ultrafast":0.000075,"cache_creation_input_token_cost_above_12hr":0.000025,"input_cost_per_token_above_272k_tokens_flex":0.00001,"output_cost_per_token_above_272k_tokens_flex":0.0000375,"cache_read_input_token_cost_above_272k_tokens":2e-6,"cache_creation_input_token_cost_above_12hr_flex":0.0000125,"input_cost_per_token_above_272k_tokens_priority":0.00004,"input_cost_per_token_above_272k_tokens_ultrafast":0.00012,"output_cost_per_token_above_272k_tokens_priority":0.00015,"cache_creation_input_token_cost_above_272k_tokens":0.000025,"output_cost_per_token_above_272k_tokens_ultrafast":0.00045,"cache_read_input_token_cost_above_272k_tokens_flex":1e-6,"cache_creation_input_token_cost_above_12hr_priority":0.00005,"cache_creation_input_token_cost_above_12hr_ultrafast":0.00015,"cache_creation_input_token_cost_above_272k_tokens_flex":0.0000125,"cache_read_input_token_cost_above_272k_tokens_priority":4e-6,"cache_read_input_token_cost_above_272k_tokens_ultrafast":0.000012,"cache_creation_input_token_cost_above_272k_tokens_priority":0.00005,"cache_creation_input_token_cost_above_272k_tokens_ultrafast":0.00015,"cache_creation_input_token_cost_above_12hr_above_272k_tokens":0.00005,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_flex":0.000025,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_priority":0.0001,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_ultrafast":0.0003},"list_pricing":{"input_cost_per_token":0.00001,"output_cost_per_token":0.00005,"input_cost_per_token_flex":5e-6,"output_cost_per_token_flex":0.000025,"cache_read_input_token_cost":1e-6,"input_cost_per_token_batches":5e-6,"input_cost_per_token_priority":0.00002,"output_cost_per_token_batches":0.000025,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"input_cost_per_token_ultrafast":0.00006,"output_cost_per_token_priority":0.0001,"cache_creation_input_token_cost":0.0000125,"output_cost_per_token_ultrafast":0.0003,"cache_read_input_token_cost_flex":5e-7,"cache_read_input_token_cost_batches":5e-7,"cache_creation_input_token_cost_flex":6.25e-6,"cache_read_input_token_cost_priority":2e-6,"cache_read_input_token_cost_ultrafast":6e-6,"input_cost_per_token_above_272k_tokens":0.00002,"output_cost_per_token_above_272k_tokens":0.000075,"cache_creation_input_token_cost_priority":0.000025,"cache_creation_input_token_cost_ultrafast":0.000075,"cache_creation_input_token_cost_above_12hr":0.000025,"input_cost_per_token_above_272k_tokens_flex":0.00001,"output_cost_per_token_above_272k_tokens_flex":0.0000375,"cache_read_input_token_cost_above_272k_tokens":2e-6,"cache_creation_input_token_cost_above_12hr_flex":0.0000125,"input_cost_per_token_above_272k_tokens_priority":0.00004,"input_cost_per_token_above_272k_tokens_ultrafast":0.00012,"output_cost_per_token_above_272k_tokens_priority":0.00015,"cache_creation_input_token_cost_above_272k_tokens":0.000025,"output_cost_per_token_above_272k_tokens_ultrafast":0.00045,"cache_read_input_token_cost_above_272k_tokens_flex":1e-6,"cache_creation_input_token_cost_above_12hr_priority":0.00005,"cache_creation_input_token_cost_above_12hr_ultrafast":0.00015,"cache_creation_input_token_cost_above_272k_tokens_flex":0.0000125,"cache_read_input_token_cost_above_272k_tokens_priority":4e-6,"cache_read_input_token_cost_above_272k_tokens_ultrafast":0.000012,"cache_creation_input_token_cost_above_272k_tokens_priority":0.00005,"cache_creation_input_token_cost_above_272k_tokens_ultrafast":0.00015,"cache_creation_input_token_cost_above_12hr_above_272k_tokens":0.00005,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_flex":0.000025,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_priority":0.0001,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_ultrafast":0.0003},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":7},{"id":"~gpt-astra-latest","object":"model","created":1789744452,"owned_by":"openai","mode":"chat","context_length":1050000,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":0.00001,"output_cost_per_token":0.00005,"input_cost_per_token_flex":5e-6,"output_cost_per_token_flex":0.000025,"cache_read_input_token_cost":1e-6,"input_cost_per_token_batches":5e-6,"input_cost_per_token_priority":0.00002,"output_cost_per_token_batches":0.000025,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"input_cost_per_token_ultrafast":0.00006,"output_cost_per_token_priority":0.0001,"cache_creation_input_token_cost":0.0000125,"output_cost_per_token_ultrafast":0.0003,"cache_read_input_token_cost_flex":5e-7,"cache_read_input_token_cost_batches":5e-7,"cache_creation_input_token_cost_flex":6.25e-6,"cache_read_input_token_cost_priority":2e-6,"cache_read_input_token_cost_ultrafast":6e-6,"input_cost_per_token_above_272k_tokens":0.00002,"output_cost_per_token_above_272k_tokens":0.000075,"cache_creation_input_token_cost_priority":0.000025,"cache_creation_input_token_cost_ultrafast":0.000075,"cache_creation_input_token_cost_above_12hr":0.000025,"input_cost_per_token_above_272k_tokens_flex":0.00001,"output_cost_per_token_above_272k_tokens_flex":0.0000375,"cache_read_input_token_cost_above_272k_tokens":2e-6,"cache_creation_input_token_cost_above_12hr_flex":0.0000125,"input_cost_per_token_above_272k_tokens_priority":0.00004,"input_cost_per_token_above_272k_tokens_ultrafast":0.00012,"output_cost_per_token_above_272k_tokens_priority":0.00015,"cache_creation_input_token_cost_above_272k_tokens":0.000025,"output_cost_per_token_above_272k_tokens_ultrafast":0.00045,"cache_read_input_token_cost_above_272k_tokens_flex":1e-6,"cache_creation_input_token_cost_above_12hr_priority":0.00005,"cache_creation_input_token_cost_above_12hr_ultrafast":0.00015,"cache_creation_input_token_cost_above_272k_tokens_flex":0.0000125,"cache_read_input_token_cost_above_272k_tokens_priority":4e-6,"cache_read_input_token_cost_above_272k_tokens_ultrafast":0.000012,"cache_creation_input_token_cost_above_272k_tokens_priority":0.00005,"cache_creation_input_token_cost_above_272k_tokens_ultrafast":0.00015,"cache_creation_input_token_cost_above_12hr_above_272k_tokens":0.00005,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_flex":0.000025,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_priority":0.0001,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_ultrafast":0.0003},"pricing_endpoint":"openai/gpt-6-astra","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":"gpt-6-astra","endpoints":[{"id":"databricks/databricks-gpt-6-astra@eu","object":"model","created":1789744452,"owned_by":"databricks","model_name":"databricks-gpt-6-astra","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-6 Astra is OpenAI's frontier model for enterprise reasoning and structured document processing. It excels at complex document reasoning and parsing, while offering capable coding and agentic search performance. This model supports multimodal (text and image) inputs and a long context window. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":0.00001,"output_cost_per_token":0.00005,"input_dbu_cost_per_token":0.00014286,"output_dbu_cost_per_token":0.00071429,"cache_read_input_token_cost":1e-6,"cache_creation_input_token_cost":0.0000125,"input_cost_per_token_above_32k_tokens":0.00002,"input_cost_per_token_above_272k_tokens":0.00002,"output_cost_per_token_above_32k_tokens":0.000075,"output_cost_per_token_above_272k_tokens":0.000075,"cache_creation_input_token_cost_priority":0.000025,"cache_read_input_token_cost_above_32k_tokens":2e-6,"cache_read_input_token_cost_above_272k_tokens":2e-6,"input_cost_per_token_above_272k_tokens_priority":0.00004,"cache_creation_input_token_cost_above_32k_tokens":0.000025,"output_cost_per_token_above_272k_tokens_priority":0.00015,"cache_creation_input_token_cost_above_272k_tokens":0.000025,"cache_read_input_token_cost_above_272k_tokens_priority":4e-6,"cache_creation_input_token_cost_above_272k_tokens_priority":0.00005},"list_pricing":{"input_cost_per_token":0.00001,"output_cost_per_token":0.00005,"input_dbu_cost_per_token":0.00014286,"output_dbu_cost_per_token":0.00071429,"cache_read_input_token_cost":1e-6,"cache_creation_input_token_cost":0.0000125,"input_cost_per_token_above_32k_tokens":0.00002,"input_cost_per_token_above_272k_tokens":0.00002,"output_cost_per_token_above_32k_tokens":0.000075,"output_cost_per_token_above_272k_tokens":0.000075,"cache_creation_input_token_cost_priority":0.000025,"cache_read_input_token_cost_above_32k_tokens":2e-6,"cache_read_input_token_cost_above_272k_tokens":2e-6,"input_cost_per_token_above_272k_tokens_priority":0.00004,"cache_creation_input_token_cost_above_32k_tokens":0.000025,"output_cost_per_token_above_272k_tokens_priority":0.00015,"cache_creation_input_token_cost_above_272k_tokens":0.000025,"cache_read_input_token_cost_above_272k_tokens_priority":4e-6,"cache_creation_input_token_cost_above_272k_tokens_priority":0.00005},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"databricks/databricks-gpt-6-astra","object":"model","created":1789744452,"owned_by":"databricks","model_name":"databricks-gpt-6-astra","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-6 Astra is OpenAI's frontier model for enterprise reasoning and structured document processing. It excels at complex document reasoning and parsing, while offering capable coding and agentic search performance. This model supports multimodal (text and image) inputs and a long context window. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":0.00001,"output_cost_per_token":0.00005,"input_dbu_cost_per_token":0.00014286,"output_dbu_cost_per_token":0.00071429,"cache_read_input_token_cost":1e-6,"cache_creation_input_token_cost":0.0000125,"input_cost_per_token_above_32k_tokens":0.00002,"input_cost_per_token_above_272k_tokens":0.00002,"output_cost_per_token_above_32k_tokens":0.000075,"output_cost_per_token_above_272k_tokens":0.000075,"cache_creation_input_token_cost_priority":0.000025,"cache_read_input_token_cost_above_32k_tokens":2e-6,"cache_read_input_token_cost_above_272k_tokens":2e-6,"input_cost_per_token_above_272k_tokens_priority":0.00004,"cache_creation_input_token_cost_above_32k_tokens":0.000025,"output_cost_per_token_above_272k_tokens_priority":0.00015,"cache_creation_input_token_cost_above_272k_tokens":0.000025,"cache_read_input_token_cost_above_272k_tokens_priority":4e-6,"cache_creation_input_token_cost_above_272k_tokens_priority":0.00005},"list_pricing":{"input_cost_per_token":0.00001,"output_cost_per_token":0.00005,"input_dbu_cost_per_token":0.00014286,"output_dbu_cost_per_token":0.00071429,"cache_read_input_token_cost":1e-6,"cache_creation_input_token_cost":0.0000125,"input_cost_per_token_above_32k_tokens":0.00002,"input_cost_per_token_above_272k_tokens":0.00002,"output_cost_per_token_above_32k_tokens":0.000075,"output_cost_per_token_above_272k_tokens":0.000075,"cache_creation_input_token_cost_priority":0.000025,"cache_read_input_token_cost_above_32k_tokens":2e-6,"cache_read_input_token_cost_above_272k_tokens":2e-6,"input_cost_per_token_above_272k_tokens_priority":0.00004,"cache_creation_input_token_cost_above_32k_tokens":0.000025,"output_cost_per_token_above_272k_tokens_priority":0.00015,"cache_creation_input_token_cost_above_272k_tokens":0.000025,"cache_read_input_token_cost_above_272k_tokens_priority":4e-6,"cache_creation_input_token_cost_above_272k_tokens_priority":0.00005},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"amazon/openai.gpt-6-astra","object":"model","created":1789016966,"owned_by":"amazon","model_name":"openai.gpt-6-astra","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":0.000011,"output_cost_per_token":0.000055,"cache_read_input_token_cost":1.1e-6,"input_cost_per_token_ultrafast":0.000066,"cache_creation_input_token_cost":0.00001375,"output_cost_per_token_ultrafast":0.00033,"cache_read_input_token_cost_ultrafast":6.6e-6,"input_cost_per_token_above_272k_tokens":0.000022,"output_cost_per_token_above_272k_tokens":0.0000825,"cache_creation_input_token_cost_ultrafast":0.0000825,"cache_read_input_token_cost_above_272k_tokens":2.2e-6,"input_cost_per_token_above_272k_tokens_ultrafast":0.000132,"cache_creation_input_token_cost_above_272k_tokens":0.0000275,"output_cost_per_token_above_272k_tokens_ultrafast":0.000495,"cache_read_input_token_cost_above_272k_tokens_ultrafast":0.0000132,"cache_creation_input_token_cost_above_272k_tokens_ultrafast":0.000165},"list_pricing":{"input_cost_per_token":0.000011,"output_cost_per_token":0.000055,"cache_read_input_token_cost":1.1e-6,"input_cost_per_token_ultrafast":0.000066,"cache_creation_input_token_cost":0.00001375,"output_cost_per_token_ultrafast":0.00033,"cache_read_input_token_cost_ultrafast":6.6e-6,"input_cost_per_token_above_272k_tokens":0.000022,"output_cost_per_token_above_272k_tokens":0.0000825,"cache_creation_input_token_cost_ultrafast":0.0000825,"cache_read_input_token_cost_above_272k_tokens":2.2e-6,"input_cost_per_token_above_272k_tokens_ultrafast":0.000132,"cache_creation_input_token_cost_above_272k_tokens":0.0000275,"output_cost_per_token_above_272k_tokens_ultrafast":0.000495,"cache_read_input_token_cost_above_272k_tokens_ultrafast":0.0000132,"cache_creation_input_token_cost_above_272k_tokens_ultrafast":0.000165},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"amazon/openai.gpt-6-astra@us","object":"model","created":1789016966,"owned_by":"amazon","model_name":"openai.gpt-6-astra","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":0.000011,"output_cost_per_token":0.000055,"cache_read_input_token_cost":1.1e-6,"input_cost_per_token_ultrafast":0.000066,"cache_creation_input_token_cost":0.00001375,"output_cost_per_token_ultrafast":0.00033,"cache_read_input_token_cost_ultrafast":6.6e-6,"input_cost_per_token_above_272k_tokens":0.000022,"output_cost_per_token_above_272k_tokens":0.0000825,"cache_creation_input_token_cost_ultrafast":0.0000825,"cache_read_input_token_cost_above_272k_tokens":2.2e-6,"input_cost_per_token_above_272k_tokens_ultrafast":0.000132,"cache_creation_input_token_cost_above_272k_tokens":0.0000275,"output_cost_per_token_above_272k_tokens_ultrafast":0.000495,"cache_read_input_token_cost_above_272k_tokens_ultrafast":0.0000132,"cache_creation_input_token_cost_above_272k_tokens_ultrafast":0.000165},"list_pricing":{"input_cost_per_token":0.000011,"output_cost_per_token":0.000055,"cache_read_input_token_cost":1.1e-6,"input_cost_per_token_ultrafast":0.000066,"cache_creation_input_token_cost":0.00001375,"output_cost_per_token_ultrafast":0.00033,"cache_read_input_token_cost_ultrafast":6.6e-6,"input_cost_per_token_above_272k_tokens":0.000022,"output_cost_per_token_above_272k_tokens":0.0000825,"cache_creation_input_token_cost_ultrafast":0.0000825,"cache_read_input_token_cost_above_272k_tokens":2.2e-6,"input_cost_per_token_above_272k_tokens_ultrafast":0.000132,"cache_creation_input_token_cost_above_272k_tokens":0.0000275,"output_cost_per_token_above_272k_tokens_ultrafast":0.000495,"cache_read_input_token_cost_above_272k_tokens_ultrafast":0.0000132,"cache_creation_input_token_cost_above_272k_tokens_ultrafast":0.000165},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null},{"id":"azure/gpt-6-astra","object":"model","created":1788844167,"owned_by":"azure","model_name":"gpt-6-astra","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-6 Astra is OpenAI's flagship model for demanding end-to-end work.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":0.00001,"output_cost_per_token":0.00005,"cache_read_input_token_cost":1e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"cache_creation_input_token_cost":0.0000125,"input_cost_per_token_above_272k_tokens":0.00002,"output_cost_per_token_above_272k_tokens":0.000075,"input_cost_per_token_above_272k_tokens_flex":0.00001,"output_cost_per_token_above_272k_tokens_flex":0.0000375,"cache_read_input_token_cost_above_272k_tokens":2e-6,"cache_creation_input_token_cost_above_272k_tokens":0.000025,"cache_read_input_token_cost_above_272k_tokens_flex":1e-6,"cache_creation_input_token_cost_above_272k_tokens_flex":0.0000125},"list_pricing":{"input_cost_per_token":0.00001,"output_cost_per_token":0.00005,"cache_read_input_token_cost":1e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"cache_creation_input_token_cost":0.0000125,"input_cost_per_token_above_272k_tokens":0.00002,"output_cost_per_token_above_272k_tokens":0.000075,"input_cost_per_token_above_272k_tokens_flex":0.00001,"output_cost_per_token_above_272k_tokens_flex":0.0000375,"cache_read_input_token_cost_above_272k_tokens":2e-6,"cache_creation_input_token_cost_above_272k_tokens":0.000025,"cache_read_input_token_cost_above_272k_tokens_flex":1e-6,"cache_creation_input_token_cost_above_272k_tokens_flex":0.0000125},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"azure/gpt-6-astra@us","object":"model","created":1788844167,"owned_by":"azure","model_name":"gpt-6-astra","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-6 Astra is OpenAI's flagship model for demanding end-to-end work.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":0.000011000000000000001,"output_cost_per_token":0.00005500000000000001,"cache_read_input_token_cost":1.1e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"cache_creation_input_token_cost":0.000013750000000000002,"input_cost_per_token_above_272k_tokens":0.000022000000000000003,"output_cost_per_token_above_272k_tokens":0.0000825,"input_cost_per_token_above_272k_tokens_flex":0.000011000000000000001,"output_cost_per_token_above_272k_tokens_flex":0.00004125,"cache_read_input_token_cost_above_272k_tokens":2.2e-6,"cache_creation_input_token_cost_above_272k_tokens":0.000027500000000000004,"cache_read_input_token_cost_above_272k_tokens_flex":1.1e-6,"cache_creation_input_token_cost_above_272k_tokens_flex":0.000013750000000000002},"list_pricing":{"input_cost_per_token":0.000011000000000000001,"output_cost_per_token":0.00005500000000000001,"cache_read_input_token_cost":1.1e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"cache_creation_input_token_cost":0.000013750000000000002,"input_cost_per_token_above_272k_tokens":0.000022000000000000003,"output_cost_per_token_above_272k_tokens":0.0000825,"input_cost_per_token_above_272k_tokens_flex":0.000011000000000000001,"output_cost_per_token_above_272k_tokens_flex":0.00004125,"cache_read_input_token_cost_above_272k_tokens":2.2e-6,"cache_creation_input_token_cost_above_272k_tokens":0.000027500000000000004,"cache_read_input_token_cost_above_272k_tokens_flex":1.1e-6,"cache_creation_input_token_cost_above_272k_tokens_flex":0.000013750000000000002},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"openai/gpt-6-astra","object":"model","created":1788552838,"owned_by":"openai","model_name":"gpt-6-astra","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-6 Astra is OpenAI's flagship model for demanding end-to-end work.","source":null,"capabilities":{"input_modalities":["file","image","text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":0.00001,"output_cost_per_token":0.00005,"input_cost_per_token_flex":5e-6,"output_cost_per_token_flex":0.000025,"cache_read_input_token_cost":1e-6,"input_cost_per_token_batches":5e-6,"input_cost_per_token_priority":0.00002,"output_cost_per_token_batches":0.000025,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"input_cost_per_token_ultrafast":0.00006,"output_cost_per_token_priority":0.0001,"cache_creation_input_token_cost":0.0000125,"output_cost_per_token_ultrafast":0.0003,"cache_read_input_token_cost_flex":5e-7,"cache_read_input_token_cost_batches":5e-7,"cache_creation_input_token_cost_flex":6.25e-6,"cache_read_input_token_cost_priority":2e-6,"cache_read_input_token_cost_ultrafast":6e-6,"input_cost_per_token_above_272k_tokens":0.00002,"output_cost_per_token_above_272k_tokens":0.000075,"cache_creation_input_token_cost_priority":0.000025,"cache_creation_input_token_cost_ultrafast":0.000075,"cache_creation_input_token_cost_above_12hr":0.000025,"input_cost_per_token_above_272k_tokens_flex":0.00001,"output_cost_per_token_above_272k_tokens_flex":0.0000375,"cache_read_input_token_cost_above_272k_tokens":2e-6,"cache_creation_input_token_cost_above_12hr_flex":0.0000125,"input_cost_per_token_above_272k_tokens_priority":0.00004,"input_cost_per_token_above_272k_tokens_ultrafast":0.00012,"output_cost_per_token_above_272k_tokens_priority":0.00015,"cache_creation_input_token_cost_above_272k_tokens":0.000025,"output_cost_per_token_above_272k_tokens_ultrafast":0.00045,"cache_read_input_token_cost_above_272k_tokens_flex":1e-6,"cache_creation_input_token_cost_above_12hr_priority":0.00005,"cache_creation_input_token_cost_above_12hr_ultrafast":0.00015,"cache_creation_input_token_cost_above_272k_tokens_flex":0.0000125,"cache_read_input_token_cost_above_272k_tokens_priority":4e-6,"cache_read_input_token_cost_above_272k_tokens_ultrafast":0.000012,"cache_creation_input_token_cost_above_272k_tokens_priority":0.00005,"cache_creation_input_token_cost_above_272k_tokens_ultrafast":0.00015,"cache_creation_input_token_cost_above_12hr_above_272k_tokens":0.00005,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_flex":0.000025,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_priority":0.0001,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_ultrafast":0.0003},"list_pricing":{"input_cost_per_token":0.00001,"output_cost_per_token":0.00005,"input_cost_per_token_flex":5e-6,"output_cost_per_token_flex":0.000025,"cache_read_input_token_cost":1e-6,"input_cost_per_token_batches":5e-6,"input_cost_per_token_priority":0.00002,"output_cost_per_token_batches":0.000025,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"input_cost_per_token_ultrafast":0.00006,"output_cost_per_token_priority":0.0001,"cache_creation_input_token_cost":0.0000125,"output_cost_per_token_ultrafast":0.0003,"cache_read_input_token_cost_flex":5e-7,"cache_read_input_token_cost_batches":5e-7,"cache_creation_input_token_cost_flex":6.25e-6,"cache_read_input_token_cost_priority":2e-6,"cache_read_input_token_cost_ultrafast":6e-6,"input_cost_per_token_above_272k_tokens":0.00002,"output_cost_per_token_above_272k_tokens":0.000075,"cache_creation_input_token_cost_priority":0.000025,"cache_creation_input_token_cost_ultrafast":0.000075,"cache_creation_input_token_cost_above_12hr":0.000025,"input_cost_per_token_above_272k_tokens_flex":0.00001,"output_cost_per_token_above_272k_tokens_flex":0.0000375,"cache_read_input_token_cost_above_272k_tokens":2e-6,"cache_creation_input_token_cost_above_12hr_flex":0.0000125,"input_cost_per_token_above_272k_tokens_priority":0.00004,"input_cost_per_token_above_272k_tokens_ultrafast":0.00012,"output_cost_per_token_above_272k_tokens_priority":0.00015,"cache_creation_input_token_cost_above_272k_tokens":0.000025,"output_cost_per_token_above_272k_tokens_ultrafast":0.00045,"cache_read_input_token_cost_above_272k_tokens_flex":1e-6,"cache_creation_input_token_cost_above_12hr_priority":0.00005,"cache_creation_input_token_cost_above_12hr_ultrafast":0.00015,"cache_creation_input_token_cost_above_272k_tokens_flex":0.0000125,"cache_read_input_token_cost_above_272k_tokens_priority":4e-6,"cache_read_input_token_cost_above_272k_tokens_ultrafast":0.000012,"cache_creation_input_token_cost_above_272k_tokens_priority":0.00005,"cache_creation_input_token_cost_above_272k_tokens_ultrafast":0.00015,"cache_creation_input_token_cost_above_12hr_above_272k_tokens":0.00005,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_flex":0.000025,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_priority":0.0001,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_ultrafast":0.0003},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":7},{"id":"glm-5","object":"model","created":1789621775,"owned_by":"zai","mode":"chat","context_length":1048576,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6e-7,"output_cost_per_token":2.08e-6,"cache_read_input_token_cost":1.2e-7},"pricing_endpoint":"deepinfra/zai-org/GLM-5","regions":[{"code":"ap","name":"Asia"},{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"mistral/zai-glm-5@eu","object":"model","created":1789621775,"owned_by":"mistral","model_name":"zai-glm-5","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.54e-6,"output_cost_per_token":4.84e-6,"cache_read_input_token_cost":1.5400000000000003e-7,"input_cost_per_token_batches":7.7e-7,"output_cost_per_token_batches":2.42e-6,"cache_read_input_token_cost_batches":7.700000000000001e-8},"list_pricing":{"input_cost_per_token":1.54e-6,"output_cost_per_token":4.84e-6,"cache_read_input_token_cost":1.5400000000000003e-7,"input_cost_per_token_batches":7.7e-7,"output_cost_per_token_batches":2.42e-6,"cache_read_input_token_cost_batches":7.700000000000001e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"mistral/zai-glm-5","object":"model","created":1789621775,"owned_by":"mistral","model_name":"zai-glm-5","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.4e-6,"output_cost_per_token":4.4e-6,"cache_read_input_token_cost":1.4e-7,"input_cost_per_token_batches":7e-7,"output_cost_per_token_batches":2.2e-6,"cache_read_input_token_cost_batches":7e-8},"list_pricing":{"input_cost_per_token":1.4e-6,"output_cost_per_token":4.4e-6,"cache_read_input_token_cost":1.4e-7,"input_cost_per_token_batches":7e-7,"output_cost_per_token_batches":2.2e-6,"cache_read_input_token_cost_batches":7e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"tensorx/z-ai/glm-5","object":"model","created":1787003349,"owned_by":"tensorx","model_name":"z-ai/glm-5","context_length":202752,"max_input_tokens":202752,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"Served by TensorX at fp8 quantization.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":3.2e-6,"cache_read_input_token_cost":2.5e-7},"list_pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":3.2e-6,"cache_read_input_token_cost":2.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/zai.glm-5","object":"model","created":1775193119,"owned_by":"amazon","model_name":"zai.glm-5","context_length":200000,"max_input_tokens":200000,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":null,"source":"https://aws.amazon.com/bedrock/pricing/","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":3.2e-6,"input_cost_per_token_flex":5e-7,"output_cost_per_token_flex":1.6e-6,"input_cost_per_token_priority":1.75e-6,"output_cost_per_token_priority":5.6e-6},"list_pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":3.2e-6,"input_cost_per_token_flex":5e-7,"output_cost_per_token_flex":1.6e-6,"input_cost_per_token_priority":1.75e-6,"output_cost_per_token_priority":5.6e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/zai.glm-5@us","object":"model","created":1775193119,"owned_by":"amazon","model_name":"zai.glm-5","context_length":200000,"max_input_tokens":200000,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":null,"source":"https://aws.amazon.com/bedrock/pricing/","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":3.2e-6,"input_cost_per_token_flex":5e-7,"output_cost_per_token_flex":1.6e-6,"input_cost_per_token_priority":1.75e-6,"output_cost_per_token_priority":5.6e-6},"list_pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":3.2e-6,"input_cost_per_token_flex":5e-7,"output_cost_per_token_flex":1.6e-6,"input_cost_per_token_priority":1.75e-6,"output_cost_per_token_priority":5.6e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"deepinfra/zai-org/GLM-5","object":"model","created":1770829182,"owned_by":"deepinfra","model_name":"zai-org/GLM-5","context_length":202752,"max_input_tokens":null,"max_output_tokens":16384,"quantization":null,"retirement_date":null,"description":"GLM-5 is Z.ai’s flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows. Built for expert developers, it delivers production-grade performance on large-scale programming tasks, rivaling leading...","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6e-7,"output_cost_per_token":2.08e-6,"cache_read_input_token_cost":1.2e-7},"list_pricing":{"input_cost_per_token":6e-7,"output_cost_per_token":2.08e-6,"cache_read_input_token_cost":1.2e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"zai/glm-5","object":"model","created":1770829182,"owned_by":"zai","model_name":"glm-5","context_length":202752,"max_input_tokens":200000,"max_output_tokens":131072,"quantization":"fp8","retirement_date":null,"description":"GLM-5 is Z.ai’s flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":3.2e-6,"cache_read_input_token_cost":2e-7,"cache_creation_input_token_cost":0.0},"list_pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":3.2e-6,"cache_read_input_token_cost":2e-7,"cache_creation_input_token_cost":0.0},"discount":null,"discount_ends_at":null,"regions":[{"code":"ap","name":"Asia"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":7},{"id":"glm-latest","object":"model","created":1789621775,"owned_by":"zai","mode":"chat","context_length":1048576,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.4e-6,"output_cost_per_token":4.4e-6,"cache_read_input_token_cost":1.4e-7,"input_cost_per_token_batches":7e-7,"output_cost_per_token_batches":2.2e-6,"cache_read_input_token_cost_batches":7e-8},"pricing_endpoint":"mistral/zai-glm-latest","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"mistral/zai-glm-latest@eu","object":"model","created":1789621775,"owned_by":"mistral","model_name":"zai-glm-latest","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.54e-6,"output_cost_per_token":4.84e-6,"cache_read_input_token_cost":1.5400000000000003e-7,"input_cost_per_token_batches":7.7e-7,"output_cost_per_token_batches":2.42e-6,"cache_read_input_token_cost_batches":7.700000000000001e-8},"list_pricing":{"input_cost_per_token":1.54e-6,"output_cost_per_token":4.84e-6,"cache_read_input_token_cost":1.5400000000000003e-7,"input_cost_per_token_batches":7.7e-7,"output_cost_per_token_batches":2.42e-6,"cache_read_input_token_cost_batches":7.700000000000001e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"mistral/zai-glm-latest","object":"model","created":1789621775,"owned_by":"mistral","model_name":"zai-glm-latest","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.4e-6,"output_cost_per_token":4.4e-6,"cache_read_input_token_cost":1.4e-7,"input_cost_per_token_batches":7e-7,"output_cost_per_token_batches":2.2e-6,"cache_read_input_token_cost_batches":7e-8},"list_pricing":{"input_cost_per_token":1.4e-6,"output_cost_per_token":4.4e-6,"cache_read_input_token_cost":1.4e-7,"input_cost_per_token_batches":7e-7,"output_cost_per_token_batches":2.2e-6,"cache_read_input_token_cost_batches":7e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"palmyra-vision-7b","object":"model","created":1789621775,"owned_by":"writer","mode":"chat","context_length":4096,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"input_cost_per_token_flex":7.5e-8,"output_cost_per_token_flex":3e-7,"input_cost_per_token_priority":2.625e-7,"output_cost_per_token_priority":1.05e-6},"pricing_endpoint":"amazon/writer.palmyra-vision-7b","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"amazon/writer.palmyra-vision-7b","object":"model","created":1789621775,"owned_by":"amazon","model_name":"writer.palmyra-vision-7b","context_length":4096,"max_input_tokens":4096,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"input_cost_per_token_flex":7.5e-8,"output_cost_per_token_flex":3e-7,"input_cost_per_token_priority":2.625e-7,"output_cost_per_token_priority":1.05e-6},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"input_cost_per_token_flex":7.5e-8,"output_cost_per_token_flex":3e-7,"input_cost_per_token_priority":2.625e-7,"output_cost_per_token_priority":1.05e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"glm-5.3-fast","object":"model","created":1789448988,"owned_by":"zai","mode":"chat","context_length":1048576,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.1e-6,"output_cost_per_token":6.6e-6,"cache_read_input_token_cost":3.9e-7},"pricing_endpoint":"fireworks_ai/accounts/fireworks/routers/glm-5p3-fast","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"fireworks_ai/accounts/fireworks/routers/glm-5p3-fast","object":"model","created":1789448988,"owned_by":"fireworks_ai","model_name":"accounts/fireworks/routers/glm-5p3-fast","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.1e-6,"output_cost_per_token":6.6e-6,"cache_read_input_token_cost":3.9e-7},"list_pricing":{"input_cost_per_token":2.1e-6,"output_cost_per_token":6.6e-6,"cache_read_input_token_cost":3.9e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"qwen3.8-flash","object":"model","created":1789386122,"owned_by":"qwen","mode":"chat","context_length":1000000,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":9.749999999999999e-8,"output_cost_per_token":3.055e-7,"cache_read_input_token_cost":1.04e-8,"cache_creation_input_token_cost":1.3000000000000003e-7},"pricing_endpoint":"qwen/qwen3.8-flash","regions":[{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"deepinfra/Qwen/Qwen3.8-Flash","object":"model","created":1789386122,"owned_by":"deepinfra","model_name":"Qwen/Qwen3.8-Flash","context_length":1000000,"max_input_tokens":null,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"Qwen3.8 Flash is a multimodal reasoning model from Alibaba. It is suited for coding assistance, agentic workflows, visual understanding, document and codebase analysis, desktop interaction, chart analysis, and long-video analysis.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.13e-7,"output_cost_per_token":3.82e-7,"cache_read_input_token_cost":1.409999988e-8},"list_pricing":{"input_cost_per_token":1.13e-7,"output_cost_per_token":3.82e-7,"cache_read_input_token_cost":1.409999988e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"qwen/qwen3.8-flash","object":"model","created":1787773060,"owned_by":"qwen","model_name":"qwen3.8-flash","context_length":1000000,"max_input_tokens":991808,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"Qwen3.8-Flash is the latest multimodal model from the Qwen family, combining powerful reasoning and generation with remarkable speed. It natively supports a million-token context window, allowing it to process lengthy documents, entire codebases, and complex conversations in a single pass. It shines in coding assistance, agentic workflows, and visual understanding — whether it's fixing code autonomously, operating desktop applications, or analyzing charts and long videos. Fully compatible with both OpenAI and Anthropic API protocols, it integrates seamlessly with popular developer tools like Claude Code and Codex, making it easy to build high-concurrency applications and intelligent workflows. With strong performance and highly competitive inference costs, Qwen3.8-Flash is an ideal choice for developers and businesses seeking the best of both worlds in AI applications.","source":null,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":9.749999999999999e-8,"output_cost_per_token":3.055e-7,"cache_read_input_token_cost":1.04e-8,"cache_creation_input_token_cost":1.3000000000000003e-7},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":4.6999999999999995e-7,"cache_read_input_token_cost":1.6e-8,"cache_creation_input_token_cost":2.0000000000000002e-7},"discount":0.35,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":2},{"id":"ling-3.0-flash-vl","object":"model","created":1789056114,"owned_by":"","mode":"chat","context_length":131072,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6.000000000000001e-8,"output_cost_per_token":1.8e-7,"cache_read_input_token_cost":1.2000000000000002e-8},"pricing_endpoint":"deepinfra/inclusionAI/Ling-3.0-flash-VL","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"deepinfra/inclusionAI/Ling-3.0-flash-VL","object":"model","created":1789056114,"owned_by":"deepinfra","model_name":"inclusionAI/Ling-3.0-flash-VL","context_length":131072,"max_input_tokens":null,"max_output_tokens":32768,"quantization":"fp4","retirement_date":null,"description":"Ling 3.0 Flash VL builds on Ling 3.0 Flash (124B total / 5.5B active MoE from InclusionAI), further strengthening its language capabilities while adding native visual perception and advanced visual...","source":null,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6.000000000000001e-8,"output_cost_per_token":1.8e-7,"cache_read_input_token_cost":1.2000000000000002e-8},"list_pricing":{"input_cost_per_token":6.000000000000001e-8,"output_cost_per_token":1.8e-7,"cache_read_input_token_cost":1.2000000000000002e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"deepseek-v3","object":"model","created":1789016966,"owned_by":"deepseek","mode":"chat","context_length":163840,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.2e-7,"output_cost_per_token":8.9e-7},"pricing_endpoint":"deepinfra/deepseek-ai/DeepSeek-V3","regions":[{"code":"eu","name":"Europe"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"amazon/deepseek.v3-v1:0","object":"model","created":1789016966,"owned_by":"amazon","model_name":"deepseek.v3-v1:0","context_length":128000,"max_input_tokens":128000,"max_output_tokens":8000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5.8e-7,"output_cost_per_token":1.68e-6},"list_pricing":{"input_cost_per_token":5.8e-7,"output_cost_per_token":1.68e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"deepinfra/deepseek-ai/DeepSeek-V3","object":"model","created":1767692616,"owned_by":"deepinfra","model_name":"deepseek-ai/DeepSeek-V3","context_length":163840,"max_input_tokens":163840,"max_output_tokens":null,"quantization":"fp4","retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.2e-7,"output_cost_per_token":8.9e-7},"list_pricing":{"input_cost_per_token":3.2e-7,"output_cost_per_token":8.9e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"qwen3-235b-a22b-2507","object":"model","created":1789016966,"owned_by":"qwen","mode":"chat","context_length":262144,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":7.2e-8,"output_cost_per_token":4.64e-7,"cache_read_input_token_cost":1.8e-8},"pricing_endpoint":"tensorx/qwen/qwen3-235b-a22b-2507","regions":[{"code":"eu","name":"Europe"}],"alias_of":null,"endpoints":[{"id":"amazon/qwen.qwen3-235b-a22b-2507-v1:0","object":"model","created":1789016966,"owned_by":"amazon","model_name":"qwen.qwen3-235b-a22b-2507-v1:0","context_length":262144,"max_input_tokens":262144,"max_output_tokens":8192,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.2e-7,"output_cost_per_token":8.8e-7,"input_cost_per_token_flex":1.1e-7,"output_cost_per_token_flex":4.4e-7},"list_pricing":{"input_cost_per_token":2.2e-7,"output_cost_per_token":8.8e-7,"input_cost_per_token_flex":1.1e-7,"output_cost_per_token_flex":4.4e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"tensorx/qwen/qwen3-235b-a22b-2507","object":"model","created":1787003349,"owned_by":"tensorx","model_name":"qwen/qwen3-235b-a22b-2507","context_length":131000,"max_input_tokens":131000,"max_output_tokens":32768,"quantization":null,"retirement_date":null,"description":"Served by TensorX at fp8 quantization.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":7.2e-8,"output_cost_per_token":4.64e-7,"cache_read_input_token_cost":1.8e-8},"list_pricing":{"input_cost_per_token":7.2e-8,"output_cost_per_token":4.64e-7,"cache_read_input_token_cost":1.8e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"qwen3-coder-480b-a35b","object":"model","created":1789016966,"owned_by":"qwen","mode":"chat","context_length":262144,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4.5e-7,"output_cost_per_token":1.8e-6},"pricing_endpoint":"amazon/qwen.qwen3-coder-480b-a35b-v1:0","regions":[{"code":"eu","name":"Europe"}],"alias_of":null,"endpoints":[{"id":"amazon/qwen.qwen3-coder-480b-a35b-v1:0","object":"model","created":1789016966,"owned_by":"amazon","model_name":"qwen.qwen3-coder-480b-a35b-v1:0","context_length":262144,"max_input_tokens":262144,"max_output_tokens":16384,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4.5e-7,"output_cost_per_token":1.8e-6},"list_pricing":{"input_cost_per_token":4.5e-7,"output_cost_per_token":1.8e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"grok-4.6","object":"model","created":1788671370,"owned_by":"xai","mode":"chat","context_length":500000,"capabilities":{"input_modalities":["text","file","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":6e-6,"input_dbu_cost_per_token":0.000035714,"output_dbu_cost_per_token":0.000107143,"cache_read_input_token_cost":2e-7,"cache_creation_input_token_cost":2.5e-6},"pricing_endpoint":"databricks/databricks-grok-4-6","regions":[{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"databricks/databricks-grok-4-6","object":"model","created":1788671370,"owned_by":"databricks","model_name":"databricks-grok-4-6","context_length":500000,"max_input_tokens":500000,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":6e-6,"input_dbu_cost_per_token":0.000035714,"output_dbu_cost_per_token":0.000107143,"cache_read_input_token_cost":2e-7,"cache_creation_input_token_cost":2.5e-6},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":6e-6,"input_dbu_cost_per_token":0.000035714,"output_dbu_cost_per_token":0.000107143,"cache_read_input_token_cost":2e-7,"cache_creation_input_token_cost":2.5e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"amazon/xai.grok-4.6","object":"model","created":1787288981,"owned_by":"amazon","model_name":"xai.grok-4.6","context_length":500000,"max_input_tokens":500000,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.2e-6,"output_cost_per_token":6.6e-6,"input_cost_per_token_flex":1.1e-6,"output_cost_per_token_flex":3.3e-6,"cache_read_input_token_cost":5.5e-7,"input_cost_per_token_priority":3.85e-6,"output_cost_per_token_priority":0.00001155,"cache_read_input_token_cost_flex":2.75e-7,"cache_read_input_token_cost_priority":9.625e-7},"list_pricing":{"input_cost_per_token":2.2e-6,"output_cost_per_token":6.6e-6,"input_cost_per_token_flex":1.1e-6,"output_cost_per_token_flex":3.3e-6,"cache_read_input_token_cost":5.5e-7,"input_cost_per_token_priority":3.85e-6,"output_cost_per_token_priority":0.00001155,"cache_read_input_token_cost_flex":2.75e-7,"cache_read_input_token_cost_priority":9.625e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/xai.grok-4.6@us","object":"model","created":1787288981,"owned_by":"amazon","model_name":"xai.grok-4.6","context_length":500000,"max_input_tokens":500000,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.2e-6,"output_cost_per_token":6.6e-6,"input_cost_per_token_flex":1.1e-6,"output_cost_per_token_flex":3.3e-6,"cache_read_input_token_cost":5.5e-7,"input_cost_per_token_priority":3.85e-6,"output_cost_per_token_priority":0.00001155,"cache_read_input_token_cost_flex":2.75e-7,"cache_read_input_token_cost_priority":9.625e-7},"list_pricing":{"input_cost_per_token":2.2e-6,"output_cost_per_token":6.6e-6,"input_cost_per_token_flex":1.1e-6,"output_cost_per_token_flex":3.3e-6,"cache_read_input_token_cost":5.5e-7,"input_cost_per_token_priority":3.85e-6,"output_cost_per_token_priority":0.00001155,"cache_read_input_token_cost_flex":2.75e-7,"cache_read_input_token_cost_priority":9.625e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"xai/grok-4.6","object":"model","created":1786548957,"owned_by":"xai","model_name":"grok-4.6","context_length":500000,"max_input_tokens":500000,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"Grok 4.6 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM. It is succeeded by Grok 4.7.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":6e-6,"input_cost_per_image_token":2e-6,"cache_read_input_token_cost":5e-7,"search_context_cost_per_query":{"search_context_size_low":0.005,"search_context_size_high":0.005,"search_context_size_medium":0.005},"input_cost_per_token_above_200k_tokens":4e-6,"output_cost_per_token_above_200k_tokens":0.000012,"cache_read_input_token_cost_above_200k_tokens":1e-6},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":6e-6,"input_cost_per_image_token":2e-6,"cache_read_input_token_cost":5e-7,"search_context_cost_per_query":{"search_context_size_low":0.005,"search_context_size_high":0.005,"search_context_size_medium":0.005},"input_cost_per_token_above_200k_tokens":4e-6,"output_cost_per_token_above_200k_tokens":0.000012,"cache_read_input_token_cost_above_200k_tokens":1e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":4},{"id":"inkling","object":"model","created":1788498545,"owned_by":"thinkingmachines","mode":"chat","context_length":1048576,"capabilities":{"input_modalities":["text","image","audio"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":9.5e-7,"output_cost_per_token":4.05e-6,"cache_read_input_token_cost":1.6e-7},"pricing_endpoint":"deepinfra/thinkingmachines/Inkling","regions":[{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"fireworks_ai/accounts/fireworks/models/inkling","object":"model","created":1788498545,"owned_by":"fireworks_ai","model_name":"accounts/fireworks/models/inkling","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":4.05e-6,"cache_read_input_token_cost":1.7e-7,"input_cost_per_token_priority":1e-6,"output_cost_per_token_priority":4.05e-6,"cache_read_input_token_cost_priority":1.7e-7},"list_pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":4.05e-6,"cache_read_input_token_cost":1.7e-7,"input_cost_per_token_priority":1e-6,"output_cost_per_token_priority":4.05e-6,"cache_read_input_token_cost_priority":1.7e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"deepinfra/thinkingmachines/Inkling","object":"model","created":1784325956,"owned_by":"deepinfra","model_name":"thinkingmachines/Inkling","context_length":524288,"max_input_tokens":null,"max_output_tokens":262144,"quantization":null,"retirement_date":null,"description":"Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems,...","source":null,"capabilities":{"input_modalities":["text","image","audio"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":9.5e-7,"output_cost_per_token":4.05e-6,"cache_read_input_token_cost":1.6e-7},"list_pricing":{"input_cost_per_token":9.5e-7,"output_cost_per_token":4.05e-6,"cache_read_input_token_cost":1.6e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"together_ai/thinkingmachines/Inkling","object":"model","created":1784325956,"owned_by":"together_ai","model_name":"thinkingmachines/Inkling","context_length":524288,"max_input_tokens":524288,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total.","source":null,"capabilities":{"input_modalities":["text","image","audio"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":4.05e-6,"cache_read_input_token_cost":1.7000000000000001e-7},"list_pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":4.05e-6,"cache_read_input_token_cost":1.7000000000000001e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":3},{"id":"qwen3.8-max-0902","object":"model","created":1788469704,"owned_by":"qwen","mode":"chat","context_length":1000000,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.3e-6,"output_cost_per_token":3.9e-6,"cache_read_input_token_cost":1.625e-7,"cache_creation_input_token_cost":1.6250000000000001e-6},"pricing_endpoint":"qwen/qwen3.8-max-0902","regions":[{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"qwen/qwen3.8-max-0902","object":"model","created":1788469704,"owned_by":"qwen","model_name":"qwen3.8-max-0902","context_length":1000000,"max_input_tokens":991808,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"Qwen3.8-Max-0902（alias qwen3.8-max-2026-09-02）is an upgraded snapshot of qwen3.8-max. Coding capability breaks new ground, handling more complex engineering-scale projects and long-horizon autonomous development. Collaborative agent performance is significantly enhanced, with greater composure in multi-tool orchestration and end-to-end task delivery. Native vision understanding is refined across chart reasoning, document parsing, and multimodal perception — sharper and more reliable. Retains the 1M context window, thinking mode, and full tool ecosystem, evolving at a higher level of intelligence.","source":null,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.3e-6,"output_cost_per_token":3.9e-6,"cache_read_input_token_cost":1.625e-7,"cache_creation_input_token_cost":1.6250000000000001e-6},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":6e-6,"cache_read_input_token_cost":2.5e-7,"cache_creation_input_token_cost":2.5e-6},"discount":0.35,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":1},{"id":"carina-60b","object":"model","created":1788457256,"owned_by":"compactifai","mode":"chat","context_length":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.2e-8,"output_cost_per_token":8.5e-8},"pricing_endpoint":"compactifai/carina-60b","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"compactifai/carina-60b@eu","object":"model","created":1788457256,"owned_by":"compactifai","model_name":"carina-60b","context_length":null,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.2e-8,"output_cost_per_token":8.5e-8},"list_pricing":{"input_cost_per_token":2.2e-8,"output_cost_per_token":8.5e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"compactifai/carina-60b","object":"model","created":1788457256,"owned_by":"compactifai","model_name":"carina-60b","context_length":null,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.2e-8,"output_cost_per_token":8.5e-8},"list_pricing":{"input_cost_per_token":2.2e-8,"output_cost_per_token":8.5e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null},{"id":"compactifai/carina-60b@us","object":"model","created":1788457256,"owned_by":"compactifai","model_name":"carina-60b","context_length":null,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.2e-8,"output_cost_per_token":8.5e-8},"list_pricing":{"input_cost_per_token":2.2e-8,"output_cost_per_token":8.5e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":3},{"id":"hypernova-60b","object":"model","created":1788457256,"owned_by":"amazon","mode":"chat","context_length":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4e-8,"output_cost_per_token":1.4e-7},"pricing_endpoint":"compactifai/hypernova-60b","regions":[{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"compactifai/hypernova-60b","object":"model","created":1788457256,"owned_by":"compactifai","model_name":"hypernova-60b","context_length":null,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4e-8,"output_cost_per_token":1.4e-7},"list_pricing":{"input_cost_per_token":4e-8,"output_cost_per_token":1.4e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null},{"id":"compactifai/hypernova-60b@us","object":"model","created":1788457256,"owned_by":"compactifai","model_name":"hypernova-60b","context_length":null,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4e-8,"output_cost_per_token":1.4e-7},"list_pricing":{"input_cost_per_token":4e-8,"output_cost_per_token":1.4e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":2},{"id":"claude-fable-5.1","object":"model","created":1788285838,"owned_by":"anthropic","mode":"chat","context_length":1000000,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":0.00001,"output_cost_per_token":0.00005,"provider_specific_entry":{"us":1.1},"cache_read_input_token_cost":2.5e-7,"input_cost_per_token_batches":5e-6,"output_cost_per_token_batches":0.000025,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":0.0000125,"cache_read_input_token_cost_batches":1.25e-7,"cache_creation_input_token_cost_above_1hr":0.00002},"pricing_endpoint":"anthropic/claude-fable-5-1","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"anthropic/claude-fable-5-1","object":"model","created":1788285838,"owned_by":"anthropic","model_name":"claude-fable-5-1","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, and knowledge work: long code refactors, front-end and visual...","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":0.00001,"output_cost_per_token":0.00005,"provider_specific_entry":{"us":1.1},"cache_read_input_token_cost":2.5e-7,"input_cost_per_token_batches":5e-6,"output_cost_per_token_batches":0.000025,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":0.0000125,"cache_read_input_token_cost_batches":1.25e-7,"cache_creation_input_token_cost_above_1hr":0.00002},"list_pricing":{"input_cost_per_token":0.00001,"output_cost_per_token":0.00005,"provider_specific_entry":{"us":1.1},"cache_read_input_token_cost":2.5e-7,"input_cost_per_token_batches":5e-6,"output_cost_per_token_batches":0.000025,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":0.0000125,"cache_read_input_token_cost_batches":1.25e-7,"cache_creation_input_token_cost_above_1hr":0.00002},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null},{"id":"vertex/claude-fable-5-1@eu","object":"model","created":1788285838,"owned_by":"vertex","model_name":"claude-fable-5-1","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, and knowledge work: long code refactors, front-end and visual...","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":0.000011000000000000001,"output_cost_per_token":0.00005500000000000001,"cache_read_input_token_cost":2.75e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":0.000013750000000000002,"cache_creation_input_token_cost_above_1hr":0.000022000000000000003},"list_pricing":{"input_cost_per_token":0.000011000000000000001,"output_cost_per_token":0.00005500000000000001,"cache_read_input_token_cost":2.75e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":0.000013750000000000002,"cache_creation_input_token_cost_above_1hr":0.000022000000000000003},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"vertex/claude-fable-5-1","object":"model","created":1788285838,"owned_by":"vertex","model_name":"claude-fable-5-1","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, and knowledge work: long code refactors, front-end and visual...","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":0.00001,"output_cost_per_token":0.00005,"cache_read_input_token_cost":2.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":0.0000125,"cache_creation_input_token_cost_above_1hr":0.00002},"list_pricing":{"input_cost_per_token":0.00001,"output_cost_per_token":0.00005,"cache_read_input_token_cost":2.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":0.0000125,"cache_creation_input_token_cost_above_1hr":0.00002},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"vertex/claude-fable-5-1@us","object":"model","created":1788285838,"owned_by":"vertex","model_name":"claude-fable-5-1","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, and knowledge work: long code refactors, front-end and visual...","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":0.000011000000000000001,"output_cost_per_token":0.00005500000000000001,"cache_read_input_token_cost":2.75e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":0.000013750000000000002,"cache_creation_input_token_cost_above_1hr":0.000022000000000000003},"list_pricing":{"input_cost_per_token":0.000011000000000000001,"output_cost_per_token":0.00005500000000000001,"cache_read_input_token_cost":2.75e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":0.000013750000000000002,"cache_creation_input_token_cost_above_1hr":0.000022000000000000003},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":4},{"id":"granite-4.2-8b","object":"model","created":1788206780,"owned_by":"ibm","mode":"chat","context_length":131072,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6.000000000000001e-8,"output_cost_per_token":2.5e-7,"cache_read_input_token_cost":1.5000000000000002e-8},"pricing_endpoint":"deepinfra/ibm-granite/granite-4.2-8b","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"deepinfra/ibm-granite/granite-4.2-8b","object":"model","created":1788206780,"owned_by":"deepinfra","model_name":"ibm-granite/granite-4.2-8b","context_length":131072,"max_input_tokens":null,"max_output_tokens":null,"quantization":"bf16","retirement_date":null,"description":"Granite 4.2 8B is a dense reasoning model from IBM. It is suited for mathematics, code generation, multilingual dialogue, and agentic workflows that need multi-step reasoning.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6.000000000000001e-8,"output_cost_per_token":2.5e-7,"cache_read_input_token_cost":1.5000000000000002e-8},"list_pricing":{"input_cost_per_token":6.000000000000001e-8,"output_cost_per_token":2.5e-7,"cache_read_input_token_cost":1.5000000000000002e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"nano-banana-pro-preview","object":"model","created":1788066616,"owned_by":"google","mode":"chat","context_length":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_image":0.0011,"input_cost_per_token":2e-6,"output_cost_per_image":0.134,"output_cost_per_token":0.000012,"output_cost_per_image_token":0.00012},"pricing_endpoint":"google/nano-banana-pro-preview","regions":[{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"google/nano-banana-pro-preview","object":"model","created":1788066616,"owned_by":"google","model_name":"nano-banana-pro-preview","context_length":null,"max_input_tokens":131072,"max_output_tokens":32768,"quantization":null,"retirement_date":null,"description":null,"source":"https://ai.google.dev/gemini-api/docs/pricing","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_image":0.0011,"input_cost_per_token":2e-6,"output_cost_per_image":0.134,"output_cost_per_token":0.000012,"output_cost_per_image_token":0.00012},"list_pricing":{"input_cost_per_image":0.0011,"input_cost_per_token":2e-6,"output_cost_per_image":0.134,"output_cost_per_token":0.000012,"output_cost_per_image_token":0.00012},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":1},{"id":"mistral-code-agent-latest","object":"model","created":1788066615,"owned_by":"mistral","mode":"chat","context_length":262144,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4e-7,"output_cost_per_token":2e-6},"pricing_endpoint":"mistral/mistral-code-agent-latest","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"mistral/mistral-code-agent-latest@eu","object":"model","created":1788066615,"owned_by":"mistral","model_name":"mistral-code-agent-latest","context_length":262144,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":"2026-08-31","description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4.4e-7,"output_cost_per_token":2.2e-6},"list_pricing":{"input_cost_per_token":4.4e-7,"output_cost_per_token":2.2e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"mistral/mistral-code-agent-latest","object":"model","created":1788066615,"owned_by":"mistral","model_name":"mistral-code-agent-latest","context_length":262144,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":"2026-08-31","description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4e-7,"output_cost_per_token":2e-6},"list_pricing":{"input_cost_per_token":4e-7,"output_cost_per_token":2e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"mistral-code-fim-latest","object":"model","created":1788066615,"owned_by":"mistral","mode":"chat","context_length":256000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":9e-7,"cache_read_input_token_cost":3e-8,"input_cost_per_token_batches":1.5e-7,"output_cost_per_token_batches":4.5e-7,"cache_read_input_token_cost_batches":1.5e-8},"pricing_endpoint":"mistral/mistral-code-fim-latest","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"mistral/mistral-code-fim-latest@eu","object":"model","created":1788066615,"owned_by":"mistral","model_name":"mistral-code-fim-latest","context_length":256000,"max_input_tokens":128000,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.3e-7,"output_cost_per_token":9.9e-7,"cache_read_input_token_cost":3.3e-8,"input_cost_per_token_batches":1.65e-7,"output_cost_per_token_batches":4.95e-7,"cache_read_input_token_cost_batches":1.65e-8},"list_pricing":{"input_cost_per_token":3.3e-7,"output_cost_per_token":9.9e-7,"cache_read_input_token_cost":3.3e-8,"input_cost_per_token_batches":1.65e-7,"output_cost_per_token_batches":4.95e-7,"cache_read_input_token_cost_batches":1.65e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"mistral/mistral-code-fim-latest","object":"model","created":1788066615,"owned_by":"mistral","model_name":"mistral-code-fim-latest","context_length":256000,"max_input_tokens":128000,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":9e-7,"cache_read_input_token_cost":3e-8,"input_cost_per_token_batches":1.5e-7,"output_cost_per_token_batches":4.5e-7,"cache_read_input_token_cost_batches":1.5e-8},"list_pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":9e-7,"cache_read_input_token_cost":3e-8,"input_cost_per_token_batches":1.5e-7,"output_cost_per_token_batches":4.5e-7,"cache_read_input_token_cost_batches":1.5e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"mistral-code-latest","object":"model","created":1788066615,"owned_by":"mistral","mode":"chat","context_length":256000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":9e-7,"cache_read_input_token_cost":3e-8,"input_cost_per_token_batches":1.5e-7,"output_cost_per_token_batches":4.5e-7,"cache_read_input_token_cost_batches":1.5e-8},"pricing_endpoint":"mistral/mistral-code-latest","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"mistral/mistral-code-latest@eu","object":"model","created":1788066615,"owned_by":"mistral","model_name":"mistral-code-latest","context_length":256000,"max_input_tokens":128000,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.3e-7,"output_cost_per_token":9.9e-7,"cache_read_input_token_cost":3.3e-8,"input_cost_per_token_batches":1.65e-7,"output_cost_per_token_batches":4.95e-7,"cache_read_input_token_cost_batches":1.65e-8},"list_pricing":{"input_cost_per_token":3.3e-7,"output_cost_per_token":9.9e-7,"cache_read_input_token_cost":3.3e-8,"input_cost_per_token_batches":1.65e-7,"output_cost_per_token_batches":4.95e-7,"cache_read_input_token_cost_batches":1.65e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"mistral/mistral-code-latest","object":"model","created":1788066615,"owned_by":"mistral","model_name":"mistral-code-latest","context_length":256000,"max_input_tokens":128000,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":9e-7,"cache_read_input_token_cost":3e-8,"input_cost_per_token_batches":1.5e-7,"output_cost_per_token_batches":4.5e-7,"cache_read_input_token_cost_batches":1.5e-8},"list_pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":9e-7,"cache_read_input_token_cost":3e-8,"input_cost_per_token_batches":1.5e-7,"output_cost_per_token_batches":4.5e-7,"cache_read_input_token_cost_batches":1.5e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"mistral-vibe-cli-fast","object":"model","created":1788066615,"owned_by":"mistral","mode":"chat","context_length":262144,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":1.5e-8,"input_cost_per_token_batches":7.5e-8,"output_cost_per_token_batches":3e-7,"cache_read_input_token_cost_batches":7.5e-9},"pricing_endpoint":"mistral/mistral-vibe-cli-fast","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"mistral/mistral-vibe-cli-fast@eu","object":"model","created":1788066615,"owned_by":"mistral","model_name":"mistral-vibe-cli-fast","context_length":262144,"max_input_tokens":262144,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.65e-7,"output_cost_per_token":6.6e-7,"cache_read_input_token_cost":1.65e-8,"input_cost_per_token_batches":8.25e-8,"output_cost_per_token_batches":3.3e-7,"cache_read_input_token_cost_batches":8.25e-9},"list_pricing":{"input_cost_per_token":1.65e-7,"output_cost_per_token":6.6e-7,"cache_read_input_token_cost":1.65e-8,"input_cost_per_token_batches":8.25e-8,"output_cost_per_token_batches":3.3e-7,"cache_read_input_token_cost_batches":8.25e-9},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"mistral/mistral-vibe-cli-fast","object":"model","created":1788066615,"owned_by":"mistral","model_name":"mistral-vibe-cli-fast","context_length":262144,"max_input_tokens":262144,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":1.5e-8,"input_cost_per_token_batches":7.5e-8,"output_cost_per_token_batches":3e-7,"cache_read_input_token_cost_batches":7.5e-9},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":1.5e-8,"input_cost_per_token_batches":7.5e-8,"output_cost_per_token_batches":3e-7,"cache_read_input_token_cost_batches":7.5e-9},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"mistral-vibe-cli-latest","object":"model","created":1788066615,"owned_by":"mistral","mode":"chat","context_length":262144,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-6,"output_cost_per_token":7.5e-6,"cache_read_input_token_cost":1.5e-7,"input_cost_per_token_batches":7.5e-7,"output_cost_per_token_batches":3.75e-6,"cache_read_input_token_cost_batches":7.5e-8},"pricing_endpoint":"mistral/mistral-vibe-cli-latest","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"mistral/mistral-vibe-cli-latest@eu","object":"model","created":1788066615,"owned_by":"mistral","model_name":"mistral-vibe-cli-latest","context_length":262144,"max_input_tokens":262144,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.65e-6,"output_cost_per_token":8.25e-6,"cache_read_input_token_cost":1.65e-7,"input_cost_per_token_batches":8.25e-7,"output_cost_per_token_batches":4.125e-6,"cache_read_input_token_cost_batches":8.25e-8},"list_pricing":{"input_cost_per_token":1.65e-6,"output_cost_per_token":8.25e-6,"cache_read_input_token_cost":1.65e-7,"input_cost_per_token_batches":8.25e-7,"output_cost_per_token_batches":4.125e-6,"cache_read_input_token_cost_batches":8.25e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"mistral/mistral-vibe-cli-latest","object":"model","created":1788066615,"owned_by":"mistral","model_name":"mistral-vibe-cli-latest","context_length":262144,"max_input_tokens":262144,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-6,"output_cost_per_token":7.5e-6,"cache_read_input_token_cost":1.5e-7,"input_cost_per_token_batches":7.5e-7,"output_cost_per_token_batches":3.75e-6,"cache_read_input_token_cost_batches":7.5e-8},"list_pricing":{"input_cost_per_token":1.5e-6,"output_cost_per_token":7.5e-6,"cache_read_input_token_cost":1.5e-7,"input_cost_per_token_batches":7.5e-7,"output_cost_per_token_batches":3.75e-6,"cache_read_input_token_cost_batches":7.5e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"mistral-vibe-cli-with-tools","object":"model","created":1788066615,"owned_by":"mistral","mode":"chat","context_length":262144,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-6,"output_cost_per_token":7.5e-6,"cache_read_input_token_cost":1.5e-7,"input_cost_per_token_batches":7.5e-7,"output_cost_per_token_batches":3.75e-6,"cache_read_input_token_cost_batches":7.5e-8},"pricing_endpoint":"mistral/mistral-vibe-cli-with-tools","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"mistral/mistral-vibe-cli-with-tools@eu","object":"model","created":1788066615,"owned_by":"mistral","model_name":"mistral-vibe-cli-with-tools","context_length":262144,"max_input_tokens":262144,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.65e-6,"output_cost_per_token":8.25e-6,"cache_read_input_token_cost":1.65e-7,"input_cost_per_token_batches":8.25e-7,"output_cost_per_token_batches":4.125e-6,"cache_read_input_token_cost_batches":8.25e-8},"list_pricing":{"input_cost_per_token":1.65e-6,"output_cost_per_token":8.25e-6,"cache_read_input_token_cost":1.65e-7,"input_cost_per_token_batches":8.25e-7,"output_cost_per_token_batches":4.125e-6,"cache_read_input_token_cost_batches":8.25e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"mistral/mistral-vibe-cli-with-tools","object":"model","created":1788066615,"owned_by":"mistral","model_name":"mistral-vibe-cli-with-tools","context_length":262144,"max_input_tokens":262144,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-6,"output_cost_per_token":7.5e-6,"cache_read_input_token_cost":1.5e-7,"input_cost_per_token_batches":7.5e-7,"output_cost_per_token_batches":3.75e-6,"cache_read_input_token_cost_batches":7.5e-8},"list_pricing":{"input_cost_per_token":1.5e-6,"output_cost_per_token":7.5e-6,"cache_read_input_token_cost":1.5e-7,"input_cost_per_token_batches":7.5e-7,"output_cost_per_token_batches":3.75e-6,"cache_read_input_token_cost_batches":7.5e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"ministral-14b-latest","object":"model","created":1787893793,"owned_by":"mistral","mode":"chat","context_length":262144,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":2e-7,"cache_read_input_token_cost":2e-8,"input_cost_per_token_batches":1e-7,"output_cost_per_token_batches":1e-7,"cache_read_input_token_cost_batches":1e-8},"pricing_endpoint":"mistral/ministral-14b-latest","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"mistral/ministral-14b-latest@eu","object":"model","created":1787893793,"owned_by":"mistral","model_name":"ministral-14b-latest","context_length":262144,"max_input_tokens":262144,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.2e-7,"output_cost_per_token":2.2e-7,"cache_read_input_token_cost":2.2000000000000002e-8,"input_cost_per_token_batches":1.1e-7,"output_cost_per_token_batches":1.1e-7,"cache_read_input_token_cost_batches":1.1000000000000001e-8},"list_pricing":{"input_cost_per_token":2.2e-7,"output_cost_per_token":2.2e-7,"cache_read_input_token_cost":2.2000000000000002e-8,"input_cost_per_token_batches":1.1e-7,"output_cost_per_token_batches":1.1e-7,"cache_read_input_token_cost_batches":1.1000000000000001e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"mistral/ministral-14b-latest","object":"model","created":1787893793,"owned_by":"mistral","model_name":"ministral-14b-latest","context_length":262144,"max_input_tokens":262144,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":2e-7,"cache_read_input_token_cost":2e-8,"input_cost_per_token_batches":1e-7,"output_cost_per_token_batches":1e-7,"cache_read_input_token_cost_batches":1e-8},"list_pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":2e-7,"cache_read_input_token_cost":2e-8,"input_cost_per_token_batches":1e-7,"output_cost_per_token_batches":1e-7,"cache_read_input_token_cost_batches":1e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"ministral-3b-latest","object":"model","created":1787893793,"owned_by":"mistral","mode":"chat","context_length":131072,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":1e-7,"cache_read_input_token_cost":1e-8,"input_cost_per_token_batches":5e-8,"output_cost_per_token_batches":5e-8,"cache_read_input_token_cost_batches":5e-9},"pricing_endpoint":"mistral/ministral-3b-latest","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"mistral/ministral-3b-latest@eu","object":"model","created":1787893793,"owned_by":"mistral","model_name":"ministral-3b-latest","context_length":131072,"max_input_tokens":131072,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.1e-7,"output_cost_per_token":1.1e-7,"cache_read_input_token_cost":1.1000000000000001e-8,"input_cost_per_token_batches":5.5e-8,"output_cost_per_token_batches":5.5e-8,"cache_read_input_token_cost_batches":5.5000000000000004e-9},"list_pricing":{"input_cost_per_token":1.1e-7,"output_cost_per_token":1.1e-7,"cache_read_input_token_cost":1.1000000000000001e-8,"input_cost_per_token_batches":5.5e-8,"output_cost_per_token_batches":5.5e-8,"cache_read_input_token_cost_batches":5.5000000000000004e-9},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"mistral/ministral-3b-latest","object":"model","created":1787893793,"owned_by":"mistral","model_name":"ministral-3b-latest","context_length":131072,"max_input_tokens":131072,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":1e-7,"cache_read_input_token_cost":1e-8,"input_cost_per_token_batches":5e-8,"output_cost_per_token_batches":5e-8,"cache_read_input_token_cost_batches":5e-9},"list_pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":1e-7,"cache_read_input_token_cost":1e-8,"input_cost_per_token_batches":5e-8,"output_cost_per_token_batches":5e-8,"cache_read_input_token_cost_batches":5e-9},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"voxtral-small-2507","object":"model","created":1787893793,"owned_by":"mistral","mode":"chat","context_length":32768,"capabilities":{"input_modalities":["text","audio"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":4e-7,"cache_read_input_token_cost":1e-8,"input_cost_per_token_batches":5e-8,"output_cost_per_token_batches":2e-7,"cache_read_input_token_cost_batches":5e-9},"pricing_endpoint":"mistral/voxtral-small-2507","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"mistral/voxtral-small-2507@eu","object":"model","created":1787893793,"owned_by":"mistral","model_name":"voxtral-small-2507","context_length":32768,"max_input_tokens":32768,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","audio"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.1e-7,"output_cost_per_token":4.4e-7,"cache_read_input_token_cost":1.1000000000000001e-8,"input_cost_per_token_batches":5.5e-8,"output_cost_per_token_batches":2.2e-7,"cache_read_input_token_cost_batches":5.5000000000000004e-9},"list_pricing":{"input_cost_per_token":1.1e-7,"output_cost_per_token":4.4e-7,"cache_read_input_token_cost":1.1000000000000001e-8,"input_cost_per_token_batches":5.5e-8,"output_cost_per_token_batches":2.2e-7,"cache_read_input_token_cost_batches":5.5000000000000004e-9},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"mistral/voxtral-small-2507","object":"model","created":1787893793,"owned_by":"mistral","model_name":"voxtral-small-2507","context_length":32768,"max_input_tokens":32768,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","audio"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":4e-7,"cache_read_input_token_cost":1e-8,"input_cost_per_token_batches":5e-8,"output_cost_per_token_batches":2e-7,"cache_read_input_token_cost_batches":5e-9},"list_pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":4e-7,"cache_read_input_token_cost":1e-8,"input_cost_per_token_batches":5e-8,"output_cost_per_token_batches":2e-7,"cache_read_input_token_cost_batches":5e-9},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"voxtral-small-latest","object":"model","created":1787893793,"owned_by":"mistral","mode":"chat","context_length":32768,"capabilities":{"input_modalities":["text","audio"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":4e-7,"cache_read_input_token_cost":1e-8,"input_cost_per_token_batches":5e-8,"output_cost_per_token_batches":2e-7,"cache_read_input_token_cost_batches":5e-9},"pricing_endpoint":"mistral/voxtral-small-latest","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"mistral/voxtral-small-latest@eu","object":"model","created":1787893793,"owned_by":"mistral","model_name":"voxtral-small-latest","context_length":32768,"max_input_tokens":32768,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","audio"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.1e-7,"output_cost_per_token":4.4e-7,"cache_read_input_token_cost":1.1000000000000001e-8,"input_cost_per_token_batches":5.5e-8,"output_cost_per_token_batches":2.2e-7,"cache_read_input_token_cost_batches":5.5000000000000004e-9},"list_pricing":{"input_cost_per_token":1.1e-7,"output_cost_per_token":4.4e-7,"cache_read_input_token_cost":1.1000000000000001e-8,"input_cost_per_token_batches":5.5e-8,"output_cost_per_token_batches":2.2e-7,"cache_read_input_token_cost_batches":5.5000000000000004e-9},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"mistral/voxtral-small-latest","object":"model","created":1787893793,"owned_by":"mistral","model_name":"voxtral-small-latest","context_length":32768,"max_input_tokens":32768,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","audio"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":4e-7,"cache_read_input_token_cost":1e-8,"input_cost_per_token_batches":5e-8,"output_cost_per_token_batches":2e-7,"cache_read_input_token_cost_batches":5e-9},"list_pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":4e-7,"cache_read_input_token_cost":1e-8,"input_cost_per_token_batches":5e-8,"output_cost_per_token_batches":2e-7,"cache_read_input_token_cost_batches":5e-9},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"ling-3.0-flash-fin","object":"model","created":1787846290,"owned_by":"","mode":"chat","context_length":262144,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6.000000000000001e-8,"output_cost_per_token":1.8e-7,"cache_read_input_token_cost":1.2000000000000002e-8},"pricing_endpoint":"deepinfra/inclusionAI/Ling-3.0-flash-Fin","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"deepinfra/inclusionAI/Ling-3.0-flash-Fin","object":"model","created":1787846290,"owned_by":"deepinfra","model_name":"inclusionAI/Ling-3.0-flash-Fin","context_length":262144,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"Ling 3.0 Flash Fin is a finance-focused mixture-of-experts model from InclusionAI, built on Ling 3.0 Flash with 5.1B active parameters out of 124B total. It is designed for real-world investment...","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6.000000000000001e-8,"output_cost_per_token":1.8e-7,"cache_read_input_token_cost":1.2000000000000002e-8},"list_pricing":{"input_cost_per_token":6.000000000000001e-8,"output_cost_per_token":1.8e-7,"cache_read_input_token_cost":1.2000000000000002e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"granite-4.2-30b","object":"model","created":1787720977,"owned_by":"ibm","mode":"chat","context_length":131072,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.6e-7,"output_cost_per_token":6.499999999999999e-7,"cache_read_input_token_cost":4e-8},"pricing_endpoint":"deepinfra/ibm-granite/granite-4.2-30b","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"deepinfra/ibm-granite/granite-4.2-30b","object":"model","created":1787720977,"owned_by":"deepinfra","model_name":"ibm-granite/granite-4.2-30b","context_length":131072,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.6e-7,"output_cost_per_token":6.499999999999999e-7,"cache_read_input_token_cost":4e-8},"list_pricing":{"input_cost_per_token":1.6e-7,"output_cost_per_token":6.499999999999999e-7,"cache_read_input_token_cost":4e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"granite-4.2-3b","object":"model","created":1787720977,"owned_by":"ibm","mode":"chat","context_length":131072,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.0000000000000004e-8,"output_cost_per_token":1.2000000000000002e-7,"cache_read_input_token_cost":7.500000000000001e-9},"pricing_endpoint":"deepinfra/ibm-granite/granite-4.2-3b","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"deepinfra/ibm-granite/granite-4.2-3b","object":"model","created":1787720977,"owned_by":"deepinfra","model_name":"ibm-granite/granite-4.2-3b","context_length":131072,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.0000000000000004e-8,"output_cost_per_token":1.2000000000000002e-7,"cache_read_input_token_cost":7.500000000000001e-9},"list_pricing":{"input_cost_per_token":3.0000000000000004e-8,"output_cost_per_token":1.2000000000000002e-7,"cache_read_input_token_cost":7.500000000000001e-9},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"ternary-bonsai-27b","object":"model","created":1787720977,"owned_by":"","mode":"chat","context_length":262144,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":0.0,"output_cost_per_token":0.0},"pricing_endpoint":"together_ai/Prism-ML/Ternary-Bonsai-27B","regions":[{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"together_ai/Prism-ML/Ternary-Bonsai-27B","object":"model","created":1787720977,"owned_by":"together_ai","model_name":"Prism-ML/Ternary-Bonsai-27B","context_length":262144,"max_input_tokens":262144,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":0.0,"output_cost_per_token":0.0},"list_pricing":{"input_cost_per_token":0.0,"output_cost_per_token":0.0},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":1},{"id":"gpt-5.6-luna","object":"model","created":1787461792,"owned_by":"openai","mode":"chat","context_length":1050000,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":1.2e-6,"input_cost_per_token_flex":1e-7,"output_cost_per_token_flex":6e-7,"cache_read_input_token_cost":2e-8,"input_cost_per_token_batches":1e-7,"input_cost_per_token_priority":4e-7,"output_cost_per_token_batches":6e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"output_cost_per_token_priority":2.4e-6,"cache_creation_input_token_cost":2.5e-7,"cache_read_input_token_cost_flex":1e-8,"cache_read_input_token_cost_batches":1e-8,"cache_creation_input_token_cost_flex":1.25e-7,"cache_read_input_token_cost_priority":4e-8,"input_cost_per_token_above_272k_tokens":4e-7,"output_cost_per_token_above_272k_tokens":1.8e-6,"cache_creation_input_token_cost_priority":5e-7,"cache_creation_input_token_cost_above_12hr":5e-7,"input_cost_per_token_above_272k_tokens_flex":2e-7,"output_cost_per_token_above_272k_tokens_flex":9e-7,"cache_read_input_token_cost_above_272k_tokens":4e-8,"cache_creation_input_token_cost_above_12hr_flex":2.5e-7,"input_cost_per_token_above_272k_tokens_priority":8e-7,"output_cost_per_token_above_272k_tokens_priority":3.6e-6,"cache_creation_input_token_cost_above_272k_tokens":5e-7,"cache_read_input_token_cost_above_272k_tokens_flex":2e-8,"cache_creation_input_token_cost_above_12hr_priority":1e-6,"cache_creation_input_token_cost_above_272k_tokens_flex":2.5e-7,"cache_read_input_token_cost_above_272k_tokens_priority":8e-8,"cache_creation_input_token_cost_above_272k_tokens_priority":1e-6,"cache_creation_input_token_cost_above_12hr_above_272k_tokens":1e-6,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_flex":5e-7,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_priority":2e-6},"pricing_endpoint":"openai/gpt-5.6-luna","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"amazon/openai.gpt-5.6-luna","object":"model","created":1787461792,"owned_by":"amazon","model_name":"openai.gpt-5.6-luna","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.2e-7,"output_cost_per_token":1.32e-6,"cache_read_input_token_cost":2.2e-8,"cache_creation_input_token_cost":2.75e-7,"input_cost_per_token_above_272k_tokens":4.4e-7,"output_cost_per_token_above_272k_tokens":1.98e-6,"cache_read_input_token_cost_above_272k_tokens":4.4e-8,"cache_creation_input_token_cost_above_272k_tokens":5.5e-7},"list_pricing":{"input_cost_per_token":2.2e-7,"output_cost_per_token":1.32e-6,"cache_read_input_token_cost":2.2e-8,"cache_creation_input_token_cost":2.75e-7,"input_cost_per_token_above_272k_tokens":4.4e-7,"output_cost_per_token_above_272k_tokens":1.98e-6,"cache_read_input_token_cost_above_272k_tokens":4.4e-8,"cache_creation_input_token_cost_above_272k_tokens":5.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"amazon/openai.gpt-5.6-luna@us","object":"model","created":1787461792,"owned_by":"amazon","model_name":"openai.gpt-5.6-luna","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.2e-7,"output_cost_per_token":1.32e-6,"cache_read_input_token_cost":2.2e-8,"cache_creation_input_token_cost":2.75e-7,"input_cost_per_token_above_272k_tokens":4.4e-7,"output_cost_per_token_above_272k_tokens":1.98e-6,"cache_read_input_token_cost_above_272k_tokens":4.4e-8,"cache_creation_input_token_cost_above_272k_tokens":5.5e-7},"list_pricing":{"input_cost_per_token":2.2e-7,"output_cost_per_token":1.32e-6,"cache_read_input_token_cost":2.2e-8,"cache_creation_input_token_cost":2.75e-7,"input_cost_per_token_above_272k_tokens":4.4e-7,"output_cost_per_token_above_272k_tokens":1.98e-6,"cache_read_input_token_cost_above_272k_tokens":4.4e-8,"cache_creation_input_token_cost_above_272k_tokens":5.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null},{"id":"azure/gpt-5.6-luna@eu","object":"model","created":1784804086,"owned_by":"azure","model_name":"gpt-5.6-luna","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2.2000000000000004e-7,"output_cost_per_token":1.32e-6,"input_cost_per_token_flex":1.1e-7,"output_cost_per_token_flex":6.6e-7,"cache_read_input_token_cost":2.2000000000000005e-8,"input_cost_per_token_priority":4.4e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":2.64e-6,"cache_creation_input_token_cost":2.7500000000000007e-7,"cache_read_input_token_cost_flex":1.1000000000000001e-8,"cache_creation_input_token_cost_flex":1.375e-7,"cache_read_input_token_cost_priority":4.4000000000000004e-8,"input_cost_per_token_above_272k_tokens":4.400000000000001e-7,"output_cost_per_token_above_272k_tokens":1.98e-6,"cache_creation_input_token_cost_priority":5.5e-7,"input_cost_per_token_above_272k_tokens_flex":2.2e-7,"output_cost_per_token_above_272k_tokens_flex":9.9e-7,"cache_read_input_token_cost_above_272k_tokens":4.400000000000001e-8,"input_cost_per_token_above_272k_tokens_priority":8.8e-7,"output_cost_per_token_above_272k_tokens_priority":3.96e-6,"cache_creation_input_token_cost_above_272k_tokens":5.500000000000001e-7,"cache_read_input_token_cost_above_272k_tokens_flex":2.2000000000000002e-8,"cache_creation_input_token_cost_above_272k_tokens_flex":2.75e-7,"cache_read_input_token_cost_above_272k_tokens_priority":8.800000000000001e-8,"cache_creation_input_token_cost_above_272k_tokens_priority":1.1e-6},"list_pricing":{"input_cost_per_token":2.2000000000000004e-7,"output_cost_per_token":1.32e-6,"input_cost_per_token_flex":1.1e-7,"output_cost_per_token_flex":6.6e-7,"cache_read_input_token_cost":2.2000000000000005e-8,"input_cost_per_token_priority":4.4e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":2.64e-6,"cache_creation_input_token_cost":2.7500000000000007e-7,"cache_read_input_token_cost_flex":1.1000000000000001e-8,"cache_creation_input_token_cost_flex":1.375e-7,"cache_read_input_token_cost_priority":4.4000000000000004e-8,"input_cost_per_token_above_272k_tokens":4.400000000000001e-7,"output_cost_per_token_above_272k_tokens":1.98e-6,"cache_creation_input_token_cost_priority":5.5e-7,"input_cost_per_token_above_272k_tokens_flex":2.2e-7,"output_cost_per_token_above_272k_tokens_flex":9.9e-7,"cache_read_input_token_cost_above_272k_tokens":4.400000000000001e-8,"input_cost_per_token_above_272k_tokens_priority":8.8e-7,"output_cost_per_token_above_272k_tokens_priority":3.96e-6,"cache_creation_input_token_cost_above_272k_tokens":5.500000000000001e-7,"cache_read_input_token_cost_above_272k_tokens_flex":2.2000000000000002e-8,"cache_creation_input_token_cost_above_272k_tokens_flex":2.75e-7,"cache_read_input_token_cost_above_272k_tokens_priority":8.800000000000001e-8,"cache_creation_input_token_cost_above_272k_tokens_priority":1.1e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"azure/gpt-5.6-luna","object":"model","created":1784804086,"owned_by":"azure","model_name":"gpt-5.6-luna","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2.0000000000000002e-7,"output_cost_per_token":1.2e-6,"input_cost_per_token_flex":1e-7,"output_cost_per_token_flex":6e-7,"cache_read_input_token_cost":2.0000000000000004e-8,"input_cost_per_token_priority":4e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":2.4e-6,"cache_creation_input_token_cost":2.5000000000000004e-7,"cache_read_input_token_cost_flex":1e-8,"cache_creation_input_token_cost_flex":1.25e-7,"cache_read_input_token_cost_priority":4e-8,"input_cost_per_token_above_272k_tokens":4.0000000000000003e-7,"output_cost_per_token_above_272k_tokens":1.8000000000000001e-6,"cache_creation_input_token_cost_priority":5e-7,"input_cost_per_token_above_272k_tokens_flex":2e-7,"output_cost_per_token_above_272k_tokens_flex":9e-7,"cache_read_input_token_cost_above_272k_tokens":4.000000000000001e-8,"input_cost_per_token_above_272k_tokens_priority":8e-7,"output_cost_per_token_above_272k_tokens_priority":3.6e-6,"cache_creation_input_token_cost_above_272k_tokens":5.000000000000001e-7,"cache_read_input_token_cost_above_272k_tokens_flex":2e-8,"cache_creation_input_token_cost_above_272k_tokens_flex":2.5e-7,"cache_read_input_token_cost_above_272k_tokens_priority":8e-8,"cache_creation_input_token_cost_above_272k_tokens_priority":1e-6},"list_pricing":{"input_cost_per_token":2.0000000000000002e-7,"output_cost_per_token":1.2e-6,"input_cost_per_token_flex":1e-7,"output_cost_per_token_flex":6e-7,"cache_read_input_token_cost":2.0000000000000004e-8,"input_cost_per_token_priority":4e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":2.4e-6,"cache_creation_input_token_cost":2.5000000000000004e-7,"cache_read_input_token_cost_flex":1e-8,"cache_creation_input_token_cost_flex":1.25e-7,"cache_read_input_token_cost_priority":4e-8,"input_cost_per_token_above_272k_tokens":4.0000000000000003e-7,"output_cost_per_token_above_272k_tokens":1.8000000000000001e-6,"cache_creation_input_token_cost_priority":5e-7,"input_cost_per_token_above_272k_tokens_flex":2e-7,"output_cost_per_token_above_272k_tokens_flex":9e-7,"cache_read_input_token_cost_above_272k_tokens":4.000000000000001e-8,"input_cost_per_token_above_272k_tokens_priority":8e-7,"output_cost_per_token_above_272k_tokens_priority":3.6e-6,"cache_creation_input_token_cost_above_272k_tokens":5.000000000000001e-7,"cache_read_input_token_cost_above_272k_tokens_flex":2e-8,"cache_creation_input_token_cost_above_272k_tokens_flex":2.5e-7,"cache_read_input_token_cost_above_272k_tokens_priority":8e-8,"cache_creation_input_token_cost_above_272k_tokens_priority":1e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"azure/gpt-5.6-luna@us","object":"model","created":1784804086,"owned_by":"azure","model_name":"gpt-5.6-luna","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2.2000000000000004e-7,"output_cost_per_token":1.32e-6,"input_cost_per_token_flex":1.1e-7,"output_cost_per_token_flex":6.6e-7,"cache_read_input_token_cost":2.2000000000000005e-8,"input_cost_per_token_priority":4.4e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":2.64e-6,"cache_creation_input_token_cost":2.7500000000000007e-7,"cache_read_input_token_cost_flex":1.1000000000000001e-8,"cache_creation_input_token_cost_flex":1.375e-7,"cache_read_input_token_cost_priority":4.4000000000000004e-8,"input_cost_per_token_above_272k_tokens":4.400000000000001e-7,"output_cost_per_token_above_272k_tokens":1.98e-6,"cache_creation_input_token_cost_priority":5.5e-7,"input_cost_per_token_above_272k_tokens_flex":2.2e-7,"output_cost_per_token_above_272k_tokens_flex":9.9e-7,"cache_read_input_token_cost_above_272k_tokens":4.400000000000001e-8,"input_cost_per_token_above_272k_tokens_priority":8.8e-7,"output_cost_per_token_above_272k_tokens_priority":3.96e-6,"cache_creation_input_token_cost_above_272k_tokens":5.500000000000001e-7,"cache_read_input_token_cost_above_272k_tokens_flex":2.2000000000000002e-8,"cache_creation_input_token_cost_above_272k_tokens_flex":2.75e-7,"cache_read_input_token_cost_above_272k_tokens_priority":8.800000000000001e-8,"cache_creation_input_token_cost_above_272k_tokens_priority":1.1e-6},"list_pricing":{"input_cost_per_token":2.2000000000000004e-7,"output_cost_per_token":1.32e-6,"input_cost_per_token_flex":1.1e-7,"output_cost_per_token_flex":6.6e-7,"cache_read_input_token_cost":2.2000000000000005e-8,"input_cost_per_token_priority":4.4e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":2.64e-6,"cache_creation_input_token_cost":2.7500000000000007e-7,"cache_read_input_token_cost_flex":1.1000000000000001e-8,"cache_creation_input_token_cost_flex":1.375e-7,"cache_read_input_token_cost_priority":4.4000000000000004e-8,"input_cost_per_token_above_272k_tokens":4.400000000000001e-7,"output_cost_per_token_above_272k_tokens":1.98e-6,"cache_creation_input_token_cost_priority":5.5e-7,"input_cost_per_token_above_272k_tokens_flex":2.2e-7,"output_cost_per_token_above_272k_tokens_flex":9.9e-7,"cache_read_input_token_cost_above_272k_tokens":4.400000000000001e-8,"input_cost_per_token_above_272k_tokens_priority":8.8e-7,"output_cost_per_token_above_272k_tokens_priority":3.96e-6,"cache_creation_input_token_cost_above_272k_tokens":5.500000000000001e-7,"cache_read_input_token_cost_above_272k_tokens_flex":2.2000000000000002e-8,"cache_creation_input_token_cost_above_272k_tokens_flex":2.75e-7,"cache_read_input_token_cost_above_272k_tokens_priority":8.800000000000001e-8,"cache_creation_input_token_cost_above_272k_tokens_priority":1.1e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"databricks/databricks-gpt-5-6-luna@eu","object":"model","created":1783590864,"owned_by":"databricks","model_name":"databricks-gpt-5-6-luna","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5.6 Luna is the fast, cost-efficient model in OpenAI's GPT-5.6 family, bringing strong reasoning and agentic capability at the lowest cost in the lineup. This model supports multimodal (text and image) inputs and a long context window. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["file","image","text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":1.2e-6,"input_dbu_cost_per_token":2.857e-6,"output_dbu_cost_per_token":0.000017143,"cache_read_input_token_cost":2e-8,"input_cost_per_token_priority":4e-7,"output_cost_per_token_priority":2.4e-6,"cache_creation_input_token_cost":2.5e-7,"input_cost_per_token_above_272k_tokens":4e-7,"output_cost_per_token_above_272k_tokens":1.8e-6,"cache_creation_input_token_cost_priority":5e-7,"cache_read_input_token_cost_above_272k_tokens":4e-8,"input_cost_per_token_above_272k_tokens_priority":8e-7,"output_cost_per_token_above_272k_tokens_priority":3.6e-6,"cache_creation_input_token_cost_above_272k_tokens":5e-7,"cache_read_input_token_cost_above_272k_tokens_priority":8e-8,"cache_creation_input_token_cost_above_272k_tokens_priority":1e-6},"list_pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":1.2e-6,"input_dbu_cost_per_token":2.857e-6,"output_dbu_cost_per_token":0.000017143,"cache_read_input_token_cost":2e-8,"input_cost_per_token_priority":4e-7,"output_cost_per_token_priority":2.4e-6,"cache_creation_input_token_cost":2.5e-7,"input_cost_per_token_above_272k_tokens":4e-7,"output_cost_per_token_above_272k_tokens":1.8e-6,"cache_creation_input_token_cost_priority":5e-7,"cache_read_input_token_cost_above_272k_tokens":4e-8,"input_cost_per_token_above_272k_tokens_priority":8e-7,"output_cost_per_token_above_272k_tokens_priority":3.6e-6,"cache_creation_input_token_cost_above_272k_tokens":5e-7,"cache_read_input_token_cost_above_272k_tokens_priority":8e-8,"cache_creation_input_token_cost_above_272k_tokens_priority":1e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"databricks/databricks-gpt-5-6-luna","object":"model","created":1783590864,"owned_by":"databricks","model_name":"databricks-gpt-5-6-luna","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5.6 Luna is the fast, cost-efficient model in OpenAI's GPT-5.6 family, bringing strong reasoning and agentic capability at the lowest cost in the lineup. This model supports multimodal (text and image) inputs and a long context window. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["file","image","text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":1.2e-6,"input_dbu_cost_per_token":2.857e-6,"output_dbu_cost_per_token":0.000017143,"cache_read_input_token_cost":2e-8,"input_cost_per_token_priority":4e-7,"output_cost_per_token_priority":2.4e-6,"cache_creation_input_token_cost":2.5e-7,"input_cost_per_token_above_272k_tokens":4e-7,"output_cost_per_token_above_272k_tokens":1.8e-6,"cache_creation_input_token_cost_priority":5e-7,"cache_read_input_token_cost_above_272k_tokens":4e-8,"input_cost_per_token_above_272k_tokens_priority":8e-7,"output_cost_per_token_above_272k_tokens_priority":3.6e-6,"cache_creation_input_token_cost_above_272k_tokens":5e-7,"cache_read_input_token_cost_above_272k_tokens_priority":8e-8,"cache_creation_input_token_cost_above_272k_tokens_priority":1e-6},"list_pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":1.2e-6,"input_dbu_cost_per_token":2.857e-6,"output_dbu_cost_per_token":0.000017143,"cache_read_input_token_cost":2e-8,"input_cost_per_token_priority":4e-7,"output_cost_per_token_priority":2.4e-6,"cache_creation_input_token_cost":2.5e-7,"input_cost_per_token_above_272k_tokens":4e-7,"output_cost_per_token_above_272k_tokens":1.8e-6,"cache_creation_input_token_cost_priority":5e-7,"cache_read_input_token_cost_above_272k_tokens":4e-8,"input_cost_per_token_above_272k_tokens_priority":8e-7,"output_cost_per_token_above_272k_tokens_priority":3.6e-6,"cache_creation_input_token_cost_above_272k_tokens":5e-7,"cache_read_input_token_cost_above_272k_tokens_priority":8e-8,"cache_creation_input_token_cost_above_272k_tokens_priority":1e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"openai/gpt-5.6-luna","object":"model","created":1783590864,"owned_by":"openai","model_name":"gpt-5.6-luna","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series.","source":null,"capabilities":{"input_modalities":["file","image","text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":1.2e-6,"input_cost_per_token_flex":1e-7,"output_cost_per_token_flex":6e-7,"cache_read_input_token_cost":2e-8,"input_cost_per_token_batches":1e-7,"input_cost_per_token_priority":4e-7,"output_cost_per_token_batches":6e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"output_cost_per_token_priority":2.4e-6,"cache_creation_input_token_cost":2.5e-7,"cache_read_input_token_cost_flex":1e-8,"cache_read_input_token_cost_batches":1e-8,"cache_creation_input_token_cost_flex":1.25e-7,"cache_read_input_token_cost_priority":4e-8,"input_cost_per_token_above_272k_tokens":4e-7,"output_cost_per_token_above_272k_tokens":1.8e-6,"cache_creation_input_token_cost_priority":5e-7,"cache_creation_input_token_cost_above_12hr":5e-7,"input_cost_per_token_above_272k_tokens_flex":2e-7,"output_cost_per_token_above_272k_tokens_flex":9e-7,"cache_read_input_token_cost_above_272k_tokens":4e-8,"cache_creation_input_token_cost_above_12hr_flex":2.5e-7,"input_cost_per_token_above_272k_tokens_priority":8e-7,"output_cost_per_token_above_272k_tokens_priority":3.6e-6,"cache_creation_input_token_cost_above_272k_tokens":5e-7,"cache_read_input_token_cost_above_272k_tokens_flex":2e-8,"cache_creation_input_token_cost_above_12hr_priority":1e-6,"cache_creation_input_token_cost_above_272k_tokens_flex":2.5e-7,"cache_read_input_token_cost_above_272k_tokens_priority":8e-8,"cache_creation_input_token_cost_above_272k_tokens_priority":1e-6,"cache_creation_input_token_cost_above_12hr_above_272k_tokens":1e-6,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_flex":5e-7,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_priority":2e-6},"list_pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":1.2e-6,"input_cost_per_token_flex":1e-7,"output_cost_per_token_flex":6e-7,"cache_read_input_token_cost":2e-8,"input_cost_per_token_batches":1e-7,"input_cost_per_token_priority":4e-7,"output_cost_per_token_batches":6e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"output_cost_per_token_priority":2.4e-6,"cache_creation_input_token_cost":2.5e-7,"cache_read_input_token_cost_flex":1e-8,"cache_read_input_token_cost_batches":1e-8,"cache_creation_input_token_cost_flex":1.25e-7,"cache_read_input_token_cost_priority":4e-8,"input_cost_per_token_above_272k_tokens":4e-7,"output_cost_per_token_above_272k_tokens":1.8e-6,"cache_creation_input_token_cost_priority":5e-7,"cache_creation_input_token_cost_above_12hr":5e-7,"input_cost_per_token_above_272k_tokens_flex":2e-7,"output_cost_per_token_above_272k_tokens_flex":9e-7,"cache_read_input_token_cost_above_272k_tokens":4e-8,"cache_creation_input_token_cost_above_12hr_flex":2.5e-7,"input_cost_per_token_above_272k_tokens_priority":8e-7,"output_cost_per_token_above_272k_tokens_priority":3.6e-6,"cache_creation_input_token_cost_above_272k_tokens":5e-7,"cache_read_input_token_cost_above_272k_tokens_flex":2e-8,"cache_creation_input_token_cost_above_12hr_priority":1e-6,"cache_creation_input_token_cost_above_272k_tokens_flex":2.5e-7,"cache_read_input_token_cost_above_272k_tokens_priority":8e-8,"cache_creation_input_token_cost_above_272k_tokens_priority":1e-6,"cache_creation_input_token_cost_above_12hr_above_272k_tokens":1e-6,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_flex":5e-7,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_priority":2e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":8},{"id":"gpt-5.6-sol","object":"model","created":1787461792,"owned_by":"openai","mode":"chat","context_length":1050000,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":4e-6,"output_cost_per_token":0.00002,"input_cost_per_token_flex":2e-6,"output_cost_per_token_flex":0.00001,"cache_read_input_token_cost":4e-7,"input_cost_per_token_batches":2e-6,"input_cost_per_token_priority":8e-6,"output_cost_per_token_batches":0.00001,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"output_cost_per_token_priority":0.00004,"cache_creation_input_token_cost":5e-6,"cache_read_input_token_cost_flex":2e-7,"cache_read_input_token_cost_batches":2e-7,"cache_creation_input_token_cost_flex":2.5e-6,"cache_read_input_token_cost_priority":8e-7,"input_cost_per_token_above_272k_tokens":8e-6,"output_cost_per_token_above_272k_tokens":0.00003,"cache_creation_input_token_cost_priority":0.00001,"cache_creation_input_token_cost_above_12hr":0.00001,"input_cost_per_token_above_272k_tokens_flex":4e-6,"output_cost_per_token_above_272k_tokens_flex":0.000015,"cache_read_input_token_cost_above_272k_tokens":8e-7,"cache_creation_input_token_cost_above_12hr_flex":5e-6,"input_cost_per_token_above_272k_tokens_priority":0.000016,"output_cost_per_token_above_272k_tokens_priority":0.00006,"cache_creation_input_token_cost_above_272k_tokens":0.00001,"cache_read_input_token_cost_above_272k_tokens_flex":4e-7,"cache_creation_input_token_cost_above_12hr_priority":0.00002,"cache_creation_input_token_cost_above_272k_tokens_flex":5e-6,"cache_read_input_token_cost_above_272k_tokens_priority":1.6e-6,"cache_creation_input_token_cost_above_272k_tokens_priority":0.00002,"cache_creation_input_token_cost_above_12hr_above_272k_tokens":0.00002,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_flex":0.00001,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_priority":0.00004},"pricing_endpoint":"openai/gpt-5.6-sol","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"amazon/openai.gpt-5.6-sol","object":"model","created":1787461792,"owned_by":"amazon","model_name":"openai.gpt-5.6-sol","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4.4e-6,"output_cost_per_token":0.000022,"cache_read_input_token_cost":4.4e-7,"cache_creation_input_token_cost":5.5e-6,"input_cost_per_token_above_272k_tokens":8.8e-6,"output_cost_per_token_above_272k_tokens":0.000033,"cache_read_input_token_cost_above_272k_tokens":8.8e-7,"cache_creation_input_token_cost_above_272k_tokens":0.000011},"list_pricing":{"input_cost_per_token":4.4e-6,"output_cost_per_token":0.000022,"cache_read_input_token_cost":4.4e-7,"cache_creation_input_token_cost":5.5e-6,"input_cost_per_token_above_272k_tokens":8.8e-6,"output_cost_per_token_above_272k_tokens":0.000033,"cache_read_input_token_cost_above_272k_tokens":8.8e-7,"cache_creation_input_token_cost_above_272k_tokens":0.000011},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"amazon/openai.gpt-5.6-sol@us","object":"model","created":1787461792,"owned_by":"amazon","model_name":"openai.gpt-5.6-sol","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4.4e-6,"output_cost_per_token":0.000022,"cache_read_input_token_cost":4.4e-7,"cache_creation_input_token_cost":5.5e-6,"input_cost_per_token_above_272k_tokens":8.8e-6,"output_cost_per_token_above_272k_tokens":0.000033,"cache_read_input_token_cost_above_272k_tokens":8.8e-7,"cache_creation_input_token_cost_above_272k_tokens":0.000011},"list_pricing":{"input_cost_per_token":4.4e-6,"output_cost_per_token":0.000022,"cache_read_input_token_cost":4.4e-7,"cache_creation_input_token_cost":5.5e-6,"input_cost_per_token_above_272k_tokens":8.8e-6,"output_cost_per_token_above_272k_tokens":0.000033,"cache_read_input_token_cost_above_272k_tokens":8.8e-7,"cache_creation_input_token_cost_above_272k_tokens":0.000011},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null},{"id":"azure/gpt-5.6-sol@eu","object":"model","created":1784804086,"owned_by":"azure","model_name":"gpt-5.6-sol","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":4.4e-6,"output_cost_per_token":0.000022000000000000003,"input_cost_per_token_flex":2.2e-6,"output_cost_per_token_flex":0.000011000000000000001,"cache_read_input_token_cost":4.4e-7,"input_cost_per_token_priority":8.8e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.000044000000000000006,"cache_creation_input_token_cost":5.5e-6,"cache_read_input_token_cost_flex":2.2e-7,"cache_creation_input_token_cost_flex":2.7500000000000004e-6,"cache_read_input_token_cost_priority":8.8e-7,"input_cost_per_token_above_272k_tokens":8.8e-6,"output_cost_per_token_above_272k_tokens":0.000033,"cache_creation_input_token_cost_priority":0.000011000000000000001,"input_cost_per_token_above_272k_tokens_flex":4.4e-6,"output_cost_per_token_above_272k_tokens_flex":0.0000165,"cache_read_input_token_cost_above_272k_tokens":8.8e-7,"input_cost_per_token_above_272k_tokens_priority":0.0000176,"output_cost_per_token_above_272k_tokens_priority":0.000066,"cache_creation_input_token_cost_above_272k_tokens":0.000011,"cache_read_input_token_cost_above_272k_tokens_flex":4.4e-7,"cache_creation_input_token_cost_above_272k_tokens_flex":5.500000000000001e-6,"cache_read_input_token_cost_above_272k_tokens_priority":1.76e-6,"cache_creation_input_token_cost_above_272k_tokens_priority":0.000022000000000000003},"list_pricing":{"input_cost_per_token":4.4e-6,"output_cost_per_token":0.000022000000000000003,"input_cost_per_token_flex":2.2e-6,"output_cost_per_token_flex":0.000011000000000000001,"cache_read_input_token_cost":4.4e-7,"input_cost_per_token_priority":8.8e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.000044000000000000006,"cache_creation_input_token_cost":5.5e-6,"cache_read_input_token_cost_flex":2.2e-7,"cache_creation_input_token_cost_flex":2.7500000000000004e-6,"cache_read_input_token_cost_priority":8.8e-7,"input_cost_per_token_above_272k_tokens":8.8e-6,"output_cost_per_token_above_272k_tokens":0.000033,"cache_creation_input_token_cost_priority":0.000011000000000000001,"input_cost_per_token_above_272k_tokens_flex":4.4e-6,"output_cost_per_token_above_272k_tokens_flex":0.0000165,"cache_read_input_token_cost_above_272k_tokens":8.8e-7,"input_cost_per_token_above_272k_tokens_priority":0.0000176,"output_cost_per_token_above_272k_tokens_priority":0.000066,"cache_creation_input_token_cost_above_272k_tokens":0.000011,"cache_read_input_token_cost_above_272k_tokens_flex":4.4e-7,"cache_creation_input_token_cost_above_272k_tokens_flex":5.500000000000001e-6,"cache_read_input_token_cost_above_272k_tokens_priority":1.76e-6,"cache_creation_input_token_cost_above_272k_tokens_priority":0.000022000000000000003},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"azure/gpt-5.6-sol","object":"model","created":1784804086,"owned_by":"azure","model_name":"gpt-5.6-sol","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":4e-6,"output_cost_per_token":0.00002,"input_cost_per_token_flex":2e-6,"output_cost_per_token_flex":0.00001,"cache_read_input_token_cost":4e-7,"input_cost_per_token_priority":8e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.00004,"cache_creation_input_token_cost":4.9999999999999996e-6,"cache_read_input_token_cost_flex":2e-7,"cache_creation_input_token_cost_flex":2.5e-6,"cache_read_input_token_cost_priority":8e-7,"input_cost_per_token_above_272k_tokens":8e-6,"output_cost_per_token_above_272k_tokens":0.00003,"cache_creation_input_token_cost_priority":0.00001,"input_cost_per_token_above_272k_tokens_flex":4e-6,"output_cost_per_token_above_272k_tokens_flex":0.000015,"cache_read_input_token_cost_above_272k_tokens":8e-7,"input_cost_per_token_above_272k_tokens_priority":0.000016,"output_cost_per_token_above_272k_tokens_priority":0.00006,"cache_creation_input_token_cost_above_272k_tokens":9.999999999999999e-6,"cache_read_input_token_cost_above_272k_tokens_flex":4e-7,"cache_creation_input_token_cost_above_272k_tokens_flex":5e-6,"cache_read_input_token_cost_above_272k_tokens_priority":1.6e-6,"cache_creation_input_token_cost_above_272k_tokens_priority":0.00002},"list_pricing":{"input_cost_per_token":4e-6,"output_cost_per_token":0.00002,"input_cost_per_token_flex":2e-6,"output_cost_per_token_flex":0.00001,"cache_read_input_token_cost":4e-7,"input_cost_per_token_priority":8e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.00004,"cache_creation_input_token_cost":4.9999999999999996e-6,"cache_read_input_token_cost_flex":2e-7,"cache_creation_input_token_cost_flex":2.5e-6,"cache_read_input_token_cost_priority":8e-7,"input_cost_per_token_above_272k_tokens":8e-6,"output_cost_per_token_above_272k_tokens":0.00003,"cache_creation_input_token_cost_priority":0.00001,"input_cost_per_token_above_272k_tokens_flex":4e-6,"output_cost_per_token_above_272k_tokens_flex":0.000015,"cache_read_input_token_cost_above_272k_tokens":8e-7,"input_cost_per_token_above_272k_tokens_priority":0.000016,"output_cost_per_token_above_272k_tokens_priority":0.00006,"cache_creation_input_token_cost_above_272k_tokens":9.999999999999999e-6,"cache_read_input_token_cost_above_272k_tokens_flex":4e-7,"cache_creation_input_token_cost_above_272k_tokens_flex":5e-6,"cache_read_input_token_cost_above_272k_tokens_priority":1.6e-6,"cache_creation_input_token_cost_above_272k_tokens_priority":0.00002},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"azure/gpt-5.6-sol@us","object":"model","created":1784804086,"owned_by":"azure","model_name":"gpt-5.6-sol","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":4.4e-6,"output_cost_per_token":0.000022000000000000003,"input_cost_per_token_flex":2.2e-6,"output_cost_per_token_flex":0.000011000000000000001,"cache_read_input_token_cost":4.4e-7,"input_cost_per_token_priority":8.8e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.000044000000000000006,"cache_creation_input_token_cost":5.5e-6,"cache_read_input_token_cost_flex":2.2e-7,"cache_creation_input_token_cost_flex":2.7500000000000004e-6,"cache_read_input_token_cost_priority":8.8e-7,"input_cost_per_token_above_272k_tokens":8.8e-6,"output_cost_per_token_above_272k_tokens":0.000033,"cache_creation_input_token_cost_priority":0.000011000000000000001,"input_cost_per_token_above_272k_tokens_flex":4.4e-6,"output_cost_per_token_above_272k_tokens_flex":0.0000165,"cache_read_input_token_cost_above_272k_tokens":8.8e-7,"input_cost_per_token_above_272k_tokens_priority":0.0000176,"output_cost_per_token_above_272k_tokens_priority":0.000066,"cache_creation_input_token_cost_above_272k_tokens":0.000011,"cache_read_input_token_cost_above_272k_tokens_flex":4.4e-7,"cache_creation_input_token_cost_above_272k_tokens_flex":5.500000000000001e-6,"cache_read_input_token_cost_above_272k_tokens_priority":1.76e-6,"cache_creation_input_token_cost_above_272k_tokens_priority":0.000022000000000000003},"list_pricing":{"input_cost_per_token":4.4e-6,"output_cost_per_token":0.000022000000000000003,"input_cost_per_token_flex":2.2e-6,"output_cost_per_token_flex":0.000011000000000000001,"cache_read_input_token_cost":4.4e-7,"input_cost_per_token_priority":8.8e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.000044000000000000006,"cache_creation_input_token_cost":5.5e-6,"cache_read_input_token_cost_flex":2.2e-7,"cache_creation_input_token_cost_flex":2.7500000000000004e-6,"cache_read_input_token_cost_priority":8.8e-7,"input_cost_per_token_above_272k_tokens":8.8e-6,"output_cost_per_token_above_272k_tokens":0.000033,"cache_creation_input_token_cost_priority":0.000011000000000000001,"input_cost_per_token_above_272k_tokens_flex":4.4e-6,"output_cost_per_token_above_272k_tokens_flex":0.0000165,"cache_read_input_token_cost_above_272k_tokens":8.8e-7,"input_cost_per_token_above_272k_tokens_priority":0.0000176,"output_cost_per_token_above_272k_tokens_priority":0.000066,"cache_creation_input_token_cost_above_272k_tokens":0.000011,"cache_read_input_token_cost_above_272k_tokens_flex":4.4e-7,"cache_creation_input_token_cost_above_272k_tokens_flex":5.500000000000001e-6,"cache_read_input_token_cost_above_272k_tokens_priority":1.76e-6,"cache_creation_input_token_cost_above_272k_tokens_priority":0.000022000000000000003},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"databricks/databricks-gpt-5-6-sol@eu","object":"model","created":1783590850,"owned_by":"databricks","model_name":"databricks-gpt-5-6-sol","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5.6 Sol is OpenAI's flagship model in the GPT-5.6 family, delivering state-of-the-art performance on agentic coding, long-horizon reasoning, and complex tool use, with support for a new maximum reasoning effort. This model supports multimodal (text and image) inputs and a long context window. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["file","image","text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":4e-6,"output_cost_per_token":0.00002,"input_dbu_cost_per_token":0.000057143,"output_dbu_cost_per_token":0.000285714,"cache_read_input_token_cost":4e-7,"cache_creation_input_token_cost":5e-6,"input_cost_per_token_above_272k_tokens":8e-6,"output_cost_per_token_above_272k_tokens":0.00003,"cache_creation_input_token_cost_priority":0.00001,"cache_read_input_token_cost_above_272k_tokens":8e-7,"input_cost_per_token_above_272k_tokens_priority":0.000016,"output_cost_per_token_above_272k_tokens_priority":0.00006,"cache_creation_input_token_cost_above_272k_tokens":0.00001,"cache_read_input_token_cost_above_272k_tokens_priority":1.6e-6,"cache_creation_input_token_cost_above_272k_tokens_priority":0.00002},"list_pricing":{"input_cost_per_token":4e-6,"output_cost_per_token":0.00002,"input_dbu_cost_per_token":0.000057143,"output_dbu_cost_per_token":0.000285714,"cache_read_input_token_cost":4e-7,"cache_creation_input_token_cost":5e-6,"input_cost_per_token_above_272k_tokens":8e-6,"output_cost_per_token_above_272k_tokens":0.00003,"cache_creation_input_token_cost_priority":0.00001,"cache_read_input_token_cost_above_272k_tokens":8e-7,"input_cost_per_token_above_272k_tokens_priority":0.000016,"output_cost_per_token_above_272k_tokens_priority":0.00006,"cache_creation_input_token_cost_above_272k_tokens":0.00001,"cache_read_input_token_cost_above_272k_tokens_priority":1.6e-6,"cache_creation_input_token_cost_above_272k_tokens_priority":0.00002},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"databricks/databricks-gpt-5-6-sol","object":"model","created":1783590850,"owned_by":"databricks","model_name":"databricks-gpt-5-6-sol","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5.6 Sol is OpenAI's flagship model in the GPT-5.6 family, delivering state-of-the-art performance on agentic coding, long-horizon reasoning, and complex tool use, with support for a new maximum reasoning effort. This model supports multimodal (text and image) inputs and a long context window. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["file","image","text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":4e-6,"output_cost_per_token":0.00002,"input_dbu_cost_per_token":0.000057143,"output_dbu_cost_per_token":0.000285714,"cache_read_input_token_cost":4e-7,"cache_creation_input_token_cost":5e-6,"input_cost_per_token_above_272k_tokens":8e-6,"output_cost_per_token_above_272k_tokens":0.00003,"cache_creation_input_token_cost_priority":0.00001,"cache_read_input_token_cost_above_272k_tokens":8e-7,"input_cost_per_token_above_272k_tokens_priority":0.000016,"output_cost_per_token_above_272k_tokens_priority":0.00006,"cache_creation_input_token_cost_above_272k_tokens":0.00001,"cache_read_input_token_cost_above_272k_tokens_priority":1.6e-6,"cache_creation_input_token_cost_above_272k_tokens_priority":0.00002},"list_pricing":{"input_cost_per_token":4e-6,"output_cost_per_token":0.00002,"input_dbu_cost_per_token":0.000057143,"output_dbu_cost_per_token":0.000285714,"cache_read_input_token_cost":4e-7,"cache_creation_input_token_cost":5e-6,"input_cost_per_token_above_272k_tokens":8e-6,"output_cost_per_token_above_272k_tokens":0.00003,"cache_creation_input_token_cost_priority":0.00001,"cache_read_input_token_cost_above_272k_tokens":8e-7,"input_cost_per_token_above_272k_tokens_priority":0.000016,"output_cost_per_token_above_272k_tokens_priority":0.00006,"cache_creation_input_token_cost_above_272k_tokens":0.00001,"cache_read_input_token_cost_above_272k_tokens_priority":1.6e-6,"cache_creation_input_token_cost_above_272k_tokens_priority":0.00002},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"openai/gpt-5.6-sol","object":"model","created":1783590850,"owned_by":"openai","model_name":"gpt-5.6-sol","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series.","source":null,"capabilities":{"input_modalities":["file","image","text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":4e-6,"output_cost_per_token":0.00002,"input_cost_per_token_flex":2e-6,"output_cost_per_token_flex":0.00001,"cache_read_input_token_cost":4e-7,"input_cost_per_token_batches":2e-6,"input_cost_per_token_priority":8e-6,"output_cost_per_token_batches":0.00001,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"output_cost_per_token_priority":0.00004,"cache_creation_input_token_cost":5e-6,"cache_read_input_token_cost_flex":2e-7,"cache_read_input_token_cost_batches":2e-7,"cache_creation_input_token_cost_flex":2.5e-6,"cache_read_input_token_cost_priority":8e-7,"input_cost_per_token_above_272k_tokens":8e-6,"output_cost_per_token_above_272k_tokens":0.00003,"cache_creation_input_token_cost_priority":0.00001,"cache_creation_input_token_cost_above_12hr":0.00001,"input_cost_per_token_above_272k_tokens_flex":4e-6,"output_cost_per_token_above_272k_tokens_flex":0.000015,"cache_read_input_token_cost_above_272k_tokens":8e-7,"cache_creation_input_token_cost_above_12hr_flex":5e-6,"input_cost_per_token_above_272k_tokens_priority":0.000016,"output_cost_per_token_above_272k_tokens_priority":0.00006,"cache_creation_input_token_cost_above_272k_tokens":0.00001,"cache_read_input_token_cost_above_272k_tokens_flex":4e-7,"cache_creation_input_token_cost_above_12hr_priority":0.00002,"cache_creation_input_token_cost_above_272k_tokens_flex":5e-6,"cache_read_input_token_cost_above_272k_tokens_priority":1.6e-6,"cache_creation_input_token_cost_above_272k_tokens_priority":0.00002,"cache_creation_input_token_cost_above_12hr_above_272k_tokens":0.00002,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_flex":0.00001,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_priority":0.00004},"list_pricing":{"input_cost_per_token":4e-6,"output_cost_per_token":0.00002,"input_cost_per_token_flex":2e-6,"output_cost_per_token_flex":0.00001,"cache_read_input_token_cost":4e-7,"input_cost_per_token_batches":2e-6,"input_cost_per_token_priority":8e-6,"output_cost_per_token_batches":0.00001,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"output_cost_per_token_priority":0.00004,"cache_creation_input_token_cost":5e-6,"cache_read_input_token_cost_flex":2e-7,"cache_read_input_token_cost_batches":2e-7,"cache_creation_input_token_cost_flex":2.5e-6,"cache_read_input_token_cost_priority":8e-7,"input_cost_per_token_above_272k_tokens":8e-6,"output_cost_per_token_above_272k_tokens":0.00003,"cache_creation_input_token_cost_priority":0.00001,"cache_creation_input_token_cost_above_12hr":0.00001,"input_cost_per_token_above_272k_tokens_flex":4e-6,"output_cost_per_token_above_272k_tokens_flex":0.000015,"cache_read_input_token_cost_above_272k_tokens":8e-7,"cache_creation_input_token_cost_above_12hr_flex":5e-6,"input_cost_per_token_above_272k_tokens_priority":0.000016,"output_cost_per_token_above_272k_tokens_priority":0.00006,"cache_creation_input_token_cost_above_272k_tokens":0.00001,"cache_read_input_token_cost_above_272k_tokens_flex":4e-7,"cache_creation_input_token_cost_above_12hr_priority":0.00002,"cache_creation_input_token_cost_above_272k_tokens_flex":5e-6,"cache_read_input_token_cost_above_272k_tokens_priority":1.6e-6,"cache_creation_input_token_cost_above_272k_tokens_priority":0.00002,"cache_creation_input_token_cost_above_12hr_above_272k_tokens":0.00002,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_flex":0.00001,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_priority":0.00004},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":8},{"id":"gpt-5.6-terra","object":"model","created":1787461792,"owned_by":"openai","mode":"chat","context_length":1050000,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.000012,"input_cost_per_token_flex":1e-6,"output_cost_per_token_flex":6e-6,"cache_read_input_token_cost":2e-7,"input_cost_per_token_batches":1e-6,"input_cost_per_token_priority":4e-6,"output_cost_per_token_batches":6e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"output_cost_per_token_priority":0.000024,"cache_creation_input_token_cost":2.5e-6,"cache_read_input_token_cost_flex":1e-7,"cache_read_input_token_cost_batches":1e-7,"cache_creation_input_token_cost_flex":1.25e-6,"cache_read_input_token_cost_priority":4e-7,"input_cost_per_token_above_272k_tokens":4e-6,"output_cost_per_token_above_272k_tokens":0.000018,"cache_creation_input_token_cost_priority":5e-6,"cache_creation_input_token_cost_above_12hr":5e-6,"input_cost_per_token_above_272k_tokens_flex":2e-6,"output_cost_per_token_above_272k_tokens_flex":9e-6,"cache_read_input_token_cost_above_272k_tokens":4e-7,"cache_creation_input_token_cost_above_12hr_flex":2.5e-6,"input_cost_per_token_above_272k_tokens_priority":8e-6,"output_cost_per_token_above_272k_tokens_priority":0.000036,"cache_creation_input_token_cost_above_272k_tokens":5e-6,"cache_read_input_token_cost_above_272k_tokens_flex":2e-7,"cache_creation_input_token_cost_above_12hr_priority":0.00001,"cache_creation_input_token_cost_above_272k_tokens_flex":2.5e-6,"cache_read_input_token_cost_above_272k_tokens_priority":8e-7,"cache_creation_input_token_cost_above_272k_tokens_priority":0.00001,"cache_creation_input_token_cost_above_12hr_above_272k_tokens":0.00001,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_flex":5e-6,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_priority":0.00002},"pricing_endpoint":"openai/gpt-5.6-terra","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"amazon/openai.gpt-5.6-terra","object":"model","created":1787461792,"owned_by":"amazon","model_name":"openai.gpt-5.6-terra","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.2e-6,"output_cost_per_token":0.0000132,"cache_read_input_token_cost":2.2e-7,"cache_creation_input_token_cost":2.75e-6,"input_cost_per_token_above_272k_tokens":4.4e-6,"output_cost_per_token_above_272k_tokens":0.0000198,"cache_read_input_token_cost_above_272k_tokens":4.4e-7,"cache_creation_input_token_cost_above_272k_tokens":5.5e-6},"list_pricing":{"input_cost_per_token":2.2e-6,"output_cost_per_token":0.0000132,"cache_read_input_token_cost":2.2e-7,"cache_creation_input_token_cost":2.75e-6,"input_cost_per_token_above_272k_tokens":4.4e-6,"output_cost_per_token_above_272k_tokens":0.0000198,"cache_read_input_token_cost_above_272k_tokens":4.4e-7,"cache_creation_input_token_cost_above_272k_tokens":5.5e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"amazon/openai.gpt-5.6-terra@us","object":"model","created":1787461792,"owned_by":"amazon","model_name":"openai.gpt-5.6-terra","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.2e-6,"output_cost_per_token":0.0000132,"cache_read_input_token_cost":2.2e-7,"cache_creation_input_token_cost":2.75e-6,"input_cost_per_token_above_272k_tokens":4.4e-6,"output_cost_per_token_above_272k_tokens":0.0000198,"cache_read_input_token_cost_above_272k_tokens":4.4e-7,"cache_creation_input_token_cost_above_272k_tokens":5.5e-6},"list_pricing":{"input_cost_per_token":2.2e-6,"output_cost_per_token":0.0000132,"cache_read_input_token_cost":2.2e-7,"cache_creation_input_token_cost":2.75e-6,"input_cost_per_token_above_272k_tokens":4.4e-6,"output_cost_per_token_above_272k_tokens":0.0000198,"cache_read_input_token_cost_above_272k_tokens":4.4e-7,"cache_creation_input_token_cost_above_272k_tokens":5.5e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null},{"id":"azure/gpt-5.6-terra@eu","object":"model","created":1784804086,"owned_by":"azure","model_name":"gpt-5.6-terra","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2.2e-6,"output_cost_per_token":0.0000132,"input_cost_per_token_flex":1.1e-6,"output_cost_per_token_flex":6.6e-6,"cache_read_input_token_cost":2.2e-7,"input_cost_per_token_priority":4.4e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.0000264,"cache_creation_input_token_cost":2.75e-6,"cache_read_input_token_cost_flex":1.1e-7,"cache_creation_input_token_cost_flex":1.3750000000000002e-6,"cache_read_input_token_cost_priority":4.4e-7,"input_cost_per_token_above_272k_tokens":4.4e-6,"output_cost_per_token_above_272k_tokens":0.000019800000000000004,"cache_creation_input_token_cost_priority":5.500000000000001e-6,"input_cost_per_token_above_272k_tokens_flex":2.2e-6,"output_cost_per_token_above_272k_tokens_flex":9.900000000000002e-6,"cache_read_input_token_cost_above_272k_tokens":4.4e-7,"input_cost_per_token_above_272k_tokens_priority":8.8e-6,"output_cost_per_token_above_272k_tokens_priority":0.00003960000000000001,"cache_creation_input_token_cost_above_272k_tokens":5.5e-6,"cache_read_input_token_cost_above_272k_tokens_flex":2.2e-7,"cache_creation_input_token_cost_above_272k_tokens_flex":2.7500000000000004e-6,"cache_read_input_token_cost_above_272k_tokens_priority":8.8e-7,"cache_creation_input_token_cost_above_272k_tokens_priority":0.000011000000000000001},"list_pricing":{"input_cost_per_token":2.2e-6,"output_cost_per_token":0.0000132,"input_cost_per_token_flex":1.1e-6,"output_cost_per_token_flex":6.6e-6,"cache_read_input_token_cost":2.2e-7,"input_cost_per_token_priority":4.4e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.0000264,"cache_creation_input_token_cost":2.75e-6,"cache_read_input_token_cost_flex":1.1e-7,"cache_creation_input_token_cost_flex":1.3750000000000002e-6,"cache_read_input_token_cost_priority":4.4e-7,"input_cost_per_token_above_272k_tokens":4.4e-6,"output_cost_per_token_above_272k_tokens":0.000019800000000000004,"cache_creation_input_token_cost_priority":5.500000000000001e-6,"input_cost_per_token_above_272k_tokens_flex":2.2e-6,"output_cost_per_token_above_272k_tokens_flex":9.900000000000002e-6,"cache_read_input_token_cost_above_272k_tokens":4.4e-7,"input_cost_per_token_above_272k_tokens_priority":8.8e-6,"output_cost_per_token_above_272k_tokens_priority":0.00003960000000000001,"cache_creation_input_token_cost_above_272k_tokens":5.5e-6,"cache_read_input_token_cost_above_272k_tokens_flex":2.2e-7,"cache_creation_input_token_cost_above_272k_tokens_flex":2.7500000000000004e-6,"cache_read_input_token_cost_above_272k_tokens_priority":8.8e-7,"cache_creation_input_token_cost_above_272k_tokens_priority":0.000011000000000000001},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"azure/gpt-5.6-terra","object":"model","created":1784804086,"owned_by":"azure","model_name":"gpt-5.6-terra","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.000012,"input_cost_per_token_flex":1e-6,"output_cost_per_token_flex":6e-6,"cache_read_input_token_cost":2e-7,"input_cost_per_token_priority":4e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.000024,"cache_creation_input_token_cost":2.4999999999999998e-6,"cache_read_input_token_cost_flex":1e-7,"cache_creation_input_token_cost_flex":1.25e-6,"cache_read_input_token_cost_priority":4e-7,"input_cost_per_token_above_272k_tokens":4e-6,"output_cost_per_token_above_272k_tokens":0.000018,"cache_creation_input_token_cost_priority":5e-6,"input_cost_per_token_above_272k_tokens_flex":2e-6,"output_cost_per_token_above_272k_tokens_flex":9e-6,"cache_read_input_token_cost_above_272k_tokens":4e-7,"input_cost_per_token_above_272k_tokens_priority":8e-6,"output_cost_per_token_above_272k_tokens_priority":0.000036,"cache_creation_input_token_cost_above_272k_tokens":4.9999999999999996e-6,"cache_read_input_token_cost_above_272k_tokens_flex":2e-7,"cache_creation_input_token_cost_above_272k_tokens_flex":2.5e-6,"cache_read_input_token_cost_above_272k_tokens_priority":8e-7,"cache_creation_input_token_cost_above_272k_tokens_priority":0.00001},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.000012,"input_cost_per_token_flex":1e-6,"output_cost_per_token_flex":6e-6,"cache_read_input_token_cost":2e-7,"input_cost_per_token_priority":4e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.000024,"cache_creation_input_token_cost":2.4999999999999998e-6,"cache_read_input_token_cost_flex":1e-7,"cache_creation_input_token_cost_flex":1.25e-6,"cache_read_input_token_cost_priority":4e-7,"input_cost_per_token_above_272k_tokens":4e-6,"output_cost_per_token_above_272k_tokens":0.000018,"cache_creation_input_token_cost_priority":5e-6,"input_cost_per_token_above_272k_tokens_flex":2e-6,"output_cost_per_token_above_272k_tokens_flex":9e-6,"cache_read_input_token_cost_above_272k_tokens":4e-7,"input_cost_per_token_above_272k_tokens_priority":8e-6,"output_cost_per_token_above_272k_tokens_priority":0.000036,"cache_creation_input_token_cost_above_272k_tokens":4.9999999999999996e-6,"cache_read_input_token_cost_above_272k_tokens_flex":2e-7,"cache_creation_input_token_cost_above_272k_tokens_flex":2.5e-6,"cache_read_input_token_cost_above_272k_tokens_priority":8e-7,"cache_creation_input_token_cost_above_272k_tokens_priority":0.00001},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"azure/gpt-5.6-terra@us","object":"model","created":1784804086,"owned_by":"azure","model_name":"gpt-5.6-terra","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2.2e-6,"output_cost_per_token":0.0000132,"input_cost_per_token_flex":1.1e-6,"output_cost_per_token_flex":6.6e-6,"cache_read_input_token_cost":2.2e-7,"input_cost_per_token_priority":4.4e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.0000264,"cache_creation_input_token_cost":2.75e-6,"cache_read_input_token_cost_flex":1.1e-7,"cache_creation_input_token_cost_flex":1.3750000000000002e-6,"cache_read_input_token_cost_priority":4.4e-7,"input_cost_per_token_above_272k_tokens":4.4e-6,"output_cost_per_token_above_272k_tokens":0.000019800000000000004,"cache_creation_input_token_cost_priority":5.500000000000001e-6,"input_cost_per_token_above_272k_tokens_flex":2.2e-6,"output_cost_per_token_above_272k_tokens_flex":9.900000000000002e-6,"cache_read_input_token_cost_above_272k_tokens":4.4e-7,"input_cost_per_token_above_272k_tokens_priority":8.8e-6,"output_cost_per_token_above_272k_tokens_priority":0.00003960000000000001,"cache_creation_input_token_cost_above_272k_tokens":5.5e-6,"cache_read_input_token_cost_above_272k_tokens_flex":2.2e-7,"cache_creation_input_token_cost_above_272k_tokens_flex":2.7500000000000004e-6,"cache_read_input_token_cost_above_272k_tokens_priority":8.8e-7,"cache_creation_input_token_cost_above_272k_tokens_priority":0.000011000000000000001},"list_pricing":{"input_cost_per_token":2.2e-6,"output_cost_per_token":0.0000132,"input_cost_per_token_flex":1.1e-6,"output_cost_per_token_flex":6.6e-6,"cache_read_input_token_cost":2.2e-7,"input_cost_per_token_priority":4.4e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.0000264,"cache_creation_input_token_cost":2.75e-6,"cache_read_input_token_cost_flex":1.1e-7,"cache_creation_input_token_cost_flex":1.3750000000000002e-6,"cache_read_input_token_cost_priority":4.4e-7,"input_cost_per_token_above_272k_tokens":4.4e-6,"output_cost_per_token_above_272k_tokens":0.000019800000000000004,"cache_creation_input_token_cost_priority":5.500000000000001e-6,"input_cost_per_token_above_272k_tokens_flex":2.2e-6,"output_cost_per_token_above_272k_tokens_flex":9.900000000000002e-6,"cache_read_input_token_cost_above_272k_tokens":4.4e-7,"input_cost_per_token_above_272k_tokens_priority":8.8e-6,"output_cost_per_token_above_272k_tokens_priority":0.00003960000000000001,"cache_creation_input_token_cost_above_272k_tokens":5.5e-6,"cache_read_input_token_cost_above_272k_tokens_flex":2.2e-7,"cache_creation_input_token_cost_above_272k_tokens_flex":2.7500000000000004e-6,"cache_read_input_token_cost_above_272k_tokens_priority":8.8e-7,"cache_creation_input_token_cost_above_272k_tokens_priority":0.000011000000000000001},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"databricks/databricks-gpt-5-6-terra@eu","object":"model","created":1783590857,"owned_by":"databricks","model_name":"databricks-gpt-5-6-terra","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5.6 Terra is the balanced model in OpenAI's GPT-5.6 family for everyday agentic and reasoning workloads, offering performance competitive with GPT-5.5 at a lower cost. This model supports multimodal (text and image) inputs and a long context window. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["file","image","text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.000012,"input_dbu_cost_per_token":0.000028571,"output_dbu_cost_per_token":0.000171429,"cache_read_input_token_cost":2e-7,"input_cost_per_token_priority":4e-6,"output_cost_per_token_priority":0.000024,"cache_creation_input_token_cost":2.5e-6,"input_cost_per_token_above_272k_tokens":4e-6,"output_cost_per_token_above_272k_tokens":0.000018,"cache_creation_input_token_cost_priority":5e-6,"cache_read_input_token_cost_above_272k_tokens":4e-7,"input_cost_per_token_above_272k_tokens_priority":8e-6,"output_cost_per_token_above_272k_tokens_priority":0.000036,"cache_creation_input_token_cost_above_272k_tokens":5e-6,"cache_read_input_token_cost_above_272k_tokens_priority":8e-7,"cache_creation_input_token_cost_above_272k_tokens_priority":0.00001},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.000012,"input_dbu_cost_per_token":0.000028571,"output_dbu_cost_per_token":0.000171429,"cache_read_input_token_cost":2e-7,"input_cost_per_token_priority":4e-6,"output_cost_per_token_priority":0.000024,"cache_creation_input_token_cost":2.5e-6,"input_cost_per_token_above_272k_tokens":4e-6,"output_cost_per_token_above_272k_tokens":0.000018,"cache_creation_input_token_cost_priority":5e-6,"cache_read_input_token_cost_above_272k_tokens":4e-7,"input_cost_per_token_above_272k_tokens_priority":8e-6,"output_cost_per_token_above_272k_tokens_priority":0.000036,"cache_creation_input_token_cost_above_272k_tokens":5e-6,"cache_read_input_token_cost_above_272k_tokens_priority":8e-7,"cache_creation_input_token_cost_above_272k_tokens_priority":0.00001},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"databricks/databricks-gpt-5-6-terra","object":"model","created":1783590857,"owned_by":"databricks","model_name":"databricks-gpt-5-6-terra","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5.6 Terra is the balanced model in OpenAI's GPT-5.6 family for everyday agentic and reasoning workloads, offering performance competitive with GPT-5.5 at a lower cost. This model supports multimodal (text and image) inputs and a long context window. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["file","image","text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.000012,"input_dbu_cost_per_token":0.000028571,"output_dbu_cost_per_token":0.000171429,"cache_read_input_token_cost":2e-7,"input_cost_per_token_priority":4e-6,"output_cost_per_token_priority":0.000024,"cache_creation_input_token_cost":2.5e-6,"input_cost_per_token_above_272k_tokens":4e-6,"output_cost_per_token_above_272k_tokens":0.000018,"cache_creation_input_token_cost_priority":5e-6,"cache_read_input_token_cost_above_272k_tokens":4e-7,"input_cost_per_token_above_272k_tokens_priority":8e-6,"output_cost_per_token_above_272k_tokens_priority":0.000036,"cache_creation_input_token_cost_above_272k_tokens":5e-6,"cache_read_input_token_cost_above_272k_tokens_priority":8e-7,"cache_creation_input_token_cost_above_272k_tokens_priority":0.00001},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.000012,"input_dbu_cost_per_token":0.000028571,"output_dbu_cost_per_token":0.000171429,"cache_read_input_token_cost":2e-7,"input_cost_per_token_priority":4e-6,"output_cost_per_token_priority":0.000024,"cache_creation_input_token_cost":2.5e-6,"input_cost_per_token_above_272k_tokens":4e-6,"output_cost_per_token_above_272k_tokens":0.000018,"cache_creation_input_token_cost_priority":5e-6,"cache_read_input_token_cost_above_272k_tokens":4e-7,"input_cost_per_token_above_272k_tokens_priority":8e-6,"output_cost_per_token_above_272k_tokens_priority":0.000036,"cache_creation_input_token_cost_above_272k_tokens":5e-6,"cache_read_input_token_cost_above_272k_tokens_priority":8e-7,"cache_creation_input_token_cost_above_272k_tokens_priority":0.00001},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"openai/gpt-5.6-terra","object":"model","created":1783590857,"owned_by":"openai","model_name":"gpt-5.6-terra","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier.","source":null,"capabilities":{"input_modalities":["file","image","text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.000012,"input_cost_per_token_flex":1e-6,"output_cost_per_token_flex":6e-6,"cache_read_input_token_cost":2e-7,"input_cost_per_token_batches":1e-6,"input_cost_per_token_priority":4e-6,"output_cost_per_token_batches":6e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"output_cost_per_token_priority":0.000024,"cache_creation_input_token_cost":2.5e-6,"cache_read_input_token_cost_flex":1e-7,"cache_read_input_token_cost_batches":1e-7,"cache_creation_input_token_cost_flex":1.25e-6,"cache_read_input_token_cost_priority":4e-7,"input_cost_per_token_above_272k_tokens":4e-6,"output_cost_per_token_above_272k_tokens":0.000018,"cache_creation_input_token_cost_priority":5e-6,"cache_creation_input_token_cost_above_12hr":5e-6,"input_cost_per_token_above_272k_tokens_flex":2e-6,"output_cost_per_token_above_272k_tokens_flex":9e-6,"cache_read_input_token_cost_above_272k_tokens":4e-7,"cache_creation_input_token_cost_above_12hr_flex":2.5e-6,"input_cost_per_token_above_272k_tokens_priority":8e-6,"output_cost_per_token_above_272k_tokens_priority":0.000036,"cache_creation_input_token_cost_above_272k_tokens":5e-6,"cache_read_input_token_cost_above_272k_tokens_flex":2e-7,"cache_creation_input_token_cost_above_12hr_priority":0.00001,"cache_creation_input_token_cost_above_272k_tokens_flex":2.5e-6,"cache_read_input_token_cost_above_272k_tokens_priority":8e-7,"cache_creation_input_token_cost_above_272k_tokens_priority":0.00001,"cache_creation_input_token_cost_above_12hr_above_272k_tokens":0.00001,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_flex":5e-6,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_priority":0.00002},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.000012,"input_cost_per_token_flex":1e-6,"output_cost_per_token_flex":6e-6,"cache_read_input_token_cost":2e-7,"input_cost_per_token_batches":1e-6,"input_cost_per_token_priority":4e-6,"output_cost_per_token_batches":6e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"output_cost_per_token_priority":0.000024,"cache_creation_input_token_cost":2.5e-6,"cache_read_input_token_cost_flex":1e-7,"cache_read_input_token_cost_batches":1e-7,"cache_creation_input_token_cost_flex":1.25e-6,"cache_read_input_token_cost_priority":4e-7,"input_cost_per_token_above_272k_tokens":4e-6,"output_cost_per_token_above_272k_tokens":0.000018,"cache_creation_input_token_cost_priority":5e-6,"cache_creation_input_token_cost_above_12hr":5e-6,"input_cost_per_token_above_272k_tokens_flex":2e-6,"output_cost_per_token_above_272k_tokens_flex":9e-6,"cache_read_input_token_cost_above_272k_tokens":4e-7,"cache_creation_input_token_cost_above_12hr_flex":2.5e-6,"input_cost_per_token_above_272k_tokens_priority":8e-6,"output_cost_per_token_above_272k_tokens_priority":0.000036,"cache_creation_input_token_cost_above_272k_tokens":5e-6,"cache_read_input_token_cost_above_272k_tokens_flex":2e-7,"cache_creation_input_token_cost_above_12hr_priority":0.00001,"cache_creation_input_token_cost_above_272k_tokens_flex":2.5e-6,"cache_read_input_token_cost_above_272k_tokens_priority":8e-7,"cache_creation_input_token_cost_above_272k_tokens_priority":0.00001,"cache_creation_input_token_cost_above_12hr_above_272k_tokens":0.00001,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_flex":5e-6,"cache_creation_input_token_cost_above_12hr_above_272k_tokens_priority":0.00002},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":8},{"id":"chat-latest","object":"model","created":1787288981,"owned_by":"openai","mode":"chat","context_length":400000,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":5e-6,"output_cost_per_token":0.00003,"cache_read_input_token_cost":5e-7},"pricing_endpoint":"openai/chat-latest","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"openai/chat-latest","object":"model","created":1787288981,"owned_by":"openai","model_name":"chat-latest","context_length":400000,"max_input_tokens":400000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":5e-6,"output_cost_per_token":0.00003,"cache_read_input_token_cost":5e-7},"list_pricing":{"input_cost_per_token":5e-6,"output_cost_per_token":0.00003,"cache_read_input_token_cost":5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":1},{"id":"kimi-k3-fast","object":"model","created":1787288981,"owned_by":"moonshot","mode":"chat","context_length":1048576,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4.5e-6,"output_cost_per_token":0.0000225,"cache_read_input_token_cost":4.5e-7},"pricing_endpoint":"fireworks_ai/accounts/fireworks/routers/kimi-k3-fast","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"fireworks_ai/accounts/fireworks/routers/kimi-k3-fast","object":"model","created":1787288981,"owned_by":"fireworks_ai","model_name":"accounts/fireworks/routers/kimi-k3-fast","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4.5e-6,"output_cost_per_token":0.0000225,"cache_read_input_token_cost":4.5e-7},"list_pricing":{"input_cost_per_token":4.5e-6,"output_cost_per_token":0.0000225,"cache_read_input_token_cost":4.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"nemotron-3-ultra-nvfp4","object":"model","created":1787288981,"owned_by":"nvidia","mode":"chat","context_length":262144,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6e-7,"output_cost_per_token":2.4e-6,"cache_read_input_token_cost":1.2e-7,"input_cost_per_token_priority":7.5e-7,"output_cost_per_token_priority":3e-6,"cache_read_input_token_cost_priority":1.5e-7},"pricing_endpoint":"fireworks_ai/accounts/fireworks/models/nemotron-3-ultra-nvfp4","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"fireworks_ai/accounts/fireworks/models/nemotron-3-ultra-nvfp4","object":"model","created":1787288981,"owned_by":"fireworks_ai","model_name":"accounts/fireworks/models/nemotron-3-ultra-nvfp4","context_length":262144,"max_input_tokens":262144,"max_output_tokens":32768,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6e-7,"output_cost_per_token":2.4e-6,"cache_read_input_token_cost":1.2e-7,"input_cost_per_token_priority":7.5e-7,"output_cost_per_token_priority":3e-6,"cache_read_input_token_cost_priority":1.5e-7},"list_pricing":{"input_cost_per_token":6e-7,"output_cost_per_token":2.4e-6,"cache_read_input_token_cost":1.2e-7,"input_cost_per_token_priority":7.5e-7,"output_cost_per_token_priority":3e-6,"cache_read_input_token_cost_priority":1.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"nemotron-lightning-3.5-30b-a3b","object":"model","created":1787288981,"owned_by":"nvidia","mode":"chat","context_length":262144,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-8,"output_cost_per_token":2e-7,"cache_read_input_token_cost":1e-8,"input_cost_per_token_priority":6.25e-8,"output_cost_per_token_priority":2.5e-7,"cache_read_input_token_cost_priority":1.25e-8},"pricing_endpoint":"fireworks_ai/accounts/fireworks/models/nemotron-lightning-3p5-30b-a3b","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"fireworks_ai/accounts/fireworks/models/nemotron-lightning-3p5-30b-a3b","object":"model","created":1787288981,"owned_by":"fireworks_ai","model_name":"accounts/fireworks/models/nemotron-lightning-3p5-30b-a3b","context_length":262144,"max_input_tokens":262144,"max_output_tokens":32768,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-8,"output_cost_per_token":2e-7,"cache_read_input_token_cost":1e-8,"input_cost_per_token_priority":6.25e-8,"output_cost_per_token_priority":2.5e-7,"cache_read_input_token_cost_priority":1.25e-8},"list_pricing":{"input_cost_per_token":5e-8,"output_cost_per_token":2e-7,"cache_read_input_token_cost":1e-8,"input_cost_per_token_priority":6.25e-8,"output_cost_per_token_priority":2.5e-7,"cache_read_input_token_cost_priority":1.25e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"deepseek-r1-0528","object":"model","created":1787003349,"owned_by":"deepseek","mode":"chat","context_length":164000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":2.1499999999999997e-6,"cache_read_input_token_cost":3.5e-7},"pricing_endpoint":"deepinfra/deepseek-ai/DeepSeek-R1-0528","regions":[{"code":"eu","name":"Europe"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"tensorx/deepseek/deepseek-r1-0528","object":"model","created":1787003349,"owned_by":"tensorx","model_name":"deepseek/deepseek-r1-0528","context_length":164000,"max_input_tokens":164000,"max_output_tokens":8192,"quantization":null,"retirement_date":null,"description":"Served by TensorX at fp8 quantization.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6.6e-7,"output_cost_per_token":2.6e-6,"cache_read_input_token_cost":1.65e-7},"list_pricing":{"input_cost_per_token":6.6e-7,"output_cost_per_token":2.6e-6,"cache_read_input_token_cost":1.65e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"deepinfra/deepseek-ai/DeepSeek-R1-0528","object":"model","created":1748455170,"owned_by":"deepinfra","model_name":"deepseek-ai/DeepSeek-R1-0528","context_length":163840,"max_input_tokens":163840,"max_output_tokens":32768,"quantization":"fp4","retirement_date":null,"description":"May 28th update to the original DeepSeek R1 Performance on par with OpenAI o1, but open-sourced and with fully open reasoning tokens.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":2.1499999999999997e-6,"cache_read_input_token_cost":3.5e-7},"list_pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":2.1499999999999997e-6,"cache_read_input_token_cost":3.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"glm-5-turbo","object":"model","created":1787003349,"owned_by":"zai","mode":"chat","context_length":202752,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.2e-6,"output_cost_per_token":4e-6,"cache_read_input_token_cost":2.4e-7},"pricing_endpoint":"zai/glm-5-turbo","regions":[{"code":"ap","name":"Asia"},{"code":"eu","name":"Europe"}],"alias_of":null,"endpoints":[{"id":"tensorx/z-ai/glm-5-turbo","object":"model","created":1787003349,"owned_by":"tensorx","model_name":"z-ai/glm-5-turbo","context_length":202752,"max_input_tokens":202752,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"Served by TensorX at fp8 quantization.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.2e-6,"output_cost_per_token":4e-6,"cache_read_input_token_cost":3e-7},"list_pricing":{"input_cost_per_token":1.2e-6,"output_cost_per_token":4e-6,"cache_read_input_token_cost":3e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"zai/glm-5-turbo","object":"model","created":1773583573,"owned_by":"zai","model_name":"glm-5-turbo","context_length":202752,"max_input_tokens":null,"max_output_tokens":131072,"quantization":null,"retirement_date":"2098-12-31","description":"GLM-5 Turbo is a new model from Z.ai designed for fast inference and strong performance in agent-driven environments such as OpenClaw scenarios.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.2e-6,"output_cost_per_token":4e-6,"cache_read_input_token_cost":2.4e-7},"list_pricing":{"input_cost_per_token":1.2e-6,"output_cost_per_token":4e-6,"cache_read_input_token_cost":2.4e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"ap","name":"Asia"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"glm-5.1","object":"model","created":1787003349,"owned_by":"zai","mode":"chat","context_length":202752,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":9.1e-7,"output_cost_per_token":2.86e-6,"cache_read_input_token_cost":1.6900000000000002e-7},"pricing_endpoint":"qwen/glm-5.1","regions":[{"code":"ap","name":"Asia"},{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"tensorx/z-ai/glm-5.1","object":"model","created":1787003349,"owned_by":"tensorx","model_name":"z-ai/glm-5.1","context_length":202752,"max_input_tokens":202752,"max_output_tokens":64000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.4e-6,"output_cost_per_token":4.4e-6,"cache_read_input_token_cost":3.5e-7},"list_pricing":{"input_cost_per_token":1.4e-6,"output_cost_per_token":4.4e-6,"cache_read_input_token_cost":3.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"deepinfra/zai-org/GLM-5.1","object":"model","created":1775578025,"owned_by":"deepinfra","model_name":"zai-org/GLM-5.1","context_length":202752,"max_input_tokens":null,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"GLM-5.1 delivers a major leap in coding capability, with particularly significant gains in handling long-horizon tasks. Unlike previous models built around minute-level interactions, GLM-5.1 can work independently and continuously on...","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.05e-6,"output_cost_per_token":3.5e-6,"cache_read_input_token_cost":2.05e-7},"list_pricing":{"input_cost_per_token":1.05e-6,"output_cost_per_token":3.5e-6,"cache_read_input_token_cost":2.05e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"qwen/glm-5.1","object":"model","created":1775578025,"owned_by":"qwen","model_name":"glm-5.1","context_length":202745,"max_input_tokens":202745,"max_output_tokens":131072,"quantization":"fp8","retirement_date":"2026-11-20","description":"GLM-5.1 is a model developed by Zhipu AI, specifically designed for long-horizon tasks. It has 744 billion parameters, supports an ultra-long context of 200k tokens, and can generate up to 128k tokens in a single response. GLM-5.1 excels in logical reasoning, long-text understanding, and code generation, while balancing performance with inference efficiency. It delivers outstanding results across multiple multi-task benchmarks and is well-suited for applications such as intelligent human-computer interaction, enterprise solutions, and developer assistance.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":9.1e-7,"output_cost_per_token":2.86e-6,"cache_read_input_token_cost":1.6900000000000002e-7},"list_pricing":{"input_cost_per_token":1.4e-6,"output_cost_per_token":4.4e-6,"cache_read_input_token_cost":2.6e-7},"discount":0.35,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null},{"id":"zai/glm-5.1","object":"model","created":1775578025,"owned_by":"zai","model_name":"glm-5.1","context_length":202752,"max_input_tokens":200000,"max_output_tokens":131072,"quantization":"fp8","retirement_date":"2026-11-20","description":"GLM-5.1 delivers a major leap in coding capability, with particularly significant gains in handling long-horizon tasks.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.4e-6,"output_cost_per_token":4.4e-6,"cache_read_input_token_cost":2.6e-7,"cache_creation_input_token_cost":0.0},"list_pricing":{"input_cost_per_token":1.4e-6,"output_cost_per_token":4.4e-6,"cache_read_input_token_cost":2.6e-7,"cache_creation_input_token_cost":0.0},"discount":null,"discount_ends_at":null,"regions":[{"code":"ap","name":"Asia"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":4},{"id":"glm-5v-turbo","object":"model","created":1787003349,"owned_by":"zai","mode":"chat","context_length":202752,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.2e-6,"output_cost_per_token":4e-6,"cache_read_input_token_cost":2.4e-7},"pricing_endpoint":"zai/glm-5v-turbo","regions":[{"code":"ap","name":"Asia"},{"code":"eu","name":"Europe"}],"alias_of":null,"endpoints":[{"id":"tensorx/z-ai/glm-5v-turbo","object":"model","created":1787003349,"owned_by":"tensorx","model_name":"z-ai/glm-5v-turbo","context_length":202752,"max_input_tokens":202752,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"Served by TensorX at fp8 quantization.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.2e-6,"output_cost_per_token":4e-6,"cache_read_input_token_cost":3e-7},"list_pricing":{"input_cost_per_token":1.2e-6,"output_cost_per_token":4e-6,"cache_read_input_token_cost":3e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"zai/glm-5v-turbo","object":"model","created":1775061458,"owned_by":"zai","model_name":"glm-5v-turbo","context_length":202752,"max_input_tokens":200000,"max_output_tokens":131072,"quantization":"fp8","retirement_date":"2098-12-31","description":"GLM-5V-Turbo is Z.ai’s first native multimodal agent foundation model, built for vision-based coding and agent-driven tasks.","source":null,"capabilities":{"input_modalities":["image","text","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.2e-6,"output_cost_per_token":4e-6,"cache_read_input_token_cost":2.4e-7},"list_pricing":{"input_cost_per_token":1.2e-6,"output_cost_per_token":4e-6,"cache_read_input_token_cost":2.4e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"ap","name":"Asia"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"kimi-k2.5","object":"model","created":1787003349,"owned_by":"moonshot","mode":"chat","context_length":262144,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4.5e-7,"output_cost_per_token":2.25e-6,"cache_read_input_token_cost":7e-8},"pricing_endpoint":"deepinfra/moonshotai/Kimi-K2.5","regions":[{"code":"eu","name":"Europe"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"tensorx/moonshotai/kimi-k2.5","object":"model","created":1787003349,"owned_by":"tensorx","model_name":"moonshotai/kimi-k2.5","context_length":262144,"max_input_tokens":262144,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"Served by TensorX at int4 quantization.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":2.8e-6,"cache_read_input_token_cost":1.25e-7},"list_pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":2.8e-6,"cache_read_input_token_cost":1.25e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/moonshotai.kimi-k2.5","object":"model","created":1769487076,"owned_by":"amazon","model_name":"moonshotai.kimi-k2.5","context_length":262144,"max_input_tokens":262144,"max_output_tokens":131072,"quantization":null,"retirement_date":"2026-11-18","description":"Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm.","source":"https://platform.moonshot.ai/docs/guide/kimi-k2-5-quickstart","capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6e-7,"output_cost_per_token":3e-6},"list_pricing":{"input_cost_per_token":6e-7,"output_cost_per_token":3e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/moonshotai.kimi-k2.5@us","object":"model","created":1769487076,"owned_by":"amazon","model_name":"moonshotai.kimi-k2.5","context_length":262144,"max_input_tokens":262144,"max_output_tokens":131072,"quantization":null,"retirement_date":"2026-11-18","description":"Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm.","source":"https://platform.moonshot.ai/docs/guide/kimi-k2-5-quickstart","capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6e-7,"output_cost_per_token":3e-6},"list_pricing":{"input_cost_per_token":6e-7,"output_cost_per_token":3e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"deepinfra/moonshotai/Kimi-K2.5","object":"model","created":1769487076,"owned_by":"deepinfra","model_name":"moonshotai/Kimi-K2.5","context_length":262144,"max_input_tokens":null,"max_output_tokens":64000,"quantization":null,"retirement_date":"2026-08-31","description":"Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm. Built on Kimi K2 with continued pretraining over approximately 15T mixed...","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4.5e-7,"output_cost_per_token":2.25e-6,"cache_read_input_token_cost":7e-8},"list_pricing":{"input_cost_per_token":4.5e-7,"output_cost_per_token":2.25e-6,"cache_read_input_token_cost":7e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":4},{"id":"qwen3.8-2.4t-a95b","object":"model","created":1787003349,"owned_by":"qwen","mode":"chat","context_length":1000000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.3e-6,"output_cost_per_token":3.9e-6,"cache_read_input_token_cost":1.625e-7,"cache_creation_input_token_cost":1.6250000000000001e-6},"pricing_endpoint":"qwen/qwen3.8-2.4t-a95b","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"tensorx/qwen/qwen3.8-2.4t-a95b","object":"model","created":1787003349,"owned_by":"tensorx","model_name":"qwen/qwen3.8-2.4t-a95b","context_length":262144,"max_input_tokens":262144,"max_output_tokens":64000,"quantization":"fp4","retirement_date":null,"description":"Served by TensorX at nvfp4 quantization.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.5e-6,"output_cost_per_token":6e-6,"cache_read_input_token_cost":6.25e-7},"list_pricing":{"input_cost_per_token":2.5e-6,"output_cost_per_token":6e-6,"cache_read_input_token_cost":6.25e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"deepinfra/Qwen/Qwen3.8-2.4T-A95B","object":"model","created":1786551702,"owned_by":"deepinfra","model_name":"Qwen/Qwen3.8-2.4T-A95B","context_length":262144,"max_input_tokens":null,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of [Qwen3.8 Max](/qwen/qwen3.8-max), with 95 billion active parameters out of 2.4 trillion total. It is...","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":6e-6,"cache_read_input_token_cost":2e-7},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":6e-6,"cache_read_input_token_cost":2e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"qwen/qwen3.8-2.4t-a95b","object":"model","created":1786551702,"owned_by":"qwen","model_name":"qwen3.8-2.4t-a95b","context_length":1000000,"max_input_tokens":991808,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"Qwen3.8-2.4T-A95B is the open-source release of Qwen's latest flagship, launched August 2026. Its sparse MoE architecture holds 2.4T total parameters with ~95B activated per step, paired with hybrid attention and a 1M token context window. Key benchmarks: GPQA Diamond 92.6, PaperBench 93.0, OSWorld 86.1, BabyVision 82.0. Ranked 4th on CodeArena.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.3e-6,"output_cost_per_token":3.9e-6,"cache_read_input_token_cost":1.625e-7,"cache_creation_input_token_cost":1.6250000000000001e-6},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":6e-6,"cache_read_input_token_cost":2.5e-7,"cache_creation_input_token_cost":2.5e-6},"discount":0.35,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":3},{"id":"nemotron-3.5-lightning","object":"model","created":1786694503,"owned_by":"nvidia","mode":"chat","context_length":1048576,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6e-8,"output_cost_per_token":1.6e-7,"cache_read_input_token_cost":9e-9},"pricing_endpoint":"flexai/NVIDIA-Nemotron-3.5-Lightning-30B-A3B","regions":[{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"flexai/NVIDIA-Nemotron-3.5-Lightning-30B-A3B","object":"model","created":1786694503,"owned_by":"flexai","model_name":"NVIDIA-Nemotron-3.5-Lightning-30B-A3B","context_length":1048576,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6e-8,"output_cost_per_token":1.6e-7,"cache_read_input_token_cost":9e-9},"list_pricing":{"input_cost_per_token":6e-8,"output_cost_per_token":1.6e-7,"cache_read_input_token_cost":9e-9},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"deepinfra/nvidia/NVIDIA-Nemotron-3.5-Lightning","object":"model","created":1786461139,"owned_by":"deepinfra","model_name":"nvidia/NVIDIA-Nemotron-3.5-Lightning","context_length":262144,"max_input_tokens":262144,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6.000000000000001e-8,"output_cost_per_token":1.6e-7,"cache_read_input_token_cost":3.0000000000000004e-8},"list_pricing":{"input_cost_per_token":6.000000000000001e-8,"output_cost_per_token":1.6e-7,"cache_read_input_token_cost":3.0000000000000004e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"nebius/nvidia/Nemotron-3_5-Lightning","object":"model","created":1786461139,"owned_by":"nebius","model_name":"nvidia/Nemotron-3_5-Lightning","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6e-8,"output_cost_per_token":2.4e-7,"cache_read_input_token_cost":6e-8},"list_pricing":{"input_cost_per_token":6e-8,"output_cost_per_token":2.4e-7,"cache_read_input_token_cost":6e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":3},{"id":"mistral-small-24b-instruct-2501","object":"model","created":1786647205,"owned_by":"mistral","mode":"chat","context_length":128000,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5.0000000000000004e-8,"output_cost_per_token":8e-8},"pricing_endpoint":"deepinfra/mistralai/Mistral-Small-24B-Instruct-2501","regions":[{"code":"eu","name":"Europe"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"ionos/mistralai/Mistral-Small-24B-Instruct","object":"model","created":1786647205,"owned_by":"ionos","model_name":"mistralai/Mistral-Small-24B-Instruct","context_length":128000,"max_input_tokens":null,"max_output_tokens":32768,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.1014004306475685e-7,"output_cost_per_token":3.304201291942705e-7},"list_pricing":{"input_cost_per_token":1.1014004306475685e-7,"output_cost_per_token":3.304201291942705e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"deepinfra/mistralai/Mistral-Small-24B-Instruct-2501","object":"model","created":1738255409,"owned_by":"deepinfra","model_name":"mistralai/Mistral-Small-24B-Instruct-2501","context_length":32768,"max_input_tokens":32768,"max_output_tokens":16384,"quantization":"fp8","retirement_date":null,"description":"Mistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5.0000000000000004e-8,"output_cost_per_token":8e-8},"list_pricing":{"input_cost_per_token":5.0000000000000004e-8,"output_cost_per_token":8e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"qwen3-coder-next","object":"model","created":1786647205,"owned_by":"qwen","mode":"chat","context_length":262144,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.6521006459713525e-7,"output_cost_per_token":8.811203445180548e-7},"pricing_endpoint":"ionos/Qwen/Qwen3-Coder-Next","regions":[{"code":"eu","name":"Europe"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"ionos/Qwen/Qwen3-Coder-Next","object":"model","created":1786647205,"owned_by":"ionos","model_name":"Qwen/Qwen3-Coder-Next","context_length":128000,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"Qwen3-Coder-Next is an open-weight causal language model optimized for coding agents and local development workflows.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.6521006459713525e-7,"output_cost_per_token":8.811203445180548e-7},"list_pricing":{"input_cost_per_token":1.6521006459713525e-7,"output_cost_per_token":8.811203445180548e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/qwen.qwen3-coder-next","object":"model","created":1770991619,"owned_by":"amazon","model_name":"qwen.qwen3-coder-next","context_length":262144,"max_input_tokens":262144,"max_output_tokens":16384,"quantization":null,"retirement_date":null,"description":"Qwen3-Coder-Next is an open-weight causal language model optimized for coding agents and local development workflows.","source":"https://aws.amazon.com/bedrock/pricing/","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":7.8e-7,"output_cost_per_token":1.86e-6,"input_cost_per_token_flex":3.9e-7,"output_cost_per_token_flex":9.3e-7,"input_cost_per_token_priority":1.365e-6,"output_cost_per_token_priority":3.255e-6},"list_pricing":{"input_cost_per_token":7.8e-7,"output_cost_per_token":1.86e-6,"input_cost_per_token_flex":3.9e-7,"output_cost_per_token_flex":9.3e-7,"input_cost_per_token_priority":1.365e-6,"output_cost_per_token_priority":3.255e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"ministral-3-14b-instruct-2512","object":"model","created":1786631709,"owned_by":"mistral","mode":"chat","context_length":100000,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.3042012919427056e-7,"output_cost_per_token":4.4056017225902734e-7},"pricing_endpoint":"infomaniak/mistralai/Ministral-3-14B-Instruct-2512","regions":[{"code":"ch","name":"Switzerland"}],"alias_of":null,"endpoints":[{"id":"infomaniak/mistralai/Ministral-3-14B-Instruct-2512","object":"model","created":1786631709,"owned_by":"infomaniak","model_name":"mistralai/Ministral-3-14B-Instruct-2512","context_length":100000,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.3042012919427056e-7,"output_cost_per_token":4.4056017225902734e-7},"list_pricing":{"input_cost_per_token":3.3042012919427056e-7,"output_cost_per_token":4.4056017225902734e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"ch","name":"Switzerland"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"gpt-4.1","object":"model","created":1786613111,"owned_by":"openai","mode":"chat","context_length":1047576,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":8e-6,"cache_read_input_token_cost":5e-7,"input_cost_per_token_batches":1e-6,"input_cost_per_token_priority":3.5e-6,"output_cost_per_token_batches":4e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"output_cost_per_token_priority":0.000014,"cache_read_input_token_cost_priority":8.75e-7},"pricing_endpoint":"openai/gpt-4.1","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"azure/gpt-4.1@eu","object":"model","created":1786613111,"owned_by":"azure","model_name":"gpt-4.1","context_length":1047576,"max_input_tokens":1047576,"max_output_tokens":32768,"quantization":null,"retirement_date":null,"description":"GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2.2e-6,"output_cost_per_token":8.8e-6,"cache_read_input_token_cost":5.5e-7,"input_cost_per_token_priority":3.85e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.0000154,"cache_read_input_token_cost_priority":9.625e-7},"list_pricing":{"input_cost_per_token":2.2e-6,"output_cost_per_token":8.8e-6,"cache_read_input_token_cost":5.5e-7,"input_cost_per_token_priority":3.85e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.0000154,"cache_read_input_token_cost_priority":9.625e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"azure/gpt-4.1","object":"model","created":1786613111,"owned_by":"azure","model_name":"gpt-4.1","context_length":1047576,"max_input_tokens":1047576,"max_output_tokens":32768,"quantization":null,"retirement_date":null,"description":"GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":8e-6,"cache_read_input_token_cost":5e-7,"input_cost_per_token_priority":3.5e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.000014,"cache_read_input_token_cost_priority":8.75e-7},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":8e-6,"cache_read_input_token_cost":5e-7,"input_cost_per_token_priority":3.5e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.000014,"cache_read_input_token_cost_priority":8.75e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"azure/gpt-4.1@us","object":"model","created":1786613111,"owned_by":"azure","model_name":"gpt-4.1","context_length":1047576,"max_input_tokens":1047576,"max_output_tokens":32768,"quantization":null,"retirement_date":null,"description":"GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2.2e-6,"output_cost_per_token":8.8e-6,"cache_read_input_token_cost":5.5e-7,"input_cost_per_token_priority":3.85e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.0000154,"cache_read_input_token_cost_priority":9.625e-7},"list_pricing":{"input_cost_per_token":2.2e-6,"output_cost_per_token":8.8e-6,"cache_read_input_token_cost":5.5e-7,"input_cost_per_token_priority":3.85e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.0000154,"cache_read_input_token_cost_priority":9.625e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"openai/gpt-4.1","object":"model","created":1744651385,"owned_by":"openai","model_name":"gpt-4.1","context_length":1047576,"max_input_tokens":1047576,"max_output_tokens":32768,"quantization":null,"retirement_date":null,"description":"GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning.","source":null,"capabilities":{"input_modalities":["image","text","file"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":8e-6,"cache_read_input_token_cost":5e-7,"input_cost_per_token_batches":1e-6,"input_cost_per_token_priority":3.5e-6,"output_cost_per_token_batches":4e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"output_cost_per_token_priority":0.000014,"cache_read_input_token_cost_priority":8.75e-7},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":8e-6,"cache_read_input_token_cost":5e-7,"input_cost_per_token_batches":1e-6,"input_cost_per_token_priority":3.5e-6,"output_cost_per_token_batches":4e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"output_cost_per_token_priority":0.000014,"cache_read_input_token_cost_priority":8.75e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":4},{"id":"gpt-4.1-mini","object":"model","created":1786613111,"owned_by":"openai","mode":"chat","context_length":1047576,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":4e-7,"output_cost_per_token":1.6e-6,"cache_read_input_token_cost":1e-7,"input_cost_per_token_batches":2e-7,"input_cost_per_token_priority":7e-7,"output_cost_per_token_batches":8e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"output_cost_per_token_priority":2.8e-6,"cache_read_input_token_cost_priority":1.75e-7},"pricing_endpoint":"openai/gpt-4.1-mini","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"azure/gpt-4.1-mini@eu","object":"model","created":1786613111,"owned_by":"azure","model_name":"gpt-4.1-mini","context_length":1047576,"max_input_tokens":1047576,"max_output_tokens":32768,"quantization":null,"retirement_date":null,"description":"GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":4.4e-7,"output_cost_per_token":1.76e-6,"cache_read_input_token_cost":1.1e-7,"input_cost_per_token_priority":7.7e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":3.08e-6,"cache_read_input_token_cost_priority":1.925e-7},"list_pricing":{"input_cost_per_token":4.4e-7,"output_cost_per_token":1.76e-6,"cache_read_input_token_cost":1.1e-7,"input_cost_per_token_priority":7.7e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":3.08e-6,"cache_read_input_token_cost_priority":1.925e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"azure/gpt-4.1-mini","object":"model","created":1786613111,"owned_by":"azure","model_name":"gpt-4.1-mini","context_length":1047576,"max_input_tokens":1047576,"max_output_tokens":32768,"quantization":null,"retirement_date":null,"description":"GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":4e-7,"output_cost_per_token":1.6e-6,"cache_read_input_token_cost":1e-7,"input_cost_per_token_priority":7e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":2.8e-6,"cache_read_input_token_cost_priority":1.75e-7},"list_pricing":{"input_cost_per_token":4e-7,"output_cost_per_token":1.6e-6,"cache_read_input_token_cost":1e-7,"input_cost_per_token_priority":7e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":2.8e-6,"cache_read_input_token_cost_priority":1.75e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"azure/gpt-4.1-mini@us","object":"model","created":1786613111,"owned_by":"azure","model_name":"gpt-4.1-mini","context_length":1047576,"max_input_tokens":1047576,"max_output_tokens":32768,"quantization":null,"retirement_date":null,"description":"GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":4.4e-7,"output_cost_per_token":1.76e-6,"cache_read_input_token_cost":1.1e-7,"input_cost_per_token_priority":7.7e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":3.08e-6,"cache_read_input_token_cost_priority":1.925e-7},"list_pricing":{"input_cost_per_token":4.4e-7,"output_cost_per_token":1.76e-6,"cache_read_input_token_cost":1.1e-7,"input_cost_per_token_priority":7.7e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":3.08e-6,"cache_read_input_token_cost_priority":1.925e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"openai/gpt-4.1-mini","object":"model","created":1744651381,"owned_by":"openai","model_name":"gpt-4.1-mini","context_length":1047576,"max_input_tokens":1047576,"max_output_tokens":32768,"quantization":null,"retirement_date":null,"description":"GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost.","source":null,"capabilities":{"input_modalities":["image","text","file"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":4e-7,"output_cost_per_token":1.6e-6,"cache_read_input_token_cost":1e-7,"input_cost_per_token_batches":2e-7,"input_cost_per_token_priority":7e-7,"output_cost_per_token_batches":8e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"output_cost_per_token_priority":2.8e-6,"cache_read_input_token_cost_priority":1.75e-7},"list_pricing":{"input_cost_per_token":4e-7,"output_cost_per_token":1.6e-6,"cache_read_input_token_cost":1e-7,"input_cost_per_token_batches":2e-7,"input_cost_per_token_priority":7e-7,"output_cost_per_token_batches":8e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"output_cost_per_token_priority":2.8e-6,"cache_read_input_token_cost_priority":1.75e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":4},{"id":"mistral-large-3","object":"model","created":1786613111,"owned_by":"mistral","mode":"chat","context_length":256000,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":1.5e-6},"pricing_endpoint":"azure/mistral-large-3","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"azure/mistral-large-3@eu","object":"model","created":1786613111,"owned_by":"azure","model_name":"mistral-large-3","context_length":256000,"max_input_tokens":256000,"max_output_tokens":8191,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5.5e-7,"output_cost_per_token":1.65e-6},"list_pricing":{"input_cost_per_token":5.5e-7,"output_cost_per_token":1.65e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"azure/mistral-large-3","object":"model","created":1786613111,"owned_by":"azure","model_name":"mistral-large-3","context_length":256000,"max_input_tokens":256000,"max_output_tokens":8191,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":1.5e-6},"list_pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":1.5e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"azure/mistral-large-3@us","object":"model","created":1786613111,"owned_by":"azure","model_name":"mistral-large-3","context_length":256000,"max_input_tokens":256000,"max_output_tokens":8191,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5.5e-7,"output_cost_per_token":1.65e-6},"list_pricing":{"input_cost_per_token":5.5e-7,"output_cost_per_token":1.65e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":3},{"id":"glm-4.5-air-fp8","object":"model","created":1786610410,"owned_by":"zai","mode":"chat","context_length":131072,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.4e-7,"output_cost_per_token":8.6e-7,"cache_read_input_token_cost":2.1e-8},"pricing_endpoint":"flexai/GLM-4.5-Air-FP8","regions":[{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"flexai/GLM-4.5-Air-FP8","object":"model","created":1786610410,"owned_by":"flexai","model_name":"GLM-4.5-Air-FP8","context_length":131072,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"GLM-4.5-Air is the lightweight variant of our latest flagship model family, also purpose-built for agent-centric applications.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.4e-7,"output_cost_per_token":8.6e-7,"cache_read_input_token_cost":2.1e-8},"list_pricing":{"input_cost_per_token":1.4e-7,"output_cost_per_token":8.6e-7,"cache_read_input_token_cost":2.1e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"llama-3.1-8b-instruct-fp8","object":"model","created":1786610410,"owned_by":"meta","mode":"chat","context_length":131072,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-8,"output_cost_per_token":8e-8,"cache_read_input_token_cost":7.5e-9},"pricing_endpoint":"flexai/Meta-Llama-3.1-8B-Instruct-FP8","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"flexai/Meta-Llama-3.1-8B-Instruct-FP8@eu","object":"model","created":1786610410,"owned_by":"flexai","model_name":"Meta-Llama-3.1-8B-Instruct-FP8","context_length":131072,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-8,"output_cost_per_token":8e-8,"cache_read_input_token_cost":7.5e-9},"list_pricing":{"input_cost_per_token":5e-8,"output_cost_per_token":8e-8,"cache_read_input_token_cost":7.5e-9},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"flexai/Meta-Llama-3.1-8B-Instruct-FP8","object":"model","created":1786610410,"owned_by":"flexai","model_name":"Meta-Llama-3.1-8B-Instruct-FP8","context_length":131072,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-8,"output_cost_per_token":8e-8,"cache_read_input_token_cost":7.5e-9},"list_pricing":{"input_cost_per_token":5e-8,"output_cost_per_token":8e-8,"cache_read_input_token_cost":7.5e-9},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"cloudflare/@cf/meta/llama-3.1-8b-instruct-fp8","object":"model","created":1721692800,"owned_by":"cloudflare","model_name":"@cf/meta/llama-3.1-8b-instruct-fp8","context_length":32000,"max_input_tokens":32000,"max_output_tokens":null,"quantization":"fp8","retirement_date":null,"description":"Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 8B instruct-tuned version is fast and efficient.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5199999999999998e-7,"output_cost_per_token":2.8699999999999996e-7},"list_pricing":{"input_cost_per_token":1.5199999999999998e-7,"output_cost_per_token":2.8699999999999996e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":3},{"id":"llama-3.3-70b-instruct-fp8","object":"model","created":1786610410,"owned_by":"meta","mode":"chat","context_length":131072,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.2e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":3.3e-8},"pricing_endpoint":"flexai/Llama-3.3-70B-Instruct-FP8","regions":[{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"flexai/Llama-3.3-70B-Instruct-FP8","object":"model","created":1786610410,"owned_by":"flexai","model_name":"Llama-3.3-70B-Instruct-FP8","context_length":131072,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out).","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.2e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":3.3e-8},"list_pricing":{"input_cost_per_token":2.2e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":3.3e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"mistral-nemo-instruct-2407-fp8","object":"model","created":1786610410,"owned_by":"mistral","mode":"chat","context_length":131072,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.3e-8,"output_cost_per_token":3e-8,"cache_read_input_token_cost":3.4e-9},"pricing_endpoint":"flexai/Mistral-Nemo-Instruct-2407-FP8","regions":[{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"flexai/Mistral-Nemo-Instruct-2407-FP8","object":"model","created":1786610410,"owned_by":"flexai","model_name":"Mistral-Nemo-Instruct-2407-FP8","context_length":131072,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.3e-8,"output_cost_per_token":3e-8,"cache_read_input_token_cost":3.4e-9},"list_pricing":{"input_cost_per_token":2.3e-8,"output_cost_per_token":3e-8,"cache_read_input_token_cost":3.4e-9},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"muse-glimmer-30b","object":"model","created":1786610410,"owned_by":"meta","mode":"chat","context_length":131072,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1.2e-6,"cache_read_input_token_cost":3.9999999000000004e-8},"pricing_endpoint":"deepinfra/meta-models/Muse-Glimmer-30B","regions":[{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"flexai/Muse-Glimmer-30B","object":"model","created":1786610410,"owned_by":"flexai","model_name":"Muse-Glimmer-30B","context_length":131072,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"Muse Glimmer 30B is a dense, open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark and optimized for autonomous agents on consumer hardware.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.5e-7,"output_cost_per_token":1.5e-6,"cache_read_input_token_cost":4e-8},"list_pricing":{"input_cost_per_token":3.5e-7,"output_cost_per_token":1.5e-6,"cache_read_input_token_cost":4e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"deepinfra/meta-models/Muse-Glimmer-30B","object":"model","created":1786302394,"owned_by":"deepinfra","model_name":"meta-models/Muse-Glimmer-30B","context_length":131072,"max_input_tokens":131072,"max_output_tokens":16384,"quantization":"bf16","retirement_date":null,"description":"Muse Glimmer 30B is a dense, open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark and optimized for autonomous agents on consumer hardware.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1.2e-6,"cache_read_input_token_cost":3.9999999000000004e-8},"list_pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1.2e-6,"cache_read_input_token_cost":3.9999999000000004e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"together_ai/meta-models/Muse-Glimmer-30B","object":"model","created":1786302394,"owned_by":"together_ai","model_name":"meta-models/Muse-Glimmer-30B","context_length":131072,"max_input_tokens":131072,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"Muse Glimmer 30B is a dense, open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark and optimized for autonomous agents on consumer hardware.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.5e-7,"output_cost_per_token":1.5e-6,"cache_read_input_token_cost":4e-8},"list_pricing":{"input_cost_per_token":3.5e-7,"output_cost_per_token":1.5e-6,"cache_read_input_token_cost":4e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":3},{"id":"seed-2-0-code-preview-260328","object":"model","created":1786550701,"owned_by":"bytedance","mode":"chat","context_length":262144,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":3e-6,"input_cost_per_token_above_128k_tokens":1e-6,"output_cost_per_token_above_128k_tokens":6e-6},"pricing_endpoint":"bytedance/seed-2-0-code-preview-260328","regions":[{"code":"ap","name":"Asia"}],"alias_of":null,"endpoints":[{"id":"bytedance/seed-2-0-code-preview-260328","object":"model","created":1786550701,"owned_by":"bytedance","model_name":"seed-2-0-code-preview-260328","context_length":262144,"max_input_tokens":262144,"max_output_tokens":131072,"quantization":"fp8","retirement_date":"2026-11-11","description":"Seed 2.0 Code is a model from ByteDance Seed optimized for agentic coding.","source":null,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":3e-6,"input_cost_per_token_above_128k_tokens":1e-6,"output_cost_per_token_above_128k_tokens":6e-6},"list_pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":3e-6,"input_cost_per_token_above_128k_tokens":1e-6,"output_cost_per_token_above_128k_tokens":6e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"ap","name":"Asia"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":1},{"id":"gemini-robotics-er-2-preview","object":"model","created":1785929637,"owned_by":"google","mode":"chat","context_length":131072,"capabilities":{"input_modalities":["text","image","file","audio","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":5e-6,"input_cost_per_audio_token":1e-6,"cache_read_input_token_cost":1e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_reasoning_token":5e-6},"pricing_endpoint":"google/gemini-robotics-er-2-preview","regions":[{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"google/gemini-robotics-er-2-preview","object":"model","created":1785929637,"owned_by":"google","model_name":"gemini-robotics-er-2-preview","context_length":131072,"max_input_tokens":131072,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image","file","audio","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":5e-6,"input_cost_per_audio_token":1e-6,"cache_read_input_token_cost":1e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_reasoning_token":5e-6},"list_pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":5e-6,"input_cost_per_audio_token":1e-6,"cache_read_input_token_cost":1e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_reasoning_token":5e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":1},{"id":"qwen3.8-max","object":"model","created":1785769541,"owned_by":"qwen","mode":"chat","context_length":1000000,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.3e-6,"output_cost_per_token":3.9e-6,"cache_read_input_token_cost":1.625e-7,"cache_creation_input_token_cost":1.6250000000000001e-6},"pricing_endpoint":"qwen/qwen3.8-max","regions":[{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"deepinfra/Qwen/Qwen3.8-Max","object":"model","created":1785769541,"owned_by":"deepinfra","model_name":"Qwen/Qwen3.8-Max","context_length":256000,"max_input_tokens":256000,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.65e-6,"output_cost_per_token":4.9510000000000005e-6,"cache_read_input_token_cost":2.0599999200000002e-7},"list_pricing":{"input_cost_per_token":1.65e-6,"output_cost_per_token":4.9510000000000005e-6,"cache_read_input_token_cost":2.0599999200000002e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"qwen/qwen3.8-max","object":"model","created":1785731612,"owned_by":"qwen","model_name":"qwen3.8-max","context_length":1000000,"max_input_tokens":991808,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"2.4-trillion-parameter MoE flagship delivering a comprehensive leap in coding and professional work. Autonomously codes and delivers complete projects spanning 10+ days. Handles hundreds of specialized tasks across legal, financial, design, and other professional domains, producing production-grade results end-to-end in a single conversation. Native visual understanding runs through the full cycle of planning, execution, and verification, enabling deep semantic analysis of ultra-long documents and extended video content. In long-horizon tasks, plans autonomously, iterates through closed feedback loops, and continuously evolves.","source":null,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.3e-6,"output_cost_per_token":3.9e-6,"cache_read_input_token_cost":1.625e-7,"cache_creation_input_token_cost":1.6250000000000001e-6},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":6e-6,"cache_read_input_token_cost":2.5e-7,"cache_creation_input_token_cost":2.5e-6},"discount":0.35,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":2},{"id":"inkling-small","object":"model","created":1785443117,"owned_by":"thinkingmachines","mode":"chat","context_length":524288,"capabilities":{"input_modalities":["text","image","audio"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4.5000000000000003e-7,"output_cost_per_token":1.2e-6,"cache_read_input_token_cost":9.9999999e-8},"pricing_endpoint":"deepinfra/thinkingmachines/Inkling-Small","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"deepinfra/thinkingmachines/Inkling-Small","object":"model","created":1785443117,"owned_by":"deepinfra","model_name":"thinkingmachines/Inkling-Small","context_length":524288,"max_input_tokens":524288,"max_output_tokens":262144,"quantization":"fp4","retirement_date":null,"description":"Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total.","source":null,"capabilities":{"input_modalities":["text","image","audio"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4.5000000000000003e-7,"output_cost_per_token":1.2e-6,"cache_read_input_token_cost":9.9999999e-8},"list_pricing":{"input_cost_per_token":4.5000000000000003e-7,"output_cost_per_token":1.2e-6,"cache_read_input_token_cost":9.9999999e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"claude-opus-5","object":"model","created":1785417770,"owned_by":"anthropic","mode":"chat","context_length":1000000,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-6,"output_cost_per_token":0.000025,"provider_specific_entry":{"us":1.1,"fast":2.0},"cache_read_input_token_cost":5e-7,"input_cost_per_token_batches":2.5e-6,"output_cost_per_token_batches":0.0000125,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.25e-6,"cache_read_input_token_cost_batches":2.5e-7,"cache_creation_input_token_cost_above_1hr":0.00001},"pricing_endpoint":"anthropic/claude-opus-5","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"databricks/databricks-claude-opus-5@eu","object":"model","created":1785417770,"owned_by":"databricks","model_name":"databricks-claude-opus-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Opus 5 is Anthropic's latest Opus-class model, delivering frontier intelligence for complex reasoning, coding, and agentic workflows at Opus-tier pricing. It features an adjustable effort control to trade off thoroughness against latency and cost, and supports large-context tasks such as deep document analysis and multi-step tool use. This model is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-6,"output_cost_per_token":0.000025,"input_dbu_cost_per_token":0.000071429,"output_dbu_cost_per_token":0.00035714,"cache_read_input_token_cost":5e-7,"cache_creation_input_token_cost":6.25e-6,"cache_creation_input_token_cost_above_1hr":0.00001},"list_pricing":{"input_cost_per_token":5e-6,"output_cost_per_token":0.000025,"input_dbu_cost_per_token":0.000071429,"output_dbu_cost_per_token":0.00035714,"cache_read_input_token_cost":5e-7,"cache_creation_input_token_cost":6.25e-6,"cache_creation_input_token_cost_above_1hr":0.00001},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"databricks/databricks-claude-opus-5","object":"model","created":1785417770,"owned_by":"databricks","model_name":"databricks-claude-opus-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Opus 5 is Anthropic's latest Opus-class model, delivering frontier intelligence for complex reasoning, coding, and agentic workflows at Opus-tier pricing. It features an adjustable effort control to trade off thoroughness against latency and cost, and supports large-context tasks such as deep document analysis and multi-step tool use. This model is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-6,"output_cost_per_token":0.000025,"input_dbu_cost_per_token":0.000071429,"output_dbu_cost_per_token":0.00035714,"cache_read_input_token_cost":5e-7,"cache_creation_input_token_cost":6.25e-6,"cache_creation_input_token_cost_above_1hr":0.00001},"list_pricing":{"input_cost_per_token":5e-6,"output_cost_per_token":0.000025,"input_dbu_cost_per_token":0.000071429,"output_dbu_cost_per_token":0.00035714,"cache_read_input_token_cost":5e-7,"cache_creation_input_token_cost":6.25e-6,"cache_creation_input_token_cost_above_1hr":0.00001},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"deepinfra/anthropic/claude-opus-5","object":"model","created":1785164744,"owned_by":"deepinfra","model_name":"anthropic/claude-opus-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-6,"output_cost_per_token":0.000025},"list_pricing":{"input_cost_per_token":5e-6,"output_cost_per_token":0.000025},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null},{"id":"amazon/anthropic.claude-opus-5@eu","object":"model","created":1784912544,"owned_by":"amazon","model_name":"anthropic.claude-opus-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5.500000000000001e-6,"output_cost_per_token":0.000027500000000000004,"cache_read_input_token_cost":5.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.875000000000001e-6,"cache_creation_input_token_cost_above_1hr":0.000011000000000000001},"list_pricing":{"input_cost_per_token":5.500000000000001e-6,"output_cost_per_token":0.000027500000000000004,"cache_read_input_token_cost":5.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.875000000000001e-6,"cache_creation_input_token_cost_above_1hr":0.000011000000000000001},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/anthropic.claude-opus-5","object":"model","created":1784912544,"owned_by":"amazon","model_name":"anthropic.claude-opus-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-6,"output_cost_per_token":0.000025,"cache_read_input_token_cost":5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.25e-6,"cache_creation_input_token_cost_above_1hr":0.00001},"list_pricing":{"input_cost_per_token":5e-6,"output_cost_per_token":0.000025,"cache_read_input_token_cost":5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.25e-6,"cache_creation_input_token_cost_above_1hr":0.00001},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/anthropic.claude-opus-5@us","object":"model","created":1784912544,"owned_by":"amazon","model_name":"anthropic.claude-opus-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5.500000000000001e-6,"output_cost_per_token":0.000027500000000000004,"cache_read_input_token_cost":5.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.875000000000001e-6,"cache_creation_input_token_cost_above_1hr":0.000011000000000000001},"list_pricing":{"input_cost_per_token":5.500000000000001e-6,"output_cost_per_token":0.000027500000000000004,"cache_read_input_token_cost":5.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.875000000000001e-6,"cache_creation_input_token_cost_above_1hr":0.000011000000000000001},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"anthropic/claude-opus-5","object":"model","created":1784912544,"owned_by":"anthropic","model_name":"claude-opus-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-6,"output_cost_per_token":0.000025,"provider_specific_entry":{"us":1.1,"fast":2.0},"cache_read_input_token_cost":5e-7,"input_cost_per_token_batches":2.5e-6,"output_cost_per_token_batches":0.0000125,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.25e-6,"cache_read_input_token_cost_batches":2.5e-7,"cache_creation_input_token_cost_above_1hr":0.00001},"list_pricing":{"input_cost_per_token":5e-6,"output_cost_per_token":0.000025,"provider_specific_entry":{"us":1.1,"fast":2.0},"cache_read_input_token_cost":5e-7,"input_cost_per_token_batches":2.5e-6,"output_cost_per_token_batches":0.0000125,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.25e-6,"cache_read_input_token_cost_batches":2.5e-7,"cache_creation_input_token_cost_above_1hr":0.00001},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null},{"id":"vertex/claude-opus-5@eu","object":"model","created":1784912544,"owned_by":"vertex","model_name":"claude-opus-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5.500000000000001e-6,"output_cost_per_token":0.000027500000000000004,"cache_read_input_token_cost":5.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.875000000000001e-6,"cache_creation_input_token_cost_above_1hr":0.000011000000000000001},"list_pricing":{"input_cost_per_token":5.500000000000001e-6,"output_cost_per_token":0.000027500000000000004,"cache_read_input_token_cost":5.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.875000000000001e-6,"cache_creation_input_token_cost_above_1hr":0.000011000000000000001},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"vertex/claude-opus-5","object":"model","created":1784912544,"owned_by":"vertex","model_name":"claude-opus-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-6,"output_cost_per_token":0.000025,"cache_read_input_token_cost":5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.25e-6,"cache_creation_input_token_cost_above_1hr":0.00001},"list_pricing":{"input_cost_per_token":5e-6,"output_cost_per_token":0.000025,"cache_read_input_token_cost":5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.25e-6,"cache_creation_input_token_cost_above_1hr":0.00001},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"vertex/claude-opus-5@us","object":"model","created":1784912544,"owned_by":"vertex","model_name":"claude-opus-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5.500000000000001e-6,"output_cost_per_token":0.000027500000000000004,"cache_read_input_token_cost":5.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.875000000000001e-6,"cache_creation_input_token_cost_above_1hr":0.000011000000000000001},"list_pricing":{"input_cost_per_token":5.500000000000001e-6,"output_cost_per_token":0.000027500000000000004,"cache_read_input_token_cost":5.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.875000000000001e-6,"cache_creation_input_token_cost_above_1hr":0.000011000000000000001},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":10},{"id":"claude-sonnet-5","object":"model","created":1785417770,"owned_by":"anthropic","mode":"chat","context_length":1000000,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"provider_specific_entry":{"us":1.1},"cache_read_input_token_cost":2e-7,"input_cost_per_token_batches":1e-6,"output_cost_per_token_batches":5e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":2.5e-6,"cache_read_input_token_cost_batches":1e-7,"cache_creation_input_token_cost_above_1hr":4e-6},"pricing_endpoint":"anthropic/claude-sonnet-5","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"databricks/databricks-claude-sonnet-5@eu","object":"model","created":1785417770,"owned_by":"databricks","model_name":"databricks-claude-sonnet-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Sonnet 5 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with memory, polished document creation, and confident computer use for web QA and workflow automation. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"input_dbu_cost_per_token":0.000028571,"output_dbu_cost_per_token":0.00014286,"cache_read_input_token_cost":2e-7,"cache_creation_input_token_cost":2.5e-6,"cache_creation_input_token_cost_above_1hr":4e-6},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"input_dbu_cost_per_token":0.000028571,"output_dbu_cost_per_token":0.00014286,"cache_read_input_token_cost":2e-7,"cache_creation_input_token_cost":2.5e-6,"cache_creation_input_token_cost_above_1hr":4e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"databricks/databricks-claude-sonnet-5","object":"model","created":1785417770,"owned_by":"databricks","model_name":"databricks-claude-sonnet-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Sonnet 5 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with memory, polished document creation, and confident computer use for web QA and workflow automation. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"input_dbu_cost_per_token":0.000028571,"output_dbu_cost_per_token":0.00014286,"cache_read_input_token_cost":2e-7,"cache_creation_input_token_cost":2.5e-6,"cache_creation_input_token_cost_above_1hr":4e-6},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"input_dbu_cost_per_token":0.000028571,"output_dbu_cost_per_token":0.00014286,"cache_read_input_token_cost":2e-7,"cache_creation_input_token_cost":2.5e-6,"cache_creation_input_token_cost_above_1hr":4e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"deepinfra/anthropic/claude-sonnet-5","object":"model","created":1783401184,"owned_by":"deepinfra","model_name":"anthropic/claude-sonnet-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.9999999999999997e-6,"output_cost_per_token":0.000015},"list_pricing":{"input_cost_per_token":2.9999999999999997e-6,"output_cost_per_token":0.000015},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null},{"id":"amazon/anthropic.claude-sonnet-5@eu","object":"model","created":1782843083,"owned_by":"amazon","model_name":"anthropic.claude-sonnet-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.2e-6,"output_cost_per_token":0.000011000000000000001,"cache_read_input_token_cost":2.2e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":2.7500000000000004e-6,"cache_creation_input_token_cost_above_1hr":4.4e-6},"list_pricing":{"input_cost_per_token":2.2e-6,"output_cost_per_token":0.000011000000000000001,"cache_read_input_token_cost":2.2e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":2.7500000000000004e-6,"cache_creation_input_token_cost_above_1hr":4.4e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/anthropic.claude-sonnet-5","object":"model","created":1782843083,"owned_by":"amazon","model_name":"anthropic.claude-sonnet-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"cache_read_input_token_cost":2e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":2.5e-6,"cache_creation_input_token_cost_above_1hr":4e-6},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"cache_read_input_token_cost":2e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":2.5e-6,"cache_creation_input_token_cost_above_1hr":4e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/anthropic.claude-sonnet-5@us","object":"model","created":1782843083,"owned_by":"amazon","model_name":"anthropic.claude-sonnet-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.2e-6,"output_cost_per_token":0.000011000000000000001,"cache_read_input_token_cost":2.2e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":2.7500000000000004e-6,"cache_creation_input_token_cost_above_1hr":4.4e-6},"list_pricing":{"input_cost_per_token":2.2e-6,"output_cost_per_token":0.000011000000000000001,"cache_read_input_token_cost":2.2e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":2.7500000000000004e-6,"cache_creation_input_token_cost_above_1hr":4.4e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"anthropic/claude-sonnet-5","object":"model","created":1782843083,"owned_by":"anthropic","model_name":"claude-sonnet-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"provider_specific_entry":{"us":1.1},"cache_read_input_token_cost":2e-7,"input_cost_per_token_batches":1e-6,"output_cost_per_token_batches":5e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":2.5e-6,"cache_read_input_token_cost_batches":1e-7,"cache_creation_input_token_cost_above_1hr":4e-6},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"provider_specific_entry":{"us":1.1},"cache_read_input_token_cost":2e-7,"input_cost_per_token_batches":1e-6,"output_cost_per_token_batches":5e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":2.5e-6,"cache_read_input_token_cost_batches":1e-7,"cache_creation_input_token_cost_above_1hr":4e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null},{"id":"vertex/claude-sonnet-5@eu","object":"model","created":1782843083,"owned_by":"vertex","model_name":"claude-sonnet-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.2e-6,"output_cost_per_token":0.000011000000000000001,"cache_read_input_token_cost":2.2e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":2.7500000000000004e-6,"cache_creation_input_token_cost_above_1hr":4.4e-6},"list_pricing":{"input_cost_per_token":2.2e-6,"output_cost_per_token":0.000011000000000000001,"cache_read_input_token_cost":2.2e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":2.7500000000000004e-6,"cache_creation_input_token_cost_above_1hr":4.4e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"vertex/claude-sonnet-5","object":"model","created":1782843083,"owned_by":"vertex","model_name":"claude-sonnet-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"cache_read_input_token_cost":2e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":2.5e-6,"cache_creation_input_token_cost_above_1hr":4e-6},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.00001,"cache_read_input_token_cost":2e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":2.5e-6,"cache_creation_input_token_cost_above_1hr":4e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"vertex/claude-sonnet-5@us","object":"model","created":1782843083,"owned_by":"vertex","model_name":"claude-sonnet-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.2e-6,"output_cost_per_token":0.000011000000000000001,"cache_read_input_token_cost":2.2e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":2.7500000000000004e-6,"cache_creation_input_token_cost_above_1hr":4.4e-6},"list_pricing":{"input_cost_per_token":2.2e-6,"output_cost_per_token":0.000011000000000000001,"cache_read_input_token_cost":2.2e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":2.7500000000000004e-6,"cache_creation_input_token_cost_above_1hr":4.4e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":10},{"id":"gemini-3.1-flash-lite","object":"model","created":1785417770,"owned_by":"google","mode":"chat","context_length":1048576,"capabilities":{"input_modalities":["text","image","video","audio","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2.5e-7,"output_cost_per_token":1.5e-6,"input_cost_per_token_flex":1.25e-7,"input_cost_per_audio_token":5e-7,"input_cost_per_image_token":2.5e-7,"output_cost_per_token_flex":7.5e-7,"cache_read_input_token_cost":2.5e-8,"input_cost_per_token_priority":4.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":2.7e-6,"cache_creation_input_token_cost":8.33333333333333e-8,"input_cost_per_audio_token_flex":2.5e-7,"output_cost_per_reasoning_token":1.5e-6,"cache_read_input_token_cost_flex":1.25e-8,"cache_read_input_audio_token_cost":5e-8,"input_cost_per_audio_token_priority":9e-7,"cache_read_input_token_cost_priority":4.5e-8,"google_maps_grounding_cost_per_query":0.014,"cache_read_input_audio_token_cost_flex":2.5e-8,"cache_read_input_audio_token_cost_priority":9e-8},"pricing_endpoint":"google/gemini-3.1-flash-lite","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"databricks/databricks-gemini-3-1-flash-lite@eu","object":"model","created":1785417770,"owned_by":"databricks","model_name":"databricks-gemini-3-1-flash-lite","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"Gemini 3.1 Flash Lite is Google's fastest and most cost-efficient model in the Gemini 3 series, designed for high-volume and latency-sensitive workloads at scale. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["text","image","video","audio","file"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2.5e-7,"output_cost_per_token":1.5e-6,"input_dbu_cost_per_token":4.464e-6,"output_dbu_cost_per_token":0.000026786,"input_cost_per_audio_token":6.25e-7,"input_cost_per_image_token":3.125e-7,"cache_read_input_token_cost":2.5e-8,"cache_creation_input_token_cost":3.125e-7,"cache_read_input_audio_token_cost":6.25e-8,"input_cost_per_audio_token_priority":1.125e-6,"cache_creation_input_token_cost_priority":5.625e-7,"cache_read_input_audio_token_cost_priority":1.125e-7},"list_pricing":{"input_cost_per_token":2.5e-7,"output_cost_per_token":1.5e-6,"input_dbu_cost_per_token":4.464e-6,"output_dbu_cost_per_token":0.000026786,"input_cost_per_audio_token":6.25e-7,"input_cost_per_image_token":3.125e-7,"cache_read_input_token_cost":2.5e-8,"cache_creation_input_token_cost":3.125e-7,"cache_read_input_audio_token_cost":6.25e-8,"input_cost_per_audio_token_priority":1.125e-6,"cache_creation_input_token_cost_priority":5.625e-7,"cache_read_input_audio_token_cost_priority":1.125e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"databricks/databricks-gemini-3-1-flash-lite","object":"model","created":1785417770,"owned_by":"databricks","model_name":"databricks-gemini-3-1-flash-lite","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"Gemini 3.1 Flash Lite is Google's fastest and most cost-efficient model in the Gemini 3 series, designed for high-volume and latency-sensitive workloads at scale. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["text","image","video","audio","file"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2.5e-7,"output_cost_per_token":1.5e-6,"input_dbu_cost_per_token":4.464e-6,"output_dbu_cost_per_token":0.000026786,"input_cost_per_audio_token":6.25e-7,"input_cost_per_image_token":3.125e-7,"cache_read_input_token_cost":2.5e-8,"cache_creation_input_token_cost":3.125e-7,"cache_read_input_audio_token_cost":6.25e-8,"input_cost_per_audio_token_priority":1.125e-6,"cache_creation_input_token_cost_priority":5.625e-7,"cache_read_input_audio_token_cost_priority":1.125e-7},"list_pricing":{"input_cost_per_token":2.5e-7,"output_cost_per_token":1.5e-6,"input_dbu_cost_per_token":4.464e-6,"output_dbu_cost_per_token":0.000026786,"input_cost_per_audio_token":6.25e-7,"input_cost_per_image_token":3.125e-7,"cache_read_input_token_cost":2.5e-8,"cache_creation_input_token_cost":3.125e-7,"cache_read_input_audio_token_cost":6.25e-8,"input_cost_per_audio_token_priority":1.125e-6,"cache_creation_input_token_cost_priority":5.625e-7,"cache_read_input_audio_token_cost_priority":1.125e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"deepinfra/google/gemini-3.1-flash-lite","object":"model","created":1782119040,"owned_by":"deepinfra","model_name":"google/gemini-3.1-flash-lite","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"Gemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads.","source":null,"capabilities":{"input_modalities":["text","image","audio"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.5e-7,"output_cost_per_token":1.4999999999999998e-6},"list_pricing":{"input_cost_per_token":2.5e-7,"output_cost_per_token":1.4999999999999998e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null},{"id":"google/gemini-3.1-flash-lite","object":"model","created":1778168828,"owned_by":"google","model_name":"gemini-3.1-flash-lite","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"Gemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads.","source":"https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-lite","capabilities":{"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2.5e-7,"output_cost_per_token":1.5e-6,"input_cost_per_token_flex":1.25e-7,"input_cost_per_audio_token":5e-7,"input_cost_per_image_token":2.5e-7,"output_cost_per_token_flex":7.5e-7,"cache_read_input_token_cost":2.5e-8,"input_cost_per_token_priority":4.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":2.7e-6,"cache_creation_input_token_cost":8.33333333333333e-8,"input_cost_per_audio_token_flex":2.5e-7,"output_cost_per_reasoning_token":1.5e-6,"cache_read_input_token_cost_flex":1.25e-8,"cache_read_input_audio_token_cost":5e-8,"input_cost_per_audio_token_priority":9e-7,"cache_read_input_token_cost_priority":4.5e-8,"google_maps_grounding_cost_per_query":0.014,"cache_read_input_audio_token_cost_flex":2.5e-8,"cache_read_input_audio_token_cost_priority":9e-8},"list_pricing":{"input_cost_per_token":2.5e-7,"output_cost_per_token":1.5e-6,"input_cost_per_token_flex":1.25e-7,"input_cost_per_audio_token":5e-7,"input_cost_per_image_token":2.5e-7,"output_cost_per_token_flex":7.5e-7,"cache_read_input_token_cost":2.5e-8,"input_cost_per_token_priority":4.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":2.7e-6,"cache_creation_input_token_cost":8.33333333333333e-8,"input_cost_per_audio_token_flex":2.5e-7,"output_cost_per_reasoning_token":1.5e-6,"cache_read_input_token_cost_flex":1.25e-8,"cache_read_input_audio_token_cost":5e-8,"input_cost_per_audio_token_priority":9e-7,"cache_read_input_token_cost_priority":4.5e-8,"google_maps_grounding_cost_per_query":0.014,"cache_read_input_audio_token_cost_flex":2.5e-8,"cache_read_input_audio_token_cost_priority":9e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"vertex/gemini-3.1-flash-lite@eu","object":"model","created":1778168828,"owned_by":"vertex","model_name":"gemini-3.1-flash-lite","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"Gemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads.","source":null,"capabilities":{"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2.75e-7,"output_cost_per_token":1.65e-6,"input_cost_per_token_flex":1.375e-7,"input_cost_per_audio_token":5.5e-7,"input_cost_per_image_token":2.75e-7,"output_cost_per_token_flex":8.25e-7,"cache_read_input_token_cost":2.75e-8,"input_cost_per_token_priority":4.95e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":2.9700000000000004e-6,"cache_creation_input_token_cost":9.166666666666664e-8,"input_cost_per_audio_token_flex":2.75e-7,"output_cost_per_reasoning_token":1.65e-6,"cache_read_input_token_cost_flex":1.375e-8,"cache_read_input_audio_token_cost":5.5e-8,"input_cost_per_audio_token_priority":9.9e-7,"cache_read_input_token_cost_priority":4.9500000000000006e-8,"google_maps_grounding_cost_per_query":0.015400000000000002,"cache_read_input_audio_token_cost_flex":2.75e-8,"cache_read_input_audio_token_cost_priority":9.900000000000001e-8,"input_cost_per_audio_token_above_200k_tokens":5.5e-7,"input_cost_per_audio_token_above_200k_tokens_flex":2.75e-7,"input_cost_per_audio_token_above_200k_tokens_priority":9.9e-7},"list_pricing":{"input_cost_per_token":2.75e-7,"output_cost_per_token":1.65e-6,"input_cost_per_token_flex":1.375e-7,"input_cost_per_audio_token":5.5e-7,"input_cost_per_image_token":2.75e-7,"output_cost_per_token_flex":8.25e-7,"cache_read_input_token_cost":2.75e-8,"input_cost_per_token_priority":4.95e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":2.9700000000000004e-6,"cache_creation_input_token_cost":9.166666666666664e-8,"input_cost_per_audio_token_flex":2.75e-7,"output_cost_per_reasoning_token":1.65e-6,"cache_read_input_token_cost_flex":1.375e-8,"cache_read_input_audio_token_cost":5.5e-8,"input_cost_per_audio_token_priority":9.9e-7,"cache_read_input_token_cost_priority":4.9500000000000006e-8,"google_maps_grounding_cost_per_query":0.015400000000000002,"cache_read_input_audio_token_cost_flex":2.75e-8,"cache_read_input_audio_token_cost_priority":9.900000000000001e-8,"input_cost_per_audio_token_above_200k_tokens":5.5e-7,"input_cost_per_audio_token_above_200k_tokens_flex":2.75e-7,"input_cost_per_audio_token_above_200k_tokens_priority":9.9e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"vertex/gemini-3.1-flash-lite","object":"model","created":1778168828,"owned_by":"vertex","model_name":"gemini-3.1-flash-lite","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"Gemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads.","source":null,"capabilities":{"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2.5e-7,"output_cost_per_token":1.5e-6,"input_cost_per_token_flex":1.25e-7,"input_cost_per_audio_token":5e-7,"input_cost_per_image_token":2.5e-7,"output_cost_per_token_flex":7.5e-7,"cache_read_input_token_cost":2.5e-8,"input_cost_per_token_priority":4.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":2.7e-6,"cache_creation_input_token_cost":8.33333333333333e-8,"input_cost_per_audio_token_flex":2.5e-7,"output_cost_per_reasoning_token":1.5e-6,"cache_read_input_token_cost_flex":1.25e-8,"cache_read_input_audio_token_cost":5e-8,"input_cost_per_audio_token_priority":9e-7,"cache_read_input_token_cost_priority":4.5e-8,"google_maps_grounding_cost_per_query":0.014,"cache_read_input_audio_token_cost_flex":2.5e-8,"cache_read_input_audio_token_cost_priority":9e-8,"input_cost_per_audio_token_above_200k_tokens":5e-7,"input_cost_per_audio_token_above_200k_tokens_flex":2.5e-7,"input_cost_per_audio_token_above_200k_tokens_priority":9e-7},"list_pricing":{"input_cost_per_token":2.5e-7,"output_cost_per_token":1.5e-6,"input_cost_per_token_flex":1.25e-7,"input_cost_per_audio_token":5e-7,"input_cost_per_image_token":2.5e-7,"output_cost_per_token_flex":7.5e-7,"cache_read_input_token_cost":2.5e-8,"input_cost_per_token_priority":4.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":2.7e-6,"cache_creation_input_token_cost":8.33333333333333e-8,"input_cost_per_audio_token_flex":2.5e-7,"output_cost_per_reasoning_token":1.5e-6,"cache_read_input_token_cost_flex":1.25e-8,"cache_read_input_audio_token_cost":5e-8,"input_cost_per_audio_token_priority":9e-7,"cache_read_input_token_cost_priority":4.5e-8,"google_maps_grounding_cost_per_query":0.014,"cache_read_input_audio_token_cost_flex":2.5e-8,"cache_read_input_audio_token_cost_priority":9e-8,"input_cost_per_audio_token_above_200k_tokens":5e-7,"input_cost_per_audio_token_above_200k_tokens_flex":2.5e-7,"input_cost_per_audio_token_above_200k_tokens_priority":9e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"vertex/gemini-3.1-flash-lite@us","object":"model","created":1778168828,"owned_by":"vertex","model_name":"gemini-3.1-flash-lite","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"Gemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads.","source":null,"capabilities":{"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2.75e-7,"output_cost_per_token":1.65e-6,"input_cost_per_token_flex":1.375e-7,"input_cost_per_audio_token":5.5e-7,"input_cost_per_image_token":2.75e-7,"output_cost_per_token_flex":8.25e-7,"cache_read_input_token_cost":2.75e-8,"input_cost_per_token_priority":4.95e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":2.9700000000000004e-6,"cache_creation_input_token_cost":9.166666666666664e-8,"input_cost_per_audio_token_flex":2.75e-7,"output_cost_per_reasoning_token":1.65e-6,"cache_read_input_token_cost_flex":1.375e-8,"cache_read_input_audio_token_cost":5.5e-8,"input_cost_per_audio_token_priority":9.9e-7,"cache_read_input_token_cost_priority":4.9500000000000006e-8,"google_maps_grounding_cost_per_query":0.015400000000000002,"cache_read_input_audio_token_cost_flex":2.75e-8,"cache_read_input_audio_token_cost_priority":9.900000000000001e-8,"input_cost_per_audio_token_above_200k_tokens":5.5e-7,"input_cost_per_audio_token_above_200k_tokens_flex":2.75e-7,"input_cost_per_audio_token_above_200k_tokens_priority":9.9e-7},"list_pricing":{"input_cost_per_token":2.75e-7,"output_cost_per_token":1.65e-6,"input_cost_per_token_flex":1.375e-7,"input_cost_per_audio_token":5.5e-7,"input_cost_per_image_token":2.75e-7,"output_cost_per_token_flex":8.25e-7,"cache_read_input_token_cost":2.75e-8,"input_cost_per_token_priority":4.95e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":2.9700000000000004e-6,"cache_creation_input_token_cost":9.166666666666664e-8,"input_cost_per_audio_token_flex":2.75e-7,"output_cost_per_reasoning_token":1.65e-6,"cache_read_input_token_cost_flex":1.375e-8,"cache_read_input_audio_token_cost":5.5e-8,"input_cost_per_audio_token_priority":9.9e-7,"cache_read_input_token_cost_priority":4.9500000000000006e-8,"google_maps_grounding_cost_per_query":0.015400000000000002,"cache_read_input_audio_token_cost_flex":2.75e-8,"cache_read_input_audio_token_cost_priority":9.900000000000001e-8,"input_cost_per_audio_token_above_200k_tokens":5.5e-7,"input_cost_per_audio_token_above_200k_tokens_flex":2.75e-7,"input_cost_per_audio_token_above_200k_tokens_priority":9.9e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":7},{"id":"gemini-3.5-flash","object":"model","created":1785417770,"owned_by":"google","mode":"chat","context_length":1048576,"capabilities":{"input_modalities":["text","image","video","audio","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.5e-6,"output_cost_per_token":9e-6,"input_cost_per_token_flex":7.5e-7,"input_cost_per_audio_token":3e-6,"input_cost_per_image_token":1.5e-6,"output_cost_per_token_flex":4.5e-6,"cache_read_input_token_cost":1.5e-7,"input_cost_per_token_priority":2.7e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.0000162,"cache_creation_input_token_cost":8.33333333333333e-8,"output_cost_per_reasoning_token":9e-6,"cache_read_input_token_cost_flex":8e-8,"cache_read_input_audio_token_cost":3e-7,"cache_read_input_token_cost_priority":2.7e-7,"google_maps_grounding_cost_per_query":0.014},"pricing_endpoint":"google/gemini-3.5-flash","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"databricks/databricks-gemini-3-5-flash@eu","object":"model","created":1785417770,"owned_by":"databricks","model_name":"databricks-gemini-3-5-flash","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"Gemini 3.5 Flash is Google's next generation fast and efficient model. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["text","image","video","audio","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.5e-6,"output_cost_per_token":9e-6,"input_dbu_cost_per_token":0.000026786,"output_dbu_cost_per_token":0.000160714,"cache_read_input_token_cost":1.5e-7,"cache_creation_input_token_cost":1.875e-6,"cache_creation_input_token_cost_priority":3.375e-6},"list_pricing":{"input_cost_per_token":1.5e-6,"output_cost_per_token":9e-6,"input_dbu_cost_per_token":0.000026786,"output_dbu_cost_per_token":0.000160714,"cache_read_input_token_cost":1.5e-7,"cache_creation_input_token_cost":1.875e-6,"cache_creation_input_token_cost_priority":3.375e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"databricks/databricks-gemini-3-5-flash","object":"model","created":1785417770,"owned_by":"databricks","model_name":"databricks-gemini-3-5-flash","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"Gemini 3.5 Flash is Google's next generation fast and efficient model. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["text","image","video","audio","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.5e-6,"output_cost_per_token":9e-6,"input_dbu_cost_per_token":0.000026786,"output_dbu_cost_per_token":0.000160714,"cache_read_input_token_cost":1.5e-7,"cache_creation_input_token_cost":1.875e-6,"cache_creation_input_token_cost_priority":3.375e-6},"list_pricing":{"input_cost_per_token":1.5e-6,"output_cost_per_token":9e-6,"input_dbu_cost_per_token":0.000026786,"output_dbu_cost_per_token":0.000160714,"cache_read_input_token_cost":1.5e-7,"cache_creation_input_token_cost":1.875e-6,"cache_creation_input_token_cost_priority":3.375e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"deepinfra/google/gemini-3.5-flash","object":"model","created":1782119040,"owned_by":"deepinfra","model_name":"google/gemini-3.5-flash","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed.","source":null,"capabilities":{"input_modalities":["text","image","audio"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.4999999999999998e-6,"output_cost_per_token":9e-6},"list_pricing":{"input_cost_per_token":1.4999999999999998e-6,"output_cost_per_token":9e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null},{"id":"google/gemini-3.5-flash","object":"model","created":1779193800,"owned_by":"google","model_name":"gemini-3.5-flash","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed.","source":"https://cloud.google.com/vertex-ai/generative-ai/pricing","capabilities":{"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.5e-6,"output_cost_per_token":9e-6,"input_cost_per_token_flex":7.5e-7,"input_cost_per_audio_token":3e-6,"input_cost_per_image_token":1.5e-6,"output_cost_per_token_flex":4.5e-6,"cache_read_input_token_cost":1.5e-7,"input_cost_per_token_priority":2.7e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.0000162,"cache_creation_input_token_cost":8.33333333333333e-8,"output_cost_per_reasoning_token":9e-6,"cache_read_input_token_cost_flex":8e-8,"cache_read_input_audio_token_cost":3e-7,"cache_read_input_token_cost_priority":2.7e-7,"google_maps_grounding_cost_per_query":0.014},"list_pricing":{"input_cost_per_token":1.5e-6,"output_cost_per_token":9e-6,"input_cost_per_token_flex":7.5e-7,"input_cost_per_audio_token":3e-6,"input_cost_per_image_token":1.5e-6,"output_cost_per_token_flex":4.5e-6,"cache_read_input_token_cost":1.5e-7,"input_cost_per_token_priority":2.7e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.0000162,"cache_creation_input_token_cost":8.33333333333333e-8,"output_cost_per_reasoning_token":9e-6,"cache_read_input_token_cost_flex":8e-8,"cache_read_input_audio_token_cost":3e-7,"cache_read_input_token_cost_priority":2.7e-7,"google_maps_grounding_cost_per_query":0.014},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"vertex/gemini-3.5-flash@eu","object":"model","created":1779193800,"owned_by":"vertex","model_name":"gemini-3.5-flash","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed.","source":null,"capabilities":{"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.65e-6,"output_cost_per_token":9.900000000000002e-6,"input_cost_per_token_flex":8.25e-7,"input_cost_per_audio_token":3.3e-6,"input_cost_per_image_token":1.65e-6,"output_cost_per_token_flex":4.950000000000001e-6,"cache_read_input_token_cost":1.65e-7,"input_cost_per_token_priority":2.9700000000000004e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.000017820000000000002,"cache_creation_input_token_cost":9.166666666666664e-8,"output_cost_per_reasoning_token":9.900000000000002e-6,"cache_read_input_token_cost_flex":8.25e-8,"cache_read_input_audio_token_cost":3.3e-7,"cache_read_input_token_cost_priority":2.97e-7,"google_maps_grounding_cost_per_query":0.015400000000000002},"list_pricing":{"input_cost_per_token":1.65e-6,"output_cost_per_token":9.900000000000002e-6,"input_cost_per_token_flex":8.25e-7,"input_cost_per_audio_token":3.3e-6,"input_cost_per_image_token":1.65e-6,"output_cost_per_token_flex":4.950000000000001e-6,"cache_read_input_token_cost":1.65e-7,"input_cost_per_token_priority":2.9700000000000004e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.000017820000000000002,"cache_creation_input_token_cost":9.166666666666664e-8,"output_cost_per_reasoning_token":9.900000000000002e-6,"cache_read_input_token_cost_flex":8.25e-8,"cache_read_input_audio_token_cost":3.3e-7,"cache_read_input_token_cost_priority":2.97e-7,"google_maps_grounding_cost_per_query":0.015400000000000002},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"vertex/gemini-3.5-flash","object":"model","created":1779193800,"owned_by":"vertex","model_name":"gemini-3.5-flash","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed.","source":null,"capabilities":{"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.5e-6,"output_cost_per_token":9e-6,"input_cost_per_token_flex":7.5e-7,"input_cost_per_audio_token":3e-6,"input_cost_per_image_token":1.5e-6,"output_cost_per_token_flex":4.5e-6,"cache_read_input_token_cost":1.5e-7,"input_cost_per_token_priority":2.7e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.0000162,"cache_creation_input_token_cost":8.33333333333333e-8,"output_cost_per_reasoning_token":9e-6,"cache_read_input_token_cost_flex":7.5e-8,"cache_read_input_audio_token_cost":3e-7,"cache_read_input_token_cost_priority":2.7e-7,"google_maps_grounding_cost_per_query":0.014},"list_pricing":{"input_cost_per_token":1.5e-6,"output_cost_per_token":9e-6,"input_cost_per_token_flex":7.5e-7,"input_cost_per_audio_token":3e-6,"input_cost_per_image_token":1.5e-6,"output_cost_per_token_flex":4.5e-6,"cache_read_input_token_cost":1.5e-7,"input_cost_per_token_priority":2.7e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.0000162,"cache_creation_input_token_cost":8.33333333333333e-8,"output_cost_per_reasoning_token":9e-6,"cache_read_input_token_cost_flex":7.5e-8,"cache_read_input_audio_token_cost":3e-7,"cache_read_input_token_cost_priority":2.7e-7,"google_maps_grounding_cost_per_query":0.014},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"vertex/gemini-3.5-flash@us","object":"model","created":1779193800,"owned_by":"vertex","model_name":"gemini-3.5-flash","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed.","source":null,"capabilities":{"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.65e-6,"output_cost_per_token":9.900000000000002e-6,"input_cost_per_token_flex":8.25e-7,"input_cost_per_audio_token":3.3e-6,"input_cost_per_image_token":1.65e-6,"output_cost_per_token_flex":4.950000000000001e-6,"cache_read_input_token_cost":1.65e-7,"input_cost_per_token_priority":2.9700000000000004e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.000017820000000000002,"cache_creation_input_token_cost":9.166666666666664e-8,"output_cost_per_reasoning_token":9.900000000000002e-6,"cache_read_input_token_cost_flex":8.25e-8,"cache_read_input_audio_token_cost":3.3e-7,"cache_read_input_token_cost_priority":2.97e-7,"google_maps_grounding_cost_per_query":0.015400000000000002},"list_pricing":{"input_cost_per_token":1.65e-6,"output_cost_per_token":9.900000000000002e-6,"input_cost_per_token_flex":8.25e-7,"input_cost_per_audio_token":3.3e-6,"input_cost_per_image_token":1.65e-6,"output_cost_per_token_flex":4.950000000000001e-6,"cache_read_input_token_cost":1.65e-7,"input_cost_per_token_priority":2.9700000000000004e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.000017820000000000002,"cache_creation_input_token_cost":9.166666666666664e-8,"output_cost_per_reasoning_token":9.900000000000002e-6,"cache_read_input_token_cost_flex":8.25e-8,"cache_read_input_audio_token_cost":3.3e-7,"cache_read_input_token_cost_priority":2.97e-7,"google_maps_grounding_cost_per_query":0.015400000000000002},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":7},{"id":"gpt-5.2","object":"model","created":1785417770,"owned_by":"openai","mode":"chat","context_length":400000,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.75e-6,"output_cost_per_token":0.000014,"input_dbu_cost_per_token":0.000025,"output_dbu_cost_per_token":0.0002,"cache_read_input_token_cost":1.75e-7,"input_cost_per_token_priority":3.5e-6,"output_cost_per_token_priority":0.000028,"cache_creation_input_token_cost":1.75e-6,"cache_read_input_token_cost_priority":3.5e-7,"cache_creation_input_token_cost_priority":3.5e-6},"pricing_endpoint":"databricks/databricks-gpt-5-2","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"databricks/databricks-gpt-5-2@eu","object":"model","created":1785417770,"owned_by":"databricks","model_name":"databricks-gpt-5-2","context_length":400000,"max_input_tokens":272000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5.2 is a general purpose large language model with reasoning capabilities developed by OpenAI. This model builds directly upon GPT-5.1, offering higher accuracy, improved token efficiency on medium-to-complex tasks, and more deliberate scaffolded reasoning. This model excels at structured extraction, multi-step workflows, and multimodal tasks. It supports multimodal inputs and features a 400K total token context window with 128K maximum output tokens. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.75e-6,"output_cost_per_token":0.000014,"input_dbu_cost_per_token":0.000025,"output_dbu_cost_per_token":0.0002,"cache_read_input_token_cost":1.75e-7,"input_cost_per_token_priority":3.5e-6,"output_cost_per_token_priority":0.000028,"cache_creation_input_token_cost":1.75e-6,"cache_read_input_token_cost_priority":3.5e-7,"cache_creation_input_token_cost_priority":3.5e-6},"list_pricing":{"input_cost_per_token":1.75e-6,"output_cost_per_token":0.000014,"input_dbu_cost_per_token":0.000025,"output_dbu_cost_per_token":0.0002,"cache_read_input_token_cost":1.75e-7,"input_cost_per_token_priority":3.5e-6,"output_cost_per_token_priority":0.000028,"cache_creation_input_token_cost":1.75e-6,"cache_read_input_token_cost_priority":3.5e-7,"cache_creation_input_token_cost_priority":3.5e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"databricks/databricks-gpt-5-2","object":"model","created":1785417770,"owned_by":"databricks","model_name":"databricks-gpt-5-2","context_length":400000,"max_input_tokens":272000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5.2 is a general purpose large language model with reasoning capabilities developed by OpenAI. This model builds directly upon GPT-5.1, offering higher accuracy, improved token efficiency on medium-to-complex tasks, and more deliberate scaffolded reasoning. This model excels at structured extraction, multi-step workflows, and multimodal tasks. It supports multimodal inputs and features a 400K total token context window with 128K maximum output tokens. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.75e-6,"output_cost_per_token":0.000014,"input_dbu_cost_per_token":0.000025,"output_dbu_cost_per_token":0.0002,"cache_read_input_token_cost":1.75e-7,"input_cost_per_token_priority":3.5e-6,"output_cost_per_token_priority":0.000028,"cache_creation_input_token_cost":1.75e-6,"cache_read_input_token_cost_priority":3.5e-7,"cache_creation_input_token_cost_priority":3.5e-6},"list_pricing":{"input_cost_per_token":1.75e-6,"output_cost_per_token":0.000014,"input_dbu_cost_per_token":0.000025,"output_dbu_cost_per_token":0.0002,"cache_read_input_token_cost":1.75e-7,"input_cost_per_token_priority":3.5e-6,"output_cost_per_token_priority":0.000028,"cache_creation_input_token_cost":1.75e-6,"cache_read_input_token_cost_priority":3.5e-7,"cache_creation_input_token_cost_priority":3.5e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"azure/gpt-5.2","object":"model","created":1784832896,"owned_by":"azure","model_name":"gpt-5.2","context_length":400000,"max_input_tokens":272000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5.2 is the latest frontier-grade model in the GPT-5 series, offering stronger agentic and long context perfomance compared to GPT-5.1.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.75e-6,"output_cost_per_token":0.000014,"cache_read_input_token_cost":1.75e-7,"input_cost_per_token_priority":3.5e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.000028,"cache_read_input_token_cost_priority":3.5e-7},"list_pricing":{"input_cost_per_token":1.75e-6,"output_cost_per_token":0.000014,"cache_read_input_token_cost":1.75e-7,"input_cost_per_token_priority":3.5e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.000028,"cache_read_input_token_cost_priority":3.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"azure/gpt-5.2@us","object":"model","created":1784832896,"owned_by":"azure","model_name":"gpt-5.2","context_length":400000,"max_input_tokens":272000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5.2 is the latest frontier-grade model in the GPT-5 series, offering stronger agentic and long context perfomance compared to GPT-5.1.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.925e-6,"output_cost_per_token":0.0000154,"cache_read_input_token_cost":1.925e-7,"input_cost_per_token_priority":3.85e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.0000308,"cache_read_input_token_cost_priority":3.85e-7},"list_pricing":{"input_cost_per_token":1.925e-6,"output_cost_per_token":0.0000154,"cache_read_input_token_cost":1.925e-7,"input_cost_per_token_priority":3.85e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.0000308,"cache_read_input_token_cost_priority":3.85e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"openai/gpt-5.2","object":"model","created":1765389775,"owned_by":"openai","model_name":"gpt-5.2","context_length":400000,"max_input_tokens":272000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5.2 is the latest frontier-grade model in the GPT-5 series, offering stronger agentic and long context perfomance compared to GPT-5.1.","source":null,"capabilities":{"input_modalities":["file","image","text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.75e-6,"output_cost_per_token":0.000014,"input_cost_per_token_flex":8.75e-7,"output_cost_per_token_flex":7e-6,"cache_read_input_token_cost":1.75e-7,"input_cost_per_token_batches":8.75e-7,"input_cost_per_token_priority":3.5e-6,"output_cost_per_token_batches":7e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"output_cost_per_token_priority":0.000028,"cache_read_input_token_cost_flex":8.75e-8,"cache_read_input_token_cost_batches":8.75e-8,"cache_read_input_token_cost_priority":3.5e-7},"list_pricing":{"input_cost_per_token":1.75e-6,"output_cost_per_token":0.000014,"input_cost_per_token_flex":8.75e-7,"output_cost_per_token_flex":7e-6,"cache_read_input_token_cost":1.75e-7,"input_cost_per_token_batches":8.75e-7,"input_cost_per_token_priority":3.5e-6,"output_cost_per_token_batches":7e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"output_cost_per_token_priority":0.000028,"cache_read_input_token_cost_flex":8.75e-8,"cache_read_input_token_cost_batches":8.75e-8,"cache_read_input_token_cost_priority":3.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":5},{"id":"gpt-5.5-pro","object":"model","created":1785417770,"owned_by":"openai","mode":"chat","context_length":1050000,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":0.00003,"output_cost_per_token":0.00018,"input_dbu_cost_per_token":0.00042857,"output_dbu_cost_per_token":0.0025714,"cache_read_input_token_cost":3e-6,"cache_creation_input_token_cost":0.00003,"input_cost_per_token_above_272k_tokens":0.00006,"output_cost_per_token_above_272k_tokens":0.00027},"pricing_endpoint":"databricks/databricks-gpt-5-5-pro","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"databricks/databricks-gpt-5-5-pro@eu","object":"model","created":1785417770,"owned_by":"databricks","model_name":"databricks-gpt-5-5-pro","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5.5 Pro is OpenAI's strongest frontier model for agentic work in enterprise, complex document reasoning, and long-horizon coding agents. GPT-5.5 Pro also now powers Codex, OpenAI's coding agent. Pro uses more compute to think harder and provide consistently better answers. This model supports multimodal inputs and features a 400K total token context window with 128K maximum output tokens. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":0.00003,"output_cost_per_token":0.00018,"input_dbu_cost_per_token":0.00042857,"output_dbu_cost_per_token":0.0025714,"cache_read_input_token_cost":3e-6,"cache_creation_input_token_cost":0.00003,"input_cost_per_token_above_272k_tokens":0.00006,"output_cost_per_token_above_272k_tokens":0.00027},"list_pricing":{"input_cost_per_token":0.00003,"output_cost_per_token":0.00018,"input_dbu_cost_per_token":0.00042857,"output_dbu_cost_per_token":0.0025714,"cache_read_input_token_cost":3e-6,"cache_creation_input_token_cost":0.00003,"input_cost_per_token_above_272k_tokens":0.00006,"output_cost_per_token_above_272k_tokens":0.00027},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"databricks/databricks-gpt-5-5-pro","object":"model","created":1785417770,"owned_by":"databricks","model_name":"databricks-gpt-5-5-pro","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5.5 Pro is OpenAI's strongest frontier model for agentic work in enterprise, complex document reasoning, and long-horizon coding agents. GPT-5.5 Pro also now powers Codex, OpenAI's coding agent. Pro uses more compute to think harder and provide consistently better answers. This model supports multimodal inputs and features a 400K total token context window with 128K maximum output tokens. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":0.00003,"output_cost_per_token":0.00018,"input_dbu_cost_per_token":0.00042857,"output_dbu_cost_per_token":0.0025714,"cache_read_input_token_cost":3e-6,"cache_creation_input_token_cost":0.00003,"input_cost_per_token_above_272k_tokens":0.00006,"output_cost_per_token_above_272k_tokens":0.00027},"list_pricing":{"input_cost_per_token":0.00003,"output_cost_per_token":0.00018,"input_dbu_cost_per_token":0.00042857,"output_dbu_cost_per_token":0.0025714,"cache_read_input_token_cost":3e-6,"cache_creation_input_token_cost":0.00003,"input_cost_per_token_above_272k_tokens":0.00006,"output_cost_per_token_above_272k_tokens":0.00027},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"openai/gpt-5.5-pro","object":"model","created":1777051896,"owned_by":"openai","model_name":"gpt-5.5-pro","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5.5 Pro is OpenAI’s high-capability model optimized for deep reasoning and accuracy on complex, high-stakes workloads.","source":null,"capabilities":{"input_modalities":["file","image","text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":0.00003,"output_cost_per_token":0.00018,"input_cost_per_token_flex":0.000015,"output_cost_per_token_flex":0.00009,"input_cost_per_token_batches":0.000015,"output_cost_per_token_batches":0.00009,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"input_cost_per_token_above_272k_tokens":0.00006,"output_cost_per_token_above_272k_tokens":0.00027},"list_pricing":{"input_cost_per_token":0.00003,"output_cost_per_token":0.00018,"input_cost_per_token_flex":0.000015,"output_cost_per_token_flex":0.00009,"input_cost_per_token_batches":0.000015,"output_cost_per_token_batches":0.00009,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"input_cost_per_token_above_272k_tokens":0.00006,"output_cost_per_token_above_272k_tokens":0.00027},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":3},{"id":"qwen3-next-80b-a3b-instruct","object":"model","created":1785417770,"owned_by":"qwen","mode":"chat","context_length":262144,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":9e-8,"output_cost_per_token":1.1e-6},"pricing_endpoint":"deepinfra/Qwen/Qwen3-Next-80B-A3B-Instruct","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"databricks/databricks-qwen3-next-80b-a3b-instruct@eu","object":"model","created":1785417770,"owned_by":"databricks","model_name":"databricks-qwen3-next-80b-a3b-instruct","context_length":null,"max_input_tokens":null,"max_output_tokens":262144,"quantization":null,"retirement_date":null,"description":"Qwen3-Next-80B-A3B-Instruct is a highly efficient large language model optimized for instruction-following tasks built and trained by Alibaba Cloud. This model is designed to handle ultra-long contexts and excels at multi-step workflows, retrieval-augmented generation, and enterprise applications that require deterministic outputs at high throughput. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":1.2e-6,"input_dbu_cost_per_token":2.143e-6,"output_dbu_cost_per_token":0.000017143,"cache_read_input_token_cost":1.5e-8,"cache_creation_input_token_cost":1.5e-7},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":1.2e-6,"input_dbu_cost_per_token":2.143e-6,"output_dbu_cost_per_token":0.000017143,"cache_read_input_token_cost":1.5e-8,"cache_creation_input_token_cost":1.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"databricks/databricks-qwen3-next-80b-a3b-instruct","object":"model","created":1785417770,"owned_by":"databricks","model_name":"databricks-qwen3-next-80b-a3b-instruct","context_length":null,"max_input_tokens":null,"max_output_tokens":262144,"quantization":null,"retirement_date":null,"description":"Qwen3-Next-80B-A3B-Instruct is a highly efficient large language model optimized for instruction-following tasks built and trained by Alibaba Cloud. This model is designed to handle ultra-long contexts and excels at multi-step workflows, retrieval-augmented generation, and enterprise applications that require deterministic outputs at high throughput. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":1.2e-6,"input_dbu_cost_per_token":2.143e-6,"output_dbu_cost_per_token":0.000017143,"cache_read_input_token_cost":1.5e-8,"cache_creation_input_token_cost":1.5e-7},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":1.2e-6,"input_dbu_cost_per_token":2.143e-6,"output_dbu_cost_per_token":0.000017143,"cache_read_input_token_cost":1.5e-8,"cache_creation_input_token_cost":1.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"deepinfra/Qwen/Qwen3-Next-80B-A3B-Instruct","object":"model","created":1757612213,"owned_by":"deepinfra","model_name":"Qwen/Qwen3-Next-80B-A3B-Instruct","context_length":262144,"max_input_tokens":262144,"max_output_tokens":16384,"quantization":"fp8","retirement_date":"2026-10-08","description":"Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable responses without “thinking” traces.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":9e-8,"output_cost_per_token":1.1e-6},"list_pricing":{"input_cost_per_token":9e-8,"output_cost_per_token":1.1e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":3},{"id":"qwen-flash-2025-07-28","object":"model","created":1785415829,"owned_by":"qwen","mode":"chat","context_length":1000000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"tiered_pricing":[{"range":[0,256000],"input_cost_per_token":3.2500000000000006e-8,"output_cost_per_token":2.6000000000000005e-7},{"range":[256000,1000000],"input_cost_per_token":1.625e-7,"output_cost_per_token":1.3e-6}],"input_cost_per_token":3.2500000000000006e-8,"output_cost_per_token":2.6000000000000005e-7},"pricing_endpoint":"qwen/qwen-flash-2025-07-28","regions":[{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"qwen/qwen-flash-2025-07-28","object":"model","created":1785415829,"owned_by":"qwen","model_name":"qwen-flash-2025-07-28","context_length":1000000,"max_input_tokens":995904,"max_output_tokens":32768,"quantization":null,"retirement_date":null,"description":"Qwen3 series Flash model, integrates thinking and non-thinking modes and can switch modes during dialogue. Excels at complex thinking tasks; instruction following and text understanding significantly improved. Supports 1 M context length, and uses tiered pricing. This is a snapshot from 28 July, 2025.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"tiered_pricing":[{"range":[0,256000],"input_cost_per_token":3.2500000000000006e-8,"output_cost_per_token":2.6000000000000005e-7},{"range":[256000,1000000],"input_cost_per_token":1.625e-7,"output_cost_per_token":1.3e-6}],"input_cost_per_token":3.2500000000000006e-8,"output_cost_per_token":2.6000000000000005e-7},"list_pricing":{"tiered_pricing":[{"range":[0,256000],"input_cost_per_token":5.0000000000000004e-8,"output_cost_per_token":4.0000000000000003e-7},{"range":[256000,1000000],"input_cost_per_token":2.5e-7,"output_cost_per_token":2e-6}],"input_cost_per_token":5.0000000000000004e-8,"output_cost_per_token":4.0000000000000003e-7},"discount":0.35,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":1},{"id":"qwen-plus-character-ja","object":"model","created":1785415829,"owned_by":"qwen","mode":"chat","context_length":8192,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.25e-7,"output_cost_per_token":9.1e-7,"cache_read_input_token_cost":6.500000000000001e-8},"pricing_endpoint":"qwen/qwen-plus-character-ja","regions":[{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"qwen/qwen-plus-character-ja","object":"model","created":1785415829,"owned_by":"qwen","model_name":"qwen-plus-character-ja","context_length":8192,"max_input_tokens":7680,"max_output_tokens":512,"quantization":null,"retirement_date":null,"description":"The Qwen Role-Playing Model Series is specifically optimized for Japanese anthropomorphic interaction scenarios. It demonstrates advanced capabilities in character consistency maintenance, context-aware dialogue progression, and empathetic engagement, enabling precise personalized character embodiment. This version significantly enhances Japanese linguistic localization (including dialects and honorifics), human-like role-playing authenticity, narrative coherence control, and scenario-based cognitive intelligence.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.25e-7,"output_cost_per_token":9.1e-7,"cache_read_input_token_cost":6.500000000000001e-8},"list_pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":1.4e-6,"cache_read_input_token_cost":1.0000000000000001e-7},"discount":0.35,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":1},{"id":"qwen-vl-ocr","object":"model","created":1785415829,"owned_by":"qwen","mode":"chat","context_length":38192,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4.5500000000000004e-8,"output_cost_per_token":1.04e-7},"pricing_endpoint":"qwen/qwen-vl-ocr","regions":[{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"qwen/qwen-vl-ocr","object":"model","created":1785415829,"owned_by":"qwen","model_name":"qwen-vl-ocr","context_length":38192,"max_input_tokens":30000,"max_output_tokens":8192,"quantization":null,"retirement_date":null,"description":"Qwen-VL_OCR is an OCR model trained based on Qwen-VL. It aggregates various image-text recognition, parsing, and processing tasks through a unified model approach, offering powerful image-text recognition capabilities.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4.5500000000000004e-8,"output_cost_per_token":1.04e-7},"list_pricing":{"input_cost_per_token":7e-8,"output_cost_per_token":1.6e-7},"discount":0.35,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":1},{"id":"glm-5.2-fast-preview","object":"model","created":1785412138,"owned_by":"zai","mode":"chat","context_length":1000000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.82e-6,"output_cost_per_token":5.72e-6,"cache_read_input_token_cost":3.6400000000000003e-7},"pricing_endpoint":"qwen/glm-5.2-fast-preview","regions":[{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"qwen/glm-5.2-fast-preview","object":"model","created":1785412138,"owned_by":"qwen","model_name":"glm-5.2-fast-preview","context_length":1000000,"max_input_tokens":1048576,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"GLM-5.2-Fast-Preview is the high-speed variant of Zhipu AI&#39;s GLM-5.2, with 1M context and capabilities on par with the standard version. Inference-optimized to deliver 1.5–2× the output TPS, it fits latency-sensitive use cases such as real-time chat, multi-turn agents, and streaming code generation.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.82e-6,"output_cost_per_token":5.72e-6,"cache_read_input_token_cost":3.6400000000000003e-7},"list_pricing":{"input_cost_per_token":2.8e-6,"output_cost_per_token":8.8e-6,"cache_read_input_token_cost":5.6e-7},"discount":0.35,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":1},{"id":"qwen-flash","object":"model","created":1785412138,"owned_by":"qwen","mode":"chat","context_length":1000000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"tiered_pricing":[{"range":[0,256000],"input_cost_per_token":3.2500000000000006e-8,"output_cost_per_token":2.6000000000000005e-7,"cache_read_input_token_cost":6.5e-9,"cache_creation_input_token_cost":4.095e-8},{"range":[256000,1000000],"input_cost_per_token":1.625e-7,"output_cost_per_token":1.3e-6,"cache_read_input_token_cost":3.2500000000000006e-8,"cache_creation_input_token_cost":2.0345e-7}],"input_cost_per_token":3.2500000000000006e-8,"output_cost_per_token":2.6000000000000005e-7,"cache_read_input_token_cost":6.5e-9,"cache_creation_input_token_cost":4.095e-8},"pricing_endpoint":"qwen/qwen-flash","regions":[{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"qwen/qwen-flash","object":"model","created":1785412138,"owned_by":"qwen","model_name":"qwen-flash","context_length":1000000,"max_input_tokens":995904,"max_output_tokens":32768,"quantization":null,"retirement_date":null,"description":"Qwen3 series Flash model, integrates thinking and non-thinking modes and can switch modes during dialogue. Excels at complex thinking tasks; instruction following and text understanding significantly improved. Supports 1 M context length, and uses tiered pricing.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"tiered_pricing":[{"range":[0,256000],"input_cost_per_token":3.2500000000000006e-8,"output_cost_per_token":2.6000000000000005e-7,"cache_read_input_token_cost":6.5e-9,"cache_creation_input_token_cost":4.095e-8},{"range":[256000,1000000],"input_cost_per_token":1.625e-7,"output_cost_per_token":1.3e-6,"cache_read_input_token_cost":3.2500000000000006e-8,"cache_creation_input_token_cost":2.0345e-7}],"input_cost_per_token":3.2500000000000006e-8,"output_cost_per_token":2.6000000000000005e-7,"cache_read_input_token_cost":6.5e-9,"cache_creation_input_token_cost":4.095e-8},"list_pricing":{"tiered_pricing":[{"range":[0,256000],"input_cost_per_token":5.0000000000000004e-8,"output_cost_per_token":4.0000000000000003e-7,"cache_read_input_token_cost":1e-8,"cache_creation_input_token_cost":6.3e-8},{"range":[256000,1000000],"input_cost_per_token":2.5e-7,"output_cost_per_token":2e-6,"cache_read_input_token_cost":5.0000000000000004e-8,"cache_creation_input_token_cost":3.13e-7}],"input_cost_per_token":5.0000000000000004e-8,"output_cost_per_token":4.0000000000000003e-7,"cache_read_input_token_cost":1e-8,"cache_creation_input_token_cost":6.3e-8},"discount":0.35,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":1},{"id":"qwen-flash-character","object":"model","created":1785412138,"owned_by":"qwen","mode":"chat","context_length":8192,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.2500000000000006e-8,"output_cost_per_token":2.6000000000000005e-7,"cache_read_input_token_cost":6.5e-9},"pricing_endpoint":"qwen/qwen-flash-character","regions":[{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"qwen/qwen-flash-character","object":"model","created":1785412138,"owned_by":"qwen","model_name":"qwen-flash-character","context_length":8192,"max_input_tokens":8000,"max_output_tokens":4096,"quantization":null,"retirement_date":null,"description":"The Qwen Role-Playing Model Series is specifically optimized for muti-language anthropomorphic interaction scenarios. It demonstrates advanced capabilities in character consistency maintenance, context-aware dialogue progression, and empathetic engagement, enabling precise personalized character embodiment. This version significantly enhances Japanese linguistic localization (including dialects and honorifics), human-like role-playing authenticity, narrative coherence control, and scenario-based cognitive intelligence.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.2500000000000006e-8,"output_cost_per_token":2.6000000000000005e-7,"cache_read_input_token_cost":6.5e-9},"list_pricing":{"input_cost_per_token":5.0000000000000004e-8,"output_cost_per_token":4.0000000000000003e-7,"cache_read_input_token_cost":1e-8},"discount":0.35,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":1},{"id":"qwen-max","object":"model","created":1785412138,"owned_by":"qwen","mode":"chat","context_length":32768,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.0400000000000002e-6,"output_cost_per_token":4.160000000000001e-6,"cache_read_input_token_cost":2.08e-7},"pricing_endpoint":"qwen/qwen-max","regions":[{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"qwen/qwen-max","object":"model","created":1785412138,"owned_by":"qwen","model_name":"qwen-max","context_length":32768,"max_input_tokens":30720,"max_output_tokens":8192,"quantization":null,"retirement_date":null,"description":"An ultra-large language model with hundreds of billions of parameters of the Qwen2.5 series. It supports inputs in multiple languages, such as Chinese and English. With the model's continuous upgrades, Qwen-Max will be updated periodically. If you wish to use a fixed version, use the snapshot version instead.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.0400000000000002e-6,"output_cost_per_token":4.160000000000001e-6,"cache_read_input_token_cost":2.08e-7},"list_pricing":{"input_cost_per_token":1.6000000000000001e-6,"output_cost_per_token":6.4000000000000006e-6,"cache_read_input_token_cost":3.2e-7},"discount":0.35,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":1},{"id":"qwen-mt-flash","object":"model","created":1785412138,"owned_by":"qwen","mode":"chat","context_length":16384,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.04e-7,"output_cost_per_token":3.185e-7},"pricing_endpoint":"qwen/qwen-mt-flash","regions":[{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"qwen/qwen-mt-flash","object":"model","created":1785412138,"owned_by":"qwen","model_name":"qwen-mt-flash","context_length":16384,"max_input_tokens":8192,"max_output_tokens":8192,"quantization":null,"retirement_date":null,"description":"Qwen-MT-Flash, a large language model from the Qwen series, has been fully upgraded with the Qwen3 architecture for significantly enhanced performance and translation quality. It provides rapid, cost-effective translation across 92 languages, while supporting advanced features such as terminology intervention, format preservation, and domain-specific adaptation. It is the ideal choice for applications requiring a powerful balance of speed, quality, and cost.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.04e-7,"output_cost_per_token":3.185e-7},"list_pricing":{"input_cost_per_token":1.6e-7,"output_cost_per_token":4.9e-7},"discount":0.35,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":1},{"id":"qwen-mt-lite","object":"model","created":1785412138,"owned_by":"qwen","mode":"chat","context_length":16384,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":7.8e-8,"output_cost_per_token":2.34e-7},"pricing_endpoint":"qwen/qwen-mt-lite","regions":[{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"qwen/qwen-mt-lite","object":"model","created":1785412138,"owned_by":"qwen","model_name":"qwen-mt-lite","context_length":16384,"max_input_tokens":8192,"max_output_tokens":8192,"quantization":null,"retirement_date":null,"description":"Qwen-MT-Lite is a large language model of the Qwen model series that specializes in multi-lingual translation. It provides high-quality and rapid translation services across 32 languages at a cost-effective price. It offers features such as terminology intervention, format preservation, and domain-specific translation to cater to the diverse needs of various applications, ensuring both efficiency and performance.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":7.8e-8,"output_cost_per_token":2.34e-7},"list_pricing":{"input_cost_per_token":1.2e-7,"output_cost_per_token":3.6e-7},"discount":0.35,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":1},{"id":"qwen-mt-plus","object":"model","created":1785412138,"owned_by":"qwen","mode":"chat","context_length":4096,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.599e-6,"output_cost_per_token":4.7905e-6},"pricing_endpoint":"qwen/qwen-mt-plus","regions":[{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"qwen/qwen-mt-plus","object":"model","created":1785412138,"owned_by":"qwen","model_name":"qwen-mt-plus","context_length":4096,"max_input_tokens":2048,"max_output_tokens":2048,"quantization":null,"retirement_date":null,"description":"Qwen-MT-Plus is a flagship multilingual large language model specializing in translation. Being part of the Qwen model series, it supports translation between 92 languages and significantly outperforms traditional translation models in contextual understanding, terminology intervention, format preservation, and domain-specific tasks, and thereby delivers more natural and accurate translations.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.599e-6,"output_cost_per_token":4.7905e-6},"list_pricing":{"input_cost_per_token":2.46e-6,"output_cost_per_token":7.37e-6},"discount":0.35,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":1},{"id":"qwen-plus-character","object":"model","created":1785412138,"owned_by":"qwen","mode":"chat","context_length":32768,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.25e-7,"output_cost_per_token":9.1e-7,"cache_read_input_token_cost":6.500000000000001e-8},"pricing_endpoint":"qwen/qwen-plus-character","regions":[{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"qwen/qwen-plus-character","object":"model","created":1785412138,"owned_by":"qwen","model_name":"qwen-plus-character","context_length":32768,"max_input_tokens":32768,"max_output_tokens":4096,"quantization":null,"retirement_date":null,"description":"The role-playing model of the Qwen series. This is a dynamically updated version, and notifications will be provided in advance for any model updates. It is suitable for anthropomorphic role-playing and has optimized capabilities in following predefined character instructions, advancing conversations, and demonstrating active listening and empathy. Additionally, it supports the deep restoration of personalized characters.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.25e-7,"output_cost_per_token":9.1e-7,"cache_read_input_token_cost":6.500000000000001e-8},"list_pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":1.4e-6,"cache_read_input_token_cost":1.0000000000000001e-7},"discount":0.35,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":1},{"id":"qwen-vl-ocr-2025-11-20","object":"model","created":1785412138,"owned_by":"qwen","mode":"chat","context_length":38192,"capabilities":{"input_modalities":["image","text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4.5500000000000004e-8,"output_cost_per_token":1.04e-7},"pricing_endpoint":"qwen/qwen-vl-ocr-2025-11-20","regions":[{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"qwen/qwen-vl-ocr-2025-11-20","object":"model","created":1785412138,"owned_by":"qwen","model_name":"qwen-vl-ocr-2025-11-20","context_length":38192,"max_input_tokens":30000,"max_output_tokens":8192,"quantization":null,"retirement_date":null,"description":"This model is a snapshot version from November 20, 2025, and is based on the latest Qwen-VL3 architecture with a comprehensive upgrade. It features significant improvements in document parsing and text localization capabilities, as well as substantial reductions in end-to-end latency and illusions.","source":null,"capabilities":{"input_modalities":["image","text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4.5500000000000004e-8,"output_cost_per_token":1.04e-7},"list_pricing":{"input_cost_per_token":7e-8,"output_cost_per_token":1.6e-7},"discount":0.35,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":1},{"id":"qwen3-vl-plus","object":"model","created":1785412138,"owned_by":"qwen","mode":"chat","context_length":262144,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"tiered_pricing":[{"range":[0,32000],"input_cost_per_token":1.3000000000000003e-7,"output_cost_per_token":1.0400000000000002e-6,"cache_read_input_token_cost":2.6e-8,"cache_creation_input_token_cost":1.625e-7},{"range":[32000,128000],"input_cost_per_token":1.9499999999999999e-7,"output_cost_per_token":1.5599999999999999e-6,"cache_read_input_token_cost":3.9e-8,"cache_creation_input_token_cost":2.4375e-7},{"range":[128000,256000],"input_cost_per_token":3.8999999999999997e-7,"output_cost_per_token":3.1199999999999998e-6,"cache_read_input_token_cost":7.8e-8,"cache_creation_input_token_cost":4.875e-7}],"input_cost_per_token":1.3000000000000003e-7,"output_cost_per_token":1.0400000000000002e-6,"cache_read_input_token_cost":2.6e-8,"cache_creation_input_token_cost":1.625e-7},"pricing_endpoint":"qwen/qwen3-vl-plus","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"qwen/qwen3-vl-plus@eu","object":"model","created":1785412138,"owned_by":"qwen","model_name":"qwen3-vl-plus","context_length":262144,"max_input_tokens":258048,"max_output_tokens":32768,"quantization":null,"retirement_date":null,"description":"The Qwen3 series VL models effectively integrates thinking and non-thinking modes, achieving world-leading performance in visual agent capabilities on public benchmark datasets such as OS World. This version features comprehensive upgrades in areas like visual coding, spatial perception, and multimodal reasoning, significantly enhancing visual perception and recognition abilities, and supporting the understanding of ultra-long videos.","source":null,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"tiered_pricing":[{"range":[0,32000],"input_cost_per_token":1.3000000000000003e-7,"output_cost_per_token":1.0400000000000002e-6,"cache_read_input_token_cost":2.6e-8,"cache_creation_input_token_cost":1.625e-7},{"range":[32000,128000],"input_cost_per_token":1.9499999999999999e-7,"output_cost_per_token":1.5599999999999999e-6,"cache_read_input_token_cost":3.9e-8,"cache_creation_input_token_cost":2.4375e-7},{"range":[128000,256000],"input_cost_per_token":3.8999999999999997e-7,"output_cost_per_token":3.1199999999999998e-6,"cache_read_input_token_cost":7.8e-8,"cache_creation_input_token_cost":4.875e-7}],"input_cost_per_token":1.3000000000000003e-7,"output_cost_per_token":1.0400000000000002e-6,"cache_read_input_token_cost":2.6e-8,"cache_creation_input_token_cost":1.625e-7},"list_pricing":{"tiered_pricing":[{"range":[0,32000],"input_cost_per_token":2.0000000000000002e-7,"output_cost_per_token":1.6000000000000001e-6,"cache_read_input_token_cost":4e-8,"cache_creation_input_token_cost":2.5e-7},{"range":[32000,128000],"input_cost_per_token":3e-7,"output_cost_per_token":2.4e-6,"cache_read_input_token_cost":6e-8,"cache_creation_input_token_cost":3.75e-7},{"range":[128000,256000],"input_cost_per_token":6e-7,"output_cost_per_token":4.8e-6,"cache_read_input_token_cost":1.2e-7,"cache_creation_input_token_cost":7.5e-7}],"input_cost_per_token":2.0000000000000002e-7,"output_cost_per_token":1.6000000000000001e-6,"cache_read_input_token_cost":4e-8,"cache_creation_input_token_cost":2.5e-7},"discount":0.35,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"qwen/qwen3-vl-plus","object":"model","created":1785412138,"owned_by":"qwen","model_name":"qwen3-vl-plus","context_length":262144,"max_input_tokens":258048,"max_output_tokens":32768,"quantization":null,"retirement_date":null,"description":"The Qwen3 series VL models effectively integrates thinking and non-thinking modes, achieving world-leading performance in visual agent capabilities on public benchmark datasets such as OS World. This version features comprehensive upgrades in areas like visual coding, spatial perception, and multimodal reasoning, significantly enhancing visual perception and recognition abilities, and supporting the understanding of ultra-long videos.","source":null,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"tiered_pricing":[{"range":[0,32000],"input_cost_per_token":1.3000000000000003e-7,"output_cost_per_token":1.0400000000000002e-6,"cache_read_input_token_cost":2.6e-8,"cache_creation_input_token_cost":1.625e-7},{"range":[32000,128000],"input_cost_per_token":1.9499999999999999e-7,"output_cost_per_token":1.5599999999999999e-6,"cache_read_input_token_cost":3.9e-8,"cache_creation_input_token_cost":2.4375e-7},{"range":[128000,256000],"input_cost_per_token":3.8999999999999997e-7,"output_cost_per_token":3.1199999999999998e-6,"cache_read_input_token_cost":7.8e-8,"cache_creation_input_token_cost":4.875e-7}],"input_cost_per_token":1.3000000000000003e-7,"output_cost_per_token":1.0400000000000002e-6,"cache_read_input_token_cost":2.6e-8,"cache_creation_input_token_cost":1.625e-7},"list_pricing":{"tiered_pricing":[{"range":[0,32000],"input_cost_per_token":2.0000000000000002e-7,"output_cost_per_token":1.6000000000000001e-6,"cache_read_input_token_cost":4e-8,"cache_creation_input_token_cost":2.5e-7},{"range":[32000,128000],"input_cost_per_token":3e-7,"output_cost_per_token":2.4e-6,"cache_read_input_token_cost":6e-8,"cache_creation_input_token_cost":3.75e-7},{"range":[128000,256000],"input_cost_per_token":6e-7,"output_cost_per_token":4.8e-6,"cache_read_input_token_cost":1.2e-7,"cache_creation_input_token_cost":7.5e-7}],"input_cost_per_token":2.0000000000000002e-7,"output_cost_per_token":1.6000000000000001e-6,"cache_read_input_token_cost":4e-8,"cache_creation_input_token_cost":2.5e-7},"discount":0.35,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":2},{"id":"qwen3.5-flash","object":"model","created":1785412138,"owned_by":"qwen","mode":"chat","context_length":1000000,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6.500000000000001e-8,"output_cost_per_token":2.6000000000000005e-7,"cache_creation_input_token_cost":8.125e-8},"pricing_endpoint":"qwen/qwen3.5-flash","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"qwen/qwen3.5-flash@eu","object":"model","created":1785412138,"owned_by":"qwen","model_name":"qwen3.5-flash","context_length":1000000,"max_input_tokens":991808,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"The Qwen3.5 native vision-language Flash models are built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. Compared to the 3 series, these models deliver a leap forward in performance for both pure text and multimodal tasks, offering fast response times while balancing inference speed and overall performance.","source":null,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6.500000000000001e-8,"output_cost_per_token":2.6000000000000005e-7,"cache_creation_input_token_cost":8.125e-8},"list_pricing":{"input_cost_per_token":1.0000000000000001e-7,"output_cost_per_token":4.0000000000000003e-7,"cache_creation_input_token_cost":1.25e-7},"discount":0.35,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"qwen/qwen3.5-flash","object":"model","created":1785412138,"owned_by":"qwen","model_name":"qwen3.5-flash","context_length":1000000,"max_input_tokens":991808,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"The Qwen3.5 native vision-language Flash models are built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. Compared to the 3 series, these models deliver a leap forward in performance for both pure text and multimodal tasks, offering fast response times while balancing inference speed and overall performance.","source":null,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6.500000000000001e-8,"output_cost_per_token":2.6000000000000005e-7,"cache_creation_input_token_cost":8.125e-8},"list_pricing":{"input_cost_per_token":1.0000000000000001e-7,"output_cost_per_token":4.0000000000000003e-7,"cache_creation_input_token_cost":1.25e-7},"discount":0.35,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":2},{"id":"qwen3.5-flash-2026-02-23","object":"model","created":1785412138,"owned_by":"qwen","mode":"chat","context_length":1000000,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6.500000000000001e-8,"output_cost_per_token":2.6000000000000005e-7},"pricing_endpoint":"qwen/qwen3.5-flash-2026-02-23","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"qwen/qwen3.5-flash-2026-02-23@eu","object":"model","created":1785412138,"owned_by":"qwen","model_name":"qwen3.5-flash-2026-02-23","context_length":1000000,"max_input_tokens":991808,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"The Qwen3.5 native vision-language Flash models are built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. Compared to the 3 series, these models deliver a leap forward in performance for both pure text and multimodal tasks, offering fast response times while balancing inference speed and overall performance.This version is a snapshot as of February 23, 2026.","source":null,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6.500000000000001e-8,"output_cost_per_token":2.6000000000000005e-7},"list_pricing":{"input_cost_per_token":1.0000000000000001e-7,"output_cost_per_token":4.0000000000000003e-7},"discount":0.35,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"qwen/qwen3.5-flash-2026-02-23","object":"model","created":1785412138,"owned_by":"qwen","model_name":"qwen3.5-flash-2026-02-23","context_length":1000000,"max_input_tokens":991808,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"The Qwen3.5 native vision-language Flash models are built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. Compared to the 3 series, these models deliver a leap forward in performance for both pure text and multimodal tasks, offering fast response times while balancing inference speed and overall performance.This version is a snapshot as of February 23, 2026.","source":null,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6.500000000000001e-8,"output_cost_per_token":2.6000000000000005e-7},"list_pricing":{"input_cost_per_token":1.0000000000000001e-7,"output_cost_per_token":4.0000000000000003e-7},"discount":0.35,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":2},{"id":"gemma-4-31b-it-ultra","object":"model","created":1785251243,"owned_by":"google","mode":"chat","context_length":131072,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.7e-7,"output_cost_per_token":7.6e-7},"pricing_endpoint":"deepinfra/google/gemma-4-31B-it-Ultra","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"deepinfra/google/gemma-4-31B-it-Ultra","object":"model","created":1785251243,"owned_by":"deepinfra","model_name":"google/gemma-4-31B-it-Ultra","context_length":131072,"max_input_tokens":131072,"max_output_tokens":null,"quantization":"fp8","retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.7e-7,"output_cost_per_token":7.6e-7},"list_pricing":{"input_cost_per_token":2.7e-7,"output_cost_per_token":7.6e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"gpt-oss-120b-ultra","object":"model","created":1785251243,"owned_by":"openai","mode":"chat","context_length":131072,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.0000000000000002e-7,"output_cost_per_token":9.499999999999999e-7},"pricing_endpoint":"deepinfra/openai/gpt-oss-120b-Ultra","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"deepinfra/openai/gpt-oss-120b-Ultra","object":"model","created":1785251243,"owned_by":"deepinfra","model_name":"openai/gpt-oss-120b-Ultra","context_length":131072,"max_input_tokens":131072,"max_output_tokens":null,"quantization":"fp8","retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.0000000000000002e-7,"output_cost_per_token":9.499999999999999e-7},"list_pricing":{"input_cost_per_token":2.0000000000000002e-7,"output_cost_per_token":9.499999999999999e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"qwen3.7-flash","object":"model","created":1785190561,"owned_by":"qwen","mode":"chat","context_length":1000000,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"tiered_pricing":[{"range":[0,32000],"input_cost_per_token":1.95e-8,"output_cost_per_token":8.450000000000001e-8,"cache_read_input_token_cost":3.9e-9,"cache_creation_input_token_cost":2.47e-8},{"range":[32000,256000],"input_cost_per_token":6.500000000000001e-8,"output_cost_per_token":2.6000000000000005e-7,"cache_read_input_token_cost":1.3e-8,"cache_creation_input_token_cost":8.125e-8},{"range":[256000,1000000],"input_cost_per_token":1.3000000000000003e-7,"output_cost_per_token":5.200000000000001e-7,"cache_read_input_token_cost":2.6e-8,"cache_creation_input_token_cost":1.625e-7}],"input_cost_per_token":1.95e-8,"output_cost_per_token":8.450000000000001e-8,"cache_read_input_token_cost":3.9e-9,"cache_creation_input_token_cost":2.47e-8},"pricing_endpoint":"qwen/qwen3.7-flash","regions":[{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"qwen/qwen3.7-flash","object":"model","created":1785190561,"owned_by":"qwen","model_name":"qwen3.7-flash","context_length":1000000,"max_input_tokens":991808,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"The Qwen3.7 native vision-language Flash model series delivers a comprehensive upgrade over 3.6-Flash in multimodal understanding and agent execution. This model particularly excels in enhanced multimodal foundations with stronger universal object recognition, further improved real-world perception and spatial intelligence, significantly upgraded multimodal agent capabilities for Search Agent and CI Agent scenarios with more stable end-to-end task execution, as well as optimized multimodal coding for a smoother vibe coding experience.","source":null,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"tiered_pricing":[{"range":[0,32000],"input_cost_per_token":1.95e-8,"output_cost_per_token":8.450000000000001e-8,"cache_read_input_token_cost":3.9e-9,"cache_creation_input_token_cost":2.47e-8},{"range":[32000,256000],"input_cost_per_token":6.500000000000001e-8,"output_cost_per_token":2.6000000000000005e-7,"cache_read_input_token_cost":1.3e-8,"cache_creation_input_token_cost":8.125e-8},{"range":[256000,1000000],"input_cost_per_token":1.3000000000000003e-7,"output_cost_per_token":5.200000000000001e-7,"cache_read_input_token_cost":2.6e-8,"cache_creation_input_token_cost":1.625e-7}],"input_cost_per_token":1.95e-8,"output_cost_per_token":8.450000000000001e-8,"cache_read_input_token_cost":3.9e-9,"cache_creation_input_token_cost":2.47e-8},"list_pricing":{"tiered_pricing":[{"range":[0,32000],"input_cost_per_token":3e-8,"output_cost_per_token":1.3e-7,"cache_read_input_token_cost":6e-9,"cache_creation_input_token_cost":3.7999999999999996e-8},{"range":[32000,256000],"input_cost_per_token":1.0000000000000001e-7,"output_cost_per_token":4.0000000000000003e-7,"cache_read_input_token_cost":2e-8,"cache_creation_input_token_cost":1.25e-7},{"range":[256000,1000000],"input_cost_per_token":2.0000000000000002e-7,"output_cost_per_token":8.000000000000001e-7,"cache_read_input_token_cost":4e-8,"cache_creation_input_token_cost":2.5e-7}],"input_cost_per_token":3e-8,"output_cost_per_token":1.3e-7,"cache_read_input_token_cost":6e-9,"cache_creation_input_token_cost":3.7999999999999996e-8},"discount":0.35,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":1},{"id":"qwen3.7-flash-2026-07-15","object":"model","created":1785190561,"owned_by":"qwen","mode":"chat","context_length":1000000,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"tiered_pricing":[{"range":[0,32000],"input_cost_per_token":1.95e-8,"output_cost_per_token":8.450000000000001e-8,"cache_read_input_token_cost":3.9e-9,"cache_creation_input_token_cost":2.47e-8},{"range":[32000,256000],"input_cost_per_token":6.500000000000001e-8,"output_cost_per_token":2.6000000000000005e-7,"cache_read_input_token_cost":1.3e-8,"cache_creation_input_token_cost":8.125e-8},{"range":[256000,1000000],"input_cost_per_token":1.3000000000000003e-7,"output_cost_per_token":5.200000000000001e-7,"cache_read_input_token_cost":2.6e-8,"cache_creation_input_token_cost":1.625e-7}],"input_cost_per_token":1.95e-8,"output_cost_per_token":8.450000000000001e-8,"cache_read_input_token_cost":3.9e-9,"cache_creation_input_token_cost":2.47e-8},"pricing_endpoint":"qwen/qwen3.7-flash-2026-07-15","regions":[{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"qwen/qwen3.7-flash-2026-07-15","object":"model","created":1785190561,"owned_by":"qwen","model_name":"qwen3.7-flash-2026-07-15","context_length":1000000,"max_input_tokens":991808,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"The Qwen3.7 native vision-language Flash model series delivers a comprehensive upgrade over 3.6-Flash in multimodal understanding and agent execution. This model particularly excels in enhanced multimodal foundations with stronger universal object recognition, further improved real-world perception and spatial intelligence, significantly upgraded multimodal agent capabilities for Search Agent and CI Agent scenarios with more stable end-to-end task execution, as well as optimized multimodal coding for a smoother vibe coding experience. This version is a snapshot from July 15, 2026.","source":null,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"tiered_pricing":[{"range":[0,32000],"input_cost_per_token":1.95e-8,"output_cost_per_token":8.450000000000001e-8,"cache_read_input_token_cost":3.9e-9,"cache_creation_input_token_cost":2.47e-8},{"range":[32000,256000],"input_cost_per_token":6.500000000000001e-8,"output_cost_per_token":2.6000000000000005e-7,"cache_read_input_token_cost":1.3e-8,"cache_creation_input_token_cost":8.125e-8},{"range":[256000,1000000],"input_cost_per_token":1.3000000000000003e-7,"output_cost_per_token":5.200000000000001e-7,"cache_read_input_token_cost":2.6e-8,"cache_creation_input_token_cost":1.625e-7}],"input_cost_per_token":1.95e-8,"output_cost_per_token":8.450000000000001e-8,"cache_read_input_token_cost":3.9e-9,"cache_creation_input_token_cost":2.47e-8},"list_pricing":{"tiered_pricing":[{"range":[0,32000],"input_cost_per_token":3e-8,"output_cost_per_token":1.3e-7,"cache_read_input_token_cost":6e-9,"cache_creation_input_token_cost":3.7999999999999996e-8},{"range":[32000,256000],"input_cost_per_token":1.0000000000000001e-7,"output_cost_per_token":4.0000000000000003e-7,"cache_read_input_token_cost":2e-8,"cache_creation_input_token_cost":1.25e-7},{"range":[256000,1000000],"input_cost_per_token":2.0000000000000002e-7,"output_cost_per_token":8.000000000000001e-7,"cache_read_input_token_cost":4e-8,"cache_creation_input_token_cost":2.5e-7}],"input_cost_per_token":3e-8,"output_cost_per_token":1.3e-7,"cache_read_input_token_cost":6e-9,"cache_creation_input_token_cost":3.7999999999999996e-8},"discount":0.35,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":1},{"id":"gpt-4o","object":"model","created":1784916453,"owned_by":"openai","mode":"chat","context_length":128000,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2.5e-6,"output_cost_per_token":0.00001,"cache_read_input_token_cost":1.25e-6,"input_cost_per_token_batches":1.25e-6,"input_cost_per_token_priority":4.25e-6,"output_cost_per_token_batches":5e-6,"output_cost_per_token_priority":0.000017,"cache_read_input_token_cost_priority":2.125e-6},"pricing_endpoint":"openai/gpt-4o","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"azure/gpt-4o@eu","object":"model","created":1784916453,"owned_by":"azure","model_name":"gpt-4o","context_length":128000,"max_input_tokens":128000,"max_output_tokens":16384,"quantization":null,"retirement_date":null,"description":"GPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2.7500000000000004e-6,"output_cost_per_token":0.000011000000000000001,"cache_read_input_token_cost":1.3750000000000002e-6},"list_pricing":{"input_cost_per_token":2.7500000000000004e-6,"output_cost_per_token":0.000011000000000000001,"cache_read_input_token_cost":1.3750000000000002e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"azure/gpt-4o","object":"model","created":1784916453,"owned_by":"azure","model_name":"gpt-4o","context_length":128000,"max_input_tokens":128000,"max_output_tokens":16384,"quantization":null,"retirement_date":null,"description":"GPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2.5e-6,"output_cost_per_token":0.00001,"cache_read_input_token_cost":1.25e-6},"list_pricing":{"input_cost_per_token":2.5e-6,"output_cost_per_token":0.00001,"cache_read_input_token_cost":1.25e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"azure/gpt-4o@us","object":"model","created":1784916453,"owned_by":"azure","model_name":"gpt-4o","context_length":128000,"max_input_tokens":128000,"max_output_tokens":16384,"quantization":null,"retirement_date":null,"description":"GPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2.7500000000000004e-6,"output_cost_per_token":0.000011000000000000001,"cache_read_input_token_cost":1.3750000000000002e-6},"list_pricing":{"input_cost_per_token":2.7500000000000004e-6,"output_cost_per_token":0.000011000000000000001,"cache_read_input_token_cost":1.3750000000000002e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"openai/gpt-4o","object":"model","created":1732127594,"owned_by":"openai","model_name":"gpt-4o","context_length":128000,"max_input_tokens":128000,"max_output_tokens":16384,"quantization":null,"retirement_date":null,"description":"GPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2.5e-6,"output_cost_per_token":0.00001,"cache_read_input_token_cost":1.25e-6,"input_cost_per_token_batches":1.25e-6,"input_cost_per_token_priority":4.25e-6,"output_cost_per_token_batches":5e-6,"output_cost_per_token_priority":0.000017,"cache_read_input_token_cost_priority":2.125e-6},"list_pricing":{"input_cost_per_token":2.5e-6,"output_cost_per_token":0.00001,"cache_read_input_token_cost":1.25e-6,"input_cost_per_token_batches":1.25e-6,"input_cost_per_token_priority":4.25e-6,"output_cost_per_token_batches":5e-6,"output_cost_per_token_priority":0.000017,"cache_read_input_token_cost_priority":2.125e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null},{"id":"microsoft/gpt-4o","object":"model","created":1715558400,"owned_by":"microsoft","model_name":"gpt-4o","context_length":128000,"max_input_tokens":128000,"max_output_tokens":16384,"quantization":null,"retirement_date":null,"description":"GPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as...","source":null,"capabilities":{"input_modalities":["file","image","text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2.5e-6,"output_cost_per_token":0.00001,"cache_read_input_token_cost":1.25e-6},"list_pricing":{"input_cost_per_token":2.5e-6,"output_cost_per_token":0.00001,"cache_read_input_token_cost":1.25e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":5},{"id":"gpt-4o-mini","object":"model","created":1784916453,"owned_by":"openai","mode":"chat","context_length":128000,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":7.5e-8,"input_cost_per_token_batches":7.5e-8,"input_cost_per_token_priority":2.5e-7,"output_cost_per_token_batches":3e-7,"search_context_cost_per_query":{"search_context_size_low":0.025,"search_context_size_high":0.025,"search_context_size_medium":0.025},"output_cost_per_token_priority":1e-6,"cache_read_input_token_cost_priority":1.25e-7},"pricing_endpoint":"openai/gpt-4o-mini","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"azure/gpt-4o-mini","object":"model","created":1784916453,"owned_by":"azure","model_name":"gpt-4o-mini","context_length":128000,"max_input_tokens":128000,"max_output_tokens":16384,"quantization":null,"retirement_date":null,"description":"GPT-4o mini is OpenAI's newest model after GPT-4 Omni, supporting both text and image inputs with text outputs.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.65e-7,"output_cost_per_token":6.6e-7,"cache_read_input_token_cost":8.25e-8,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014}},"list_pricing":{"input_cost_per_token":1.65e-7,"output_cost_per_token":6.6e-7,"cache_read_input_token_cost":8.25e-8,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014}},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"azure/gpt-4o-mini@us","object":"model","created":1784916453,"owned_by":"azure","model_name":"gpt-4o-mini","context_length":128000,"max_input_tokens":128000,"max_output_tokens":16384,"quantization":null,"retirement_date":null,"description":"GPT-4o mini is OpenAI's newest model after GPT-4 Omni, supporting both text and image inputs with text outputs.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.65e-7,"output_cost_per_token":6.6e-7,"cache_read_input_token_cost":8.25e-8,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014}},"list_pricing":{"input_cost_per_token":1.65e-7,"output_cost_per_token":6.6e-7,"cache_read_input_token_cost":8.25e-8,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014}},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"microsoft/gpt-4o-mini","object":"model","created":1721260800,"owned_by":"microsoft","model_name":"gpt-4o-mini","context_length":128000,"max_input_tokens":128000,"max_output_tokens":16384,"quantization":null,"retirement_date":null,"description":"GPT-4o mini is OpenAI's newest model after GPT-4 Omni, supporting both text and image inputs with text outputs.","source":null,"capabilities":{"input_modalities":["file","image","text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":7.5e-8},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":7.5e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null},{"id":"openai/gpt-4o-mini","object":"model","created":1721260800,"owned_by":"openai","model_name":"gpt-4o-mini","context_length":128000,"max_input_tokens":128000,"max_output_tokens":16384,"quantization":null,"retirement_date":null,"description":"GPT-4o mini is OpenAI's newest model after GPT-4 Omni, supporting both text and image inputs with text outputs.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":7.5e-8,"input_cost_per_token_batches":7.5e-8,"input_cost_per_token_priority":2.5e-7,"output_cost_per_token_batches":3e-7,"search_context_cost_per_query":{"search_context_size_low":0.025,"search_context_size_high":0.025,"search_context_size_medium":0.025},"output_cost_per_token_priority":1e-6,"cache_read_input_token_cost_priority":1.25e-7},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":7.5e-8,"input_cost_per_token_batches":7.5e-8,"input_cost_per_token_priority":2.5e-7,"output_cost_per_token_batches":3e-7,"search_context_cost_per_query":{"search_context_size_low":0.025,"search_context_size_high":0.025,"search_context_size_medium":0.025},"output_cost_per_token_priority":1e-6,"cache_read_input_token_cost_priority":1.25e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":4},{"id":"gpt-5-pro","object":"model","created":1784916453,"owned_by":"openai","mode":"chat","context_length":400000,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":0.000015,"output_cost_per_token":0.00012,"input_cost_per_token_batches":7.5e-6,"output_cost_per_token_batches":0.00006,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01}},"pricing_endpoint":"openai/gpt-5-pro","regions":[{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"azure/gpt-5-pro","object":"model","created":1784916453,"owned_by":"azure","model_name":"gpt-5-pro","context_length":400000,"max_input_tokens":272000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5 Pro is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":0.000015,"output_cost_per_token":0.00012,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014}},"list_pricing":{"input_cost_per_token":0.000015,"output_cost_per_token":0.00012,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014}},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"openai/gpt-5-pro","object":"model","created":1759776663,"owned_by":"openai","model_name":"gpt-5-pro","context_length":400000,"max_input_tokens":272000,"max_output_tokens":128000,"quantization":null,"retirement_date":"2026-12-11","description":"GPT-5 Pro is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience.","source":null,"capabilities":{"input_modalities":["image","text","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":0.000015,"output_cost_per_token":0.00012,"input_cost_per_token_batches":7.5e-6,"output_cost_per_token_batches":0.00006,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01}},"list_pricing":{"input_cost_per_token":0.000015,"output_cost_per_token":0.00012,"input_cost_per_token_batches":7.5e-6,"output_cost_per_token_batches":0.00006,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01}},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":2},{"id":"gpt-5.4-pro","object":"model","created":1784916453,"owned_by":"openai","mode":"chat","context_length":1050000,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":0.00003,"output_cost_per_token":0.00018,"cache_read_input_token_cost":3e-6,"input_cost_per_token_priority":0.00006,"output_cost_per_token_priority":0.00036,"cache_read_input_token_cost_priority":6e-6,"input_cost_per_token_above_272k_tokens":0.00006,"output_cost_per_token_above_272k_tokens":0.00027,"cache_read_input_token_cost_above_272k_tokens":6e-6,"input_cost_per_token_above_272k_tokens_priority":0.00012,"output_cost_per_token_above_272k_tokens_priority":0.00054,"cache_read_input_token_cost_above_272k_tokens_priority":0.000012},"pricing_endpoint":"azure/gpt-5.4-pro","regions":[{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"azure/gpt-5.4-pro","object":"model","created":1784916453,"owned_by":"azure","model_name":"gpt-5.4-pro","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5.4 Pro is OpenAI's most advanced model, building on GPT-5.4's unified architecture with enhanced reasoning capabilities for complex, high-stakes tasks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":0.00003,"output_cost_per_token":0.00018,"cache_read_input_token_cost":3e-6,"input_cost_per_token_priority":0.00006,"output_cost_per_token_priority":0.00036,"cache_read_input_token_cost_priority":6e-6,"input_cost_per_token_above_272k_tokens":0.00006,"output_cost_per_token_above_272k_tokens":0.00027,"cache_read_input_token_cost_above_272k_tokens":6e-6,"input_cost_per_token_above_272k_tokens_priority":0.00012,"output_cost_per_token_above_272k_tokens_priority":0.00054,"cache_read_input_token_cost_above_272k_tokens_priority":0.000012},"list_pricing":{"input_cost_per_token":0.00003,"output_cost_per_token":0.00018,"cache_read_input_token_cost":3e-6,"input_cost_per_token_priority":0.00006,"output_cost_per_token_priority":0.00036,"cache_read_input_token_cost_priority":6e-6,"input_cost_per_token_above_272k_tokens":0.00006,"output_cost_per_token_above_272k_tokens":0.00027,"cache_read_input_token_cost_above_272k_tokens":6e-6,"input_cost_per_token_above_272k_tokens_priority":0.00012,"output_cost_per_token_above_272k_tokens_priority":0.00054,"cache_read_input_token_cost_above_272k_tokens_priority":0.000012},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"openai/gpt-5.4-pro","object":"model","created":1772734366,"owned_by":"openai","model_name":"gpt-5.4-pro","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5.4 Pro is OpenAI's most advanced model, building on GPT-5.4's unified architecture with enhanced reasoning capabilities for complex, high-stakes tasks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":0.00003,"output_cost_per_token":0.00018,"input_cost_per_token_flex":0.000015,"output_cost_per_token_flex":0.00009,"input_cost_per_token_batches":0.000015,"output_cost_per_token_batches":0.00009,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"input_cost_per_token_above_272k_tokens":0.00006,"output_cost_per_token_above_272k_tokens":0.00027,"input_cost_per_token_above_272k_tokens_flex":0.00003,"output_cost_per_token_above_272k_tokens_flex":0.000135},"list_pricing":{"input_cost_per_token":0.00003,"output_cost_per_token":0.00018,"input_cost_per_token_flex":0.000015,"output_cost_per_token_flex":0.00009,"input_cost_per_token_batches":0.000015,"output_cost_per_token_batches":0.00009,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"input_cost_per_token_above_272k_tokens":0.00006,"output_cost_per_token_above_272k_tokens":0.00027,"input_cost_per_token_above_272k_tokens_flex":0.00003,"output_cost_per_token_above_272k_tokens_flex":0.000135},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":2},{"id":"o3","object":"model","created":1784916453,"owned_by":"openai","mode":"chat","context_length":200000,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":8e-6,"input_cost_per_token_flex":1e-6,"output_cost_per_token_flex":4e-6,"cache_read_input_token_cost":5e-7,"input_cost_per_token_batches":1e-6,"input_cost_per_token_priority":3.5e-6,"output_cost_per_token_batches":4e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"output_cost_per_token_priority":0.000014,"cache_read_input_token_cost_flex":2.5e-7,"cache_read_input_token_cost_priority":8.75e-7},"pricing_endpoint":"openai/o3","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"azure/o3@eu","object":"model","created":1784916453,"owned_by":"azure","model_name":"o3","context_length":200000,"max_input_tokens":200000,"max_output_tokens":100000,"quantization":null,"retirement_date":null,"description":"o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.2e-6,"output_cost_per_token":8.8e-6,"cache_read_input_token_cost":5.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014}},"list_pricing":{"input_cost_per_token":2.2e-6,"output_cost_per_token":8.8e-6,"cache_read_input_token_cost":5.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014}},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"azure/o3","object":"model","created":1784916453,"owned_by":"azure","model_name":"o3","context_length":200000,"max_input_tokens":200000,"max_output_tokens":100000,"quantization":null,"retirement_date":null,"description":"o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":8e-6,"cache_read_input_token_cost":5e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014}},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":8e-6,"cache_read_input_token_cost":5e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014}},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"azure/o3@us","object":"model","created":1784916453,"owned_by":"azure","model_name":"o3","context_length":200000,"max_input_tokens":200000,"max_output_tokens":100000,"quantization":null,"retirement_date":null,"description":"o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.2e-6,"output_cost_per_token":8.8e-6,"cache_read_input_token_cost":5.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014}},"list_pricing":{"input_cost_per_token":2.2e-6,"output_cost_per_token":8.8e-6,"cache_read_input_token_cost":5.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014}},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"openai/o3","object":"model","created":1744823457,"owned_by":"openai","model_name":"o3","context_length":200000,"max_input_tokens":200000,"max_output_tokens":100000,"quantization":null,"retirement_date":"2026-12-11","description":"o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks.","source":null,"capabilities":{"input_modalities":["image","text","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":8e-6,"input_cost_per_token_flex":1e-6,"output_cost_per_token_flex":4e-6,"cache_read_input_token_cost":5e-7,"input_cost_per_token_batches":1e-6,"input_cost_per_token_priority":3.5e-6,"output_cost_per_token_batches":4e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"output_cost_per_token_priority":0.000014,"cache_read_input_token_cost_flex":2.5e-7,"cache_read_input_token_cost_priority":8.75e-7},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":8e-6,"input_cost_per_token_flex":1e-6,"output_cost_per_token_flex":4e-6,"cache_read_input_token_cost":5e-7,"input_cost_per_token_batches":1e-6,"input_cost_per_token_priority":3.5e-6,"output_cost_per_token_batches":4e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"output_cost_per_token_priority":0.000014,"cache_read_input_token_cost_flex":2.5e-7,"cache_read_input_token_cost_priority":8.75e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":4},{"id":"gpt-5-codex","object":"model","created":1784832896,"owned_by":"openai","mode":"chat","context_length":272000,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":0.00001,"cache_read_input_token_cost":1.25e-7},"pricing_endpoint":"azure/gpt-5-codex","regions":[{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"azure/gpt-5-codex","object":"model","created":1784832896,"owned_by":"azure","model_name":"gpt-5-codex","context_length":272000,"max_input_tokens":272000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":0.00001,"cache_read_input_token_cost":1.25e-7},"list_pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":0.00001,"cache_read_input_token_cost":1.25e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"gpt-5.1-codex","object":"model","created":1784832896,"owned_by":"openai","mode":"chat","context_length":272000,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":0.00001,"cache_read_input_token_cost":1.25e-7},"pricing_endpoint":"azure/gpt-5.1-codex","regions":[{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"azure/gpt-5.1-codex","object":"model","created":1784832896,"owned_by":"azure","model_name":"gpt-5.1-codex","context_length":272000,"max_input_tokens":272000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5.1-Codex is a specialized version of GPT-5.1 optimized for software engineering and coding workflows.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":0.00001,"cache_read_input_token_cost":1.25e-7},"list_pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":0.00001,"cache_read_input_token_cost":1.25e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"gpt-5.1-codex-max","object":"model","created":1784832896,"owned_by":"openai","mode":"chat","context_length":272000,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":0.00001,"cache_read_input_token_cost":1.25e-7},"pricing_endpoint":"azure/gpt-5.1-codex-max","regions":[{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"azure/gpt-5.1-codex-max","object":"model","created":1784832896,"owned_by":"azure","model_name":"gpt-5.1-codex-max","context_length":272000,"max_input_tokens":272000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5.1-Codex-Max is OpenAI’s latest agentic coding model, designed for long-running, high-context software development tasks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":0.00001,"cache_read_input_token_cost":1.25e-7},"list_pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":0.00001,"cache_read_input_token_cost":1.25e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"gpt-5.1-codex-mini","object":"model","created":1784832896,"owned_by":"openai","mode":"chat","context_length":272000,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2.5e-7,"output_cost_per_token":2e-6,"cache_read_input_token_cost":2.5e-8},"pricing_endpoint":"azure/gpt-5.1-codex-mini","regions":[{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"azure/gpt-5.1-codex-mini","object":"model","created":1784832896,"owned_by":"azure","model_name":"gpt-5.1-codex-mini","context_length":272000,"max_input_tokens":272000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5.1-Codex-Mini is a smaller and faster version of GPT-5.1-Codex","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2.5e-7,"output_cost_per_token":2e-6,"cache_read_input_token_cost":2.5e-8},"list_pricing":{"input_cost_per_token":2.5e-7,"output_cost_per_token":2e-6,"cache_read_input_token_cost":2.5e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"gpt-5.2-codex","object":"model","created":1784832896,"owned_by":"openai","mode":"chat","context_length":272000,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.75e-6,"output_cost_per_token":0.000014,"cache_read_input_token_cost":1.75e-7},"pricing_endpoint":"azure/gpt-5.2-codex","regions":[{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"azure/gpt-5.2-codex","object":"model","created":1784832896,"owned_by":"azure","model_name":"gpt-5.2-codex","context_length":272000,"max_input_tokens":272000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5.2-Codex is an upgraded version of GPT-5.1-Codex optimized for software engineering and coding workflows.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.75e-6,"output_cost_per_token":0.000014,"cache_read_input_token_cost":1.75e-7},"list_pricing":{"input_cost_per_token":1.75e-6,"output_cost_per_token":0.000014,"cache_read_input_token_cost":1.75e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"gpt-5.3-codex","object":"model","created":1784832896,"owned_by":"openai","mode":"chat","context_length":400000,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.75e-6,"output_cost_per_token":0.000014,"cache_read_input_token_cost":1.75e-7,"input_cost_per_token_priority":3.5e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"output_cost_per_token_priority":0.000028,"cache_read_input_token_cost_priority":3.5e-7},"pricing_endpoint":"openai/gpt-5.3-codex","regions":[{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"azure/gpt-5.3-codex","object":"model","created":1784832896,"owned_by":"azure","model_name":"gpt-5.3-codex","context_length":400000,"max_input_tokens":272000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5.3-Codex is OpenAI’s most advanced agentic coding model, combining the frontier software engineering performance of GPT-5.2-Codex with the broader reasoning and professional knowledge capabilities of GPT-5.2.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.75e-6,"output_cost_per_token":0.000014,"cache_read_input_token_cost":1.75e-7,"input_cost_per_token_priority":3.5e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.000028,"cache_read_input_token_cost_priority":3.5e-7},"list_pricing":{"input_cost_per_token":1.75e-6,"output_cost_per_token":0.000014,"cache_read_input_token_cost":1.75e-7,"input_cost_per_token_priority":3.5e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.000028,"cache_read_input_token_cost_priority":3.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"openai/gpt-5.3-codex","object":"model","created":1771959164,"owned_by":"openai","model_name":"gpt-5.3-codex","context_length":400000,"max_input_tokens":272000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5.3-Codex is OpenAI’s most advanced agentic coding model, combining the frontier software engineering performance of GPT-5.2-Codex with the broader reasoning and professional knowledge capabilities of GPT-5.2.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.75e-6,"output_cost_per_token":0.000014,"cache_read_input_token_cost":1.75e-7,"input_cost_per_token_priority":3.5e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"output_cost_per_token_priority":0.000028,"cache_read_input_token_cost_priority":3.5e-7},"list_pricing":{"input_cost_per_token":1.75e-6,"output_cost_per_token":0.000014,"cache_read_input_token_cost":1.75e-7,"input_cost_per_token_priority":3.5e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"output_cost_per_token_priority":0.000028,"cache_read_input_token_cost_priority":3.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":2},{"id":"gpt-5.4-mini","object":"model","created":1784832896,"owned_by":"openai","mode":"chat","context_length":400000,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":7.5e-7,"output_cost_per_token":4.5e-6,"input_dbu_cost_per_token":0.000010714,"output_dbu_cost_per_token":0.000064286,"cache_read_input_token_cost":7.5e-8,"input_cost_per_token_priority":1.5e-6,"output_cost_per_token_priority":9e-6,"cache_creation_input_token_cost":7.5e-7,"cache_creation_input_token_cost_priority":1.5e-6},"pricing_endpoint":"databricks/databricks-gpt-5-4-mini","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"azure/gpt-5.4-mini@eu","object":"model","created":1784832896,"owned_by":"azure","model_name":"gpt-5.4-mini","context_length":400000,"max_input_tokens":272000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":8.25e-7,"output_cost_per_token":4.950000000000001e-6,"input_cost_per_token_flex":4.125e-7,"output_cost_per_token_flex":2.4750000000000004e-6,"cache_read_input_token_cost":8.25e-8,"input_cost_per_token_priority":1.65e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":9.900000000000002e-6,"cache_read_input_token_cost_flex":4.125e-8,"cache_read_input_token_cost_priority":1.65e-7},"list_pricing":{"input_cost_per_token":8.25e-7,"output_cost_per_token":4.950000000000001e-6,"input_cost_per_token_flex":4.125e-7,"output_cost_per_token_flex":2.4750000000000004e-6,"cache_read_input_token_cost":8.25e-8,"input_cost_per_token_priority":1.65e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":9.900000000000002e-6,"cache_read_input_token_cost_flex":4.125e-8,"cache_read_input_token_cost_priority":1.65e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"azure/gpt-5.4-mini","object":"model","created":1784832896,"owned_by":"azure","model_name":"gpt-5.4-mini","context_length":400000,"max_input_tokens":272000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":7.5e-7,"output_cost_per_token":4.5e-6,"input_cost_per_token_flex":3.75e-7,"output_cost_per_token_flex":2.25e-6,"cache_read_input_token_cost":7.5e-8,"input_cost_per_token_priority":1.5e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":9e-6,"cache_read_input_token_cost_flex":3.75e-8,"cache_read_input_token_cost_priority":1.5e-7},"list_pricing":{"input_cost_per_token":7.5e-7,"output_cost_per_token":4.5e-6,"input_cost_per_token_flex":3.75e-7,"output_cost_per_token_flex":2.25e-6,"cache_read_input_token_cost":7.5e-8,"input_cost_per_token_priority":1.5e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":9e-6,"cache_read_input_token_cost_flex":3.75e-8,"cache_read_input_token_cost_priority":1.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"azure/gpt-5.4-mini@us","object":"model","created":1784832896,"owned_by":"azure","model_name":"gpt-5.4-mini","context_length":400000,"max_input_tokens":272000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":8.25e-7,"output_cost_per_token":4.950000000000001e-6,"input_cost_per_token_flex":4.125e-7,"output_cost_per_token_flex":2.4750000000000004e-6,"cache_read_input_token_cost":8.25e-8,"input_cost_per_token_priority":1.65e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":9.900000000000002e-6,"cache_read_input_token_cost_flex":4.125e-8,"cache_read_input_token_cost_priority":1.65e-7},"list_pricing":{"input_cost_per_token":8.25e-7,"output_cost_per_token":4.950000000000001e-6,"input_cost_per_token_flex":4.125e-7,"output_cost_per_token_flex":2.4750000000000004e-6,"cache_read_input_token_cost":8.25e-8,"input_cost_per_token_priority":1.65e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":9.900000000000002e-6,"cache_read_input_token_cost_flex":4.125e-8,"cache_read_input_token_cost_priority":1.65e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"databricks/databricks-gpt-5-4-mini@eu","object":"model","created":1781107854,"owned_by":"databricks","model_name":"databricks-gpt-5-4-mini","context_length":400000,"max_input_tokens":272000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5.4 Mini is a cost-optimized large language model developed by OpenAI. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["file","image","text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":7.5e-7,"output_cost_per_token":4.5e-6,"input_dbu_cost_per_token":0.000010714,"output_dbu_cost_per_token":0.000064286,"cache_read_input_token_cost":7.5e-8,"input_cost_per_token_priority":1.5e-6,"output_cost_per_token_priority":9e-6,"cache_creation_input_token_cost":7.5e-7,"cache_creation_input_token_cost_priority":1.5e-6},"list_pricing":{"input_cost_per_token":7.5e-7,"output_cost_per_token":4.5e-6,"input_dbu_cost_per_token":0.000010714,"output_dbu_cost_per_token":0.000064286,"cache_read_input_token_cost":7.5e-8,"input_cost_per_token_priority":1.5e-6,"output_cost_per_token_priority":9e-6,"cache_creation_input_token_cost":7.5e-7,"cache_creation_input_token_cost_priority":1.5e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"databricks/databricks-gpt-5-4-mini","object":"model","created":1781107854,"owned_by":"databricks","model_name":"databricks-gpt-5-4-mini","context_length":400000,"max_input_tokens":272000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5.4 Mini is a cost-optimized large language model developed by OpenAI. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["file","image","text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":7.5e-7,"output_cost_per_token":4.5e-6,"input_dbu_cost_per_token":0.000010714,"output_dbu_cost_per_token":0.000064286,"cache_read_input_token_cost":7.5e-8,"input_cost_per_token_priority":1.5e-6,"output_cost_per_token_priority":9e-6,"cache_creation_input_token_cost":7.5e-7,"cache_creation_input_token_cost_priority":1.5e-6},"list_pricing":{"input_cost_per_token":7.5e-7,"output_cost_per_token":4.5e-6,"input_dbu_cost_per_token":0.000010714,"output_dbu_cost_per_token":0.000064286,"cache_read_input_token_cost":7.5e-8,"input_cost_per_token_priority":1.5e-6,"output_cost_per_token_priority":9e-6,"cache_creation_input_token_cost":7.5e-7,"cache_creation_input_token_cost_priority":1.5e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"openai/gpt-5.4-mini","object":"model","created":1773748178,"owned_by":"openai","model_name":"gpt-5.4-mini","context_length":400000,"max_input_tokens":272000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads.","source":null,"capabilities":{"input_modalities":["file","image","text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":7.5e-7,"output_cost_per_token":4.5e-6,"input_cost_per_token_flex":3.75e-7,"output_cost_per_token_flex":2.25e-6,"cache_read_input_token_cost":7.5e-8,"input_cost_per_token_batches":3.75e-7,"input_cost_per_token_priority":1.5e-6,"output_cost_per_token_batches":2.25e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"output_cost_per_token_priority":9e-6,"cache_read_input_token_cost_flex":3.75e-8,"cache_read_input_token_cost_batches":3.75e-8,"cache_read_input_token_cost_priority":1.5e-7},"list_pricing":{"input_cost_per_token":7.5e-7,"output_cost_per_token":4.5e-6,"input_cost_per_token_flex":3.75e-7,"output_cost_per_token_flex":2.25e-6,"cache_read_input_token_cost":7.5e-8,"input_cost_per_token_batches":3.75e-7,"input_cost_per_token_priority":1.5e-6,"output_cost_per_token_batches":2.25e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"output_cost_per_token_priority":9e-6,"cache_read_input_token_cost_flex":3.75e-8,"cache_read_input_token_cost_batches":3.75e-8,"cache_read_input_token_cost_priority":1.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":6},{"id":"gpt-5.4-nano","object":"model","created":1784832896,"owned_by":"openai","mode":"chat","context_length":400000,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":1.25e-6,"input_dbu_cost_per_token":2.857e-6,"output_dbu_cost_per_token":0.000017857,"cache_read_input_token_cost":2e-8,"cache_creation_input_token_cost":2e-7},"pricing_endpoint":"databricks/databricks-gpt-5-4-nano","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"azure/gpt-5.4-nano","object":"model","created":1784832896,"owned_by":"azure","model_name":"gpt-5.4-nano","context_length":400000,"max_input_tokens":272000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":1.25e-6,"input_cost_per_token_flex":1e-7,"output_cost_per_token_flex":6.25e-7,"cache_read_input_token_cost":2e-8,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"cache_read_input_token_cost_flex":1e-8},"list_pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":1.25e-6,"input_cost_per_token_flex":1e-7,"output_cost_per_token_flex":6.25e-7,"cache_read_input_token_cost":2e-8,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"cache_read_input_token_cost_flex":1e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"azure/gpt-5.4-nano@us","object":"model","created":1784832896,"owned_by":"azure","model_name":"gpt-5.4-nano","context_length":400000,"max_input_tokens":272000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2.2e-7,"output_cost_per_token":1.3750000000000002e-6,"input_cost_per_token_flex":1.1e-7,"output_cost_per_token_flex":6.875000000000001e-7,"cache_read_input_token_cost":2.2000000000000002e-8,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"cache_read_input_token_cost_flex":1.1000000000000001e-8},"list_pricing":{"input_cost_per_token":2.2e-7,"output_cost_per_token":1.3750000000000002e-6,"input_cost_per_token_flex":1.1e-7,"output_cost_per_token_flex":6.875000000000001e-7,"cache_read_input_token_cost":2.2000000000000002e-8,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"cache_read_input_token_cost_flex":1.1000000000000001e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"databricks/databricks-gpt-5-4-nano@eu","object":"model","created":1781107944,"owned_by":"databricks","model_name":"databricks-gpt-5-4-nano","context_length":400000,"max_input_tokens":272000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5.4 Nano is a lightweight, cost-optimized large language model developed by OpenAI. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["file","image","text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":1.25e-6,"input_dbu_cost_per_token":2.857e-6,"output_dbu_cost_per_token":0.000017857,"cache_read_input_token_cost":2e-8,"cache_creation_input_token_cost":2e-7},"list_pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":1.25e-6,"input_dbu_cost_per_token":2.857e-6,"output_dbu_cost_per_token":0.000017857,"cache_read_input_token_cost":2e-8,"cache_creation_input_token_cost":2e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"databricks/databricks-gpt-5-4-nano","object":"model","created":1781107944,"owned_by":"databricks","model_name":"databricks-gpt-5-4-nano","context_length":400000,"max_input_tokens":272000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5.4 Nano is a lightweight, cost-optimized large language model developed by OpenAI. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["file","image","text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":1.25e-6,"input_dbu_cost_per_token":2.857e-6,"output_dbu_cost_per_token":0.000017857,"cache_read_input_token_cost":2e-8,"cache_creation_input_token_cost":2e-7},"list_pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":1.25e-6,"input_dbu_cost_per_token":2.857e-6,"output_dbu_cost_per_token":0.000017857,"cache_read_input_token_cost":2e-8,"cache_creation_input_token_cost":2e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"openai/gpt-5.4-nano","object":"model","created":1773748187,"owned_by":"openai","model_name":"gpt-5.4-nano","context_length":400000,"max_input_tokens":272000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks.","source":null,"capabilities":{"input_modalities":["file","image","text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":1.25e-6,"input_cost_per_token_flex":1e-7,"output_cost_per_token_flex":6.25e-7,"cache_read_input_token_cost":2e-8,"input_cost_per_token_batches":1e-7,"output_cost_per_token_batches":6.25e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_read_input_token_cost_flex":1e-8,"cache_read_input_token_cost_batches":1e-8},"list_pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":1.25e-6,"input_cost_per_token_flex":1e-7,"output_cost_per_token_flex":6.25e-7,"cache_read_input_token_cost":2e-8,"input_cost_per_token_batches":1e-7,"output_cost_per_token_batches":6.25e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_read_input_token_cost_flex":1e-8,"cache_read_input_token_cost_batches":1e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":5},{"id":"~gpt-mini-latest","object":"model","created":1784832896,"owned_by":"openai","mode":"chat","context_length":400000,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":7.5e-7,"output_cost_per_token":4.5e-6,"input_dbu_cost_per_token":0.000010714,"output_dbu_cost_per_token":0.000064286,"cache_read_input_token_cost":7.5e-8,"input_cost_per_token_priority":1.5e-6,"output_cost_per_token_priority":9e-6,"cache_creation_input_token_cost":7.5e-7,"cache_creation_input_token_cost_priority":1.5e-6},"pricing_endpoint":"databricks/databricks-gpt-5-4-mini","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":"gpt-5.4-mini","endpoints":[{"id":"azure/gpt-5.4-mini@eu","object":"model","created":1784832896,"owned_by":"azure","model_name":"gpt-5.4-mini","context_length":400000,"max_input_tokens":272000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":8.25e-7,"output_cost_per_token":4.950000000000001e-6,"input_cost_per_token_flex":4.125e-7,"output_cost_per_token_flex":2.4750000000000004e-6,"cache_read_input_token_cost":8.25e-8,"input_cost_per_token_priority":1.65e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":9.900000000000002e-6,"cache_read_input_token_cost_flex":4.125e-8,"cache_read_input_token_cost_priority":1.65e-7},"list_pricing":{"input_cost_per_token":8.25e-7,"output_cost_per_token":4.950000000000001e-6,"input_cost_per_token_flex":4.125e-7,"output_cost_per_token_flex":2.4750000000000004e-6,"cache_read_input_token_cost":8.25e-8,"input_cost_per_token_priority":1.65e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":9.900000000000002e-6,"cache_read_input_token_cost_flex":4.125e-8,"cache_read_input_token_cost_priority":1.65e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"azure/gpt-5.4-mini","object":"model","created":1784832896,"owned_by":"azure","model_name":"gpt-5.4-mini","context_length":400000,"max_input_tokens":272000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":7.5e-7,"output_cost_per_token":4.5e-6,"input_cost_per_token_flex":3.75e-7,"output_cost_per_token_flex":2.25e-6,"cache_read_input_token_cost":7.5e-8,"input_cost_per_token_priority":1.5e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":9e-6,"cache_read_input_token_cost_flex":3.75e-8,"cache_read_input_token_cost_priority":1.5e-7},"list_pricing":{"input_cost_per_token":7.5e-7,"output_cost_per_token":4.5e-6,"input_cost_per_token_flex":3.75e-7,"output_cost_per_token_flex":2.25e-6,"cache_read_input_token_cost":7.5e-8,"input_cost_per_token_priority":1.5e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":9e-6,"cache_read_input_token_cost_flex":3.75e-8,"cache_read_input_token_cost_priority":1.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"azure/gpt-5.4-mini@us","object":"model","created":1784832896,"owned_by":"azure","model_name":"gpt-5.4-mini","context_length":400000,"max_input_tokens":272000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":8.25e-7,"output_cost_per_token":4.950000000000001e-6,"input_cost_per_token_flex":4.125e-7,"output_cost_per_token_flex":2.4750000000000004e-6,"cache_read_input_token_cost":8.25e-8,"input_cost_per_token_priority":1.65e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":9.900000000000002e-6,"cache_read_input_token_cost_flex":4.125e-8,"cache_read_input_token_cost_priority":1.65e-7},"list_pricing":{"input_cost_per_token":8.25e-7,"output_cost_per_token":4.950000000000001e-6,"input_cost_per_token_flex":4.125e-7,"output_cost_per_token_flex":2.4750000000000004e-6,"cache_read_input_token_cost":8.25e-8,"input_cost_per_token_priority":1.65e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":9.900000000000002e-6,"cache_read_input_token_cost_flex":4.125e-8,"cache_read_input_token_cost_priority":1.65e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"databricks/databricks-gpt-5-4-mini@eu","object":"model","created":1781107854,"owned_by":"databricks","model_name":"databricks-gpt-5-4-mini","context_length":400000,"max_input_tokens":272000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5.4 Mini is a cost-optimized large language model developed by OpenAI. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["file","image","text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":7.5e-7,"output_cost_per_token":4.5e-6,"input_dbu_cost_per_token":0.000010714,"output_dbu_cost_per_token":0.000064286,"cache_read_input_token_cost":7.5e-8,"input_cost_per_token_priority":1.5e-6,"output_cost_per_token_priority":9e-6,"cache_creation_input_token_cost":7.5e-7,"cache_creation_input_token_cost_priority":1.5e-6},"list_pricing":{"input_cost_per_token":7.5e-7,"output_cost_per_token":4.5e-6,"input_dbu_cost_per_token":0.000010714,"output_dbu_cost_per_token":0.000064286,"cache_read_input_token_cost":7.5e-8,"input_cost_per_token_priority":1.5e-6,"output_cost_per_token_priority":9e-6,"cache_creation_input_token_cost":7.5e-7,"cache_creation_input_token_cost_priority":1.5e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"databricks/databricks-gpt-5-4-mini","object":"model","created":1781107854,"owned_by":"databricks","model_name":"databricks-gpt-5-4-mini","context_length":400000,"max_input_tokens":272000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5.4 Mini is a cost-optimized large language model developed by OpenAI. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["file","image","text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":7.5e-7,"output_cost_per_token":4.5e-6,"input_dbu_cost_per_token":0.000010714,"output_dbu_cost_per_token":0.000064286,"cache_read_input_token_cost":7.5e-8,"input_cost_per_token_priority":1.5e-6,"output_cost_per_token_priority":9e-6,"cache_creation_input_token_cost":7.5e-7,"cache_creation_input_token_cost_priority":1.5e-6},"list_pricing":{"input_cost_per_token":7.5e-7,"output_cost_per_token":4.5e-6,"input_dbu_cost_per_token":0.000010714,"output_dbu_cost_per_token":0.000064286,"cache_read_input_token_cost":7.5e-8,"input_cost_per_token_priority":1.5e-6,"output_cost_per_token_priority":9e-6,"cache_creation_input_token_cost":7.5e-7,"cache_creation_input_token_cost_priority":1.5e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"openai/gpt-5.4-mini","object":"model","created":1773748178,"owned_by":"openai","model_name":"gpt-5.4-mini","context_length":400000,"max_input_tokens":272000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads.","source":null,"capabilities":{"input_modalities":["file","image","text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":7.5e-7,"output_cost_per_token":4.5e-6,"input_cost_per_token_flex":3.75e-7,"output_cost_per_token_flex":2.25e-6,"cache_read_input_token_cost":7.5e-8,"input_cost_per_token_batches":3.75e-7,"input_cost_per_token_priority":1.5e-6,"output_cost_per_token_batches":2.25e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"output_cost_per_token_priority":9e-6,"cache_read_input_token_cost_flex":3.75e-8,"cache_read_input_token_cost_batches":3.75e-8,"cache_read_input_token_cost_priority":1.5e-7},"list_pricing":{"input_cost_per_token":7.5e-7,"output_cost_per_token":4.5e-6,"input_cost_per_token_flex":3.75e-7,"output_cost_per_token_flex":2.25e-6,"cache_read_input_token_cost":7.5e-8,"input_cost_per_token_batches":3.75e-7,"input_cost_per_token_priority":1.5e-6,"output_cost_per_token_batches":2.25e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"output_cost_per_token_priority":9e-6,"cache_read_input_token_cost_flex":3.75e-8,"cache_read_input_token_cost_batches":3.75e-8,"cache_read_input_token_cost_priority":1.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":6},{"id":"ling-3.0-flash","object":"model","created":1784818580,"owned_by":"","mode":"chat","context_length":131072,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6.000000000000001e-8,"output_cost_per_token":1.8e-7,"cache_read_input_token_cost":1.2000000000000002e-8},"pricing_endpoint":"deepinfra/inclusionAI/Ling-3.0-flash","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"deepinfra/inclusionAI/Ling-3.0-flash","object":"model","created":1784818580,"owned_by":"deepinfra","model_name":"inclusionAI/Ling-3.0-flash","context_length":131072,"max_input_tokens":131072,"max_output_tokens":32768,"quantization":"fp4","retirement_date":null,"description":"*Ling-3.0-flash* is a *124B-parameter Mixture-of-Experts (MoE) model*, with approximately *5.1B parameters activated per token*.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6.000000000000001e-8,"output_cost_per_token":1.8e-7,"cache_read_input_token_cost":1.2000000000000002e-8},"list_pricing":{"input_cost_per_token":6.000000000000001e-8,"output_cost_per_token":1.8e-7,"cache_read_input_token_cost":1.2000000000000002e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"gpt-5","object":"model","created":1784721580,"owned_by":"openai","mode":"chat","context_length":400000,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":0.00001,"input_dbu_cost_per_token":0.000017857,"output_dbu_cost_per_token":0.000142857,"cache_read_input_token_cost":1.25e-7,"input_cost_per_token_priority":2.5e-6,"output_cost_per_token_priority":0.00002,"cache_creation_input_token_cost":1.25e-6,"cache_creation_input_token_cost_priority":2.5e-6},"pricing_endpoint":"databricks/databricks-gpt-5","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"azure/gpt-5@eu","object":"model","created":1784721580,"owned_by":"azure","model_name":"gpt-5","context_length":400000,"max_input_tokens":272000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.3750000000000002e-6,"output_cost_per_token":0.000011000000000000001,"cache_read_input_token_cost":1.375e-7,"input_cost_per_token_priority":2.7500000000000004e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.000022000000000000003,"cache_read_input_token_cost_priority":2.75e-7},"list_pricing":{"input_cost_per_token":1.3750000000000002e-6,"output_cost_per_token":0.000011000000000000001,"cache_read_input_token_cost":1.375e-7,"input_cost_per_token_priority":2.7500000000000004e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.000022000000000000003,"cache_read_input_token_cost_priority":2.75e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"azure/gpt-5","object":"model","created":1784721580,"owned_by":"azure","model_name":"gpt-5","context_length":400000,"max_input_tokens":272000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":0.00001,"cache_read_input_token_cost":1.25e-7,"input_cost_per_token_priority":2.5e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.00002,"cache_read_input_token_cost_priority":2.5e-7},"list_pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":0.00001,"cache_read_input_token_cost":1.25e-7,"input_cost_per_token_priority":2.5e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.00002,"cache_read_input_token_cost_priority":2.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"azure/gpt-5@us","object":"model","created":1784721580,"owned_by":"azure","model_name":"gpt-5","context_length":400000,"max_input_tokens":272000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.3750000000000002e-6,"output_cost_per_token":0.000011000000000000001,"cache_read_input_token_cost":1.375e-7,"input_cost_per_token_priority":2.7500000000000004e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.000022000000000000003,"cache_read_input_token_cost_priority":2.75e-7},"list_pricing":{"input_cost_per_token":1.3750000000000002e-6,"output_cost_per_token":0.000011000000000000001,"cache_read_input_token_cost":1.375e-7,"input_cost_per_token_priority":2.7500000000000004e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.000022000000000000003,"cache_read_input_token_cost_priority":2.75e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"databricks/databricks-gpt-5@eu","object":"model","created":1769507058,"owned_by":"databricks","model_name":"databricks-gpt-5","context_length":400000,"max_input_tokens":272000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5 is a state-of-the-art, general purpose large language model and reasoning model built and trained by OpenAI. It supports multimodal inputs and features a 128K token context window. The model is built for coding, chat, reasoning and agent-driven tasks. This endpoint is hosted by Databricks.","source":"https://www.databricks.com/product/pricing/proprietary-foundation-model-serving","capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":0.00001,"input_dbu_cost_per_token":0.000017857,"output_dbu_cost_per_token":0.000142857,"cache_read_input_token_cost":1.25e-7,"input_cost_per_token_priority":2.5e-6,"output_cost_per_token_priority":0.00002,"cache_creation_input_token_cost":1.25e-6,"cache_creation_input_token_cost_priority":2.5e-6},"list_pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":0.00001,"input_dbu_cost_per_token":0.000017857,"output_dbu_cost_per_token":0.000142857,"cache_read_input_token_cost":1.25e-7,"input_cost_per_token_priority":2.5e-6,"output_cost_per_token_priority":0.00002,"cache_creation_input_token_cost":1.25e-6,"cache_creation_input_token_cost_priority":2.5e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"databricks/databricks-gpt-5","object":"model","created":1769507058,"owned_by":"databricks","model_name":"databricks-gpt-5","context_length":400000,"max_input_tokens":272000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5 is a state-of-the-art, general purpose large language model and reasoning model built and trained by OpenAI. It supports multimodal inputs and features a 128K token context window. The model is built for coding, chat, reasoning and agent-driven tasks. This endpoint is hosted by Databricks.","source":"https://www.databricks.com/product/pricing/proprietary-foundation-model-serving","capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":0.00001,"input_dbu_cost_per_token":0.000017857,"output_dbu_cost_per_token":0.000142857,"cache_read_input_token_cost":1.25e-7,"input_cost_per_token_priority":2.5e-6,"output_cost_per_token_priority":0.00002,"cache_creation_input_token_cost":1.25e-6,"cache_creation_input_token_cost_priority":2.5e-6},"list_pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":0.00001,"input_dbu_cost_per_token":0.000017857,"output_dbu_cost_per_token":0.000142857,"cache_read_input_token_cost":1.25e-7,"input_cost_per_token_priority":2.5e-6,"output_cost_per_token_priority":0.00002,"cache_creation_input_token_cost":1.25e-6,"cache_creation_input_token_cost_priority":2.5e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"openai/gpt-5","object":"model","created":1754587413,"owned_by":"openai","model_name":"gpt-5","context_length":400000,"max_input_tokens":272000,"max_output_tokens":128000,"quantization":null,"retirement_date":"2026-12-11","description":"GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":0.00001,"input_cost_per_token_flex":6.25e-7,"output_cost_per_token_flex":5e-6,"cache_read_input_token_cost":1.25e-7,"input_cost_per_token_batches":6.25e-7,"input_cost_per_token_priority":2.5e-6,"output_cost_per_token_batches":5e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"output_cost_per_token_priority":0.00002,"cache_read_input_token_cost_flex":6.25e-8,"cache_read_input_token_cost_batches":6.25e-8,"cache_read_input_token_cost_priority":2.5e-7},"list_pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":0.00001,"input_cost_per_token_flex":6.25e-7,"output_cost_per_token_flex":5e-6,"cache_read_input_token_cost":1.25e-7,"input_cost_per_token_batches":6.25e-7,"input_cost_per_token_priority":2.5e-6,"output_cost_per_token_batches":5e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"output_cost_per_token_priority":0.00002,"cache_read_input_token_cost_flex":6.25e-8,"cache_read_input_token_cost_batches":6.25e-8,"cache_read_input_token_cost_priority":2.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":6},{"id":"gpt-5-mini","object":"model","created":1784721580,"owned_by":"openai","mode":"chat","context_length":400000,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2.5e-7,"output_cost_per_token":2e-6,"input_dbu_cost_per_token":3.571e-6,"output_dbu_cost_per_token":0.000028571,"cache_read_input_token_cost":2.5e-8,"input_cost_per_token_priority":4.5e-7,"output_cost_per_token_priority":3.6e-6,"cache_creation_input_token_cost":2.5e-7,"cache_creation_input_token_cost_priority":4.5e-7},"pricing_endpoint":"databricks/databricks-gpt-5-mini","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"azure/gpt-5-mini@eu","object":"model","created":1784721580,"owned_by":"azure","model_name":"gpt-5-mini","context_length":400000,"max_input_tokens":272000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2.75e-7,"output_cost_per_token":2.2e-6,"cache_read_input_token_cost":2.75e-8,"input_cost_per_token_priority":4.95e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":3.96e-6,"cache_read_input_token_cost_priority":4.9500000000000006e-8},"list_pricing":{"input_cost_per_token":2.75e-7,"output_cost_per_token":2.2e-6,"cache_read_input_token_cost":2.75e-8,"input_cost_per_token_priority":4.95e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":3.96e-6,"cache_read_input_token_cost_priority":4.9500000000000006e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"azure/gpt-5-mini","object":"model","created":1784721580,"owned_by":"azure","model_name":"gpt-5-mini","context_length":400000,"max_input_tokens":272000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2.5e-7,"output_cost_per_token":2e-6,"cache_read_input_token_cost":2.5e-8,"input_cost_per_token_priority":4.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":3.6e-6,"cache_read_input_token_cost_priority":4.5e-8},"list_pricing":{"input_cost_per_token":2.5e-7,"output_cost_per_token":2e-6,"cache_read_input_token_cost":2.5e-8,"input_cost_per_token_priority":4.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":3.6e-6,"cache_read_input_token_cost_priority":4.5e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"azure/gpt-5-mini@us","object":"model","created":1784721580,"owned_by":"azure","model_name":"gpt-5-mini","context_length":400000,"max_input_tokens":272000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2.75e-7,"output_cost_per_token":2.2e-6,"cache_read_input_token_cost":2.75e-8,"input_cost_per_token_priority":4.95e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":3.96e-6,"cache_read_input_token_cost_priority":4.9500000000000006e-8},"list_pricing":{"input_cost_per_token":2.75e-7,"output_cost_per_token":2.2e-6,"cache_read_input_token_cost":2.75e-8,"input_cost_per_token_priority":4.95e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":3.96e-6,"cache_read_input_token_cost_priority":4.9500000000000006e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"databricks/databricks-gpt-5-mini@eu","object":"model","created":1769507058,"owned_by":"databricks","model_name":"databricks-gpt-5-mini","context_length":400000,"max_input_tokens":272000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5 mini is a state-of-the-art, general purpose large language model and reasoning model built and trained by OpenAI. It supports multimodal inputs and features a 128K token context window. The model is cost-optimized for reasoning and chat workloads and excels at well-defined tasks that require reliable reasoning, precise language, and rapid output for text and images. This endpoint is hosted by Databricks.","source":"https://www.databricks.com/product/pricing/proprietary-foundation-model-serving","capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.5e-7,"output_cost_per_token":2e-6,"input_dbu_cost_per_token":3.571e-6,"output_dbu_cost_per_token":0.000028571,"cache_read_input_token_cost":2.5e-8,"input_cost_per_token_priority":4.5e-7,"output_cost_per_token_priority":3.6e-6,"cache_creation_input_token_cost":2.5e-7,"cache_creation_input_token_cost_priority":4.5e-7},"list_pricing":{"input_cost_per_token":2.5e-7,"output_cost_per_token":2e-6,"input_dbu_cost_per_token":3.571e-6,"output_dbu_cost_per_token":0.000028571,"cache_read_input_token_cost":2.5e-8,"input_cost_per_token_priority":4.5e-7,"output_cost_per_token_priority":3.6e-6,"cache_creation_input_token_cost":2.5e-7,"cache_creation_input_token_cost_priority":4.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"databricks/databricks-gpt-5-mini","object":"model","created":1769507058,"owned_by":"databricks","model_name":"databricks-gpt-5-mini","context_length":400000,"max_input_tokens":272000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5 mini is a state-of-the-art, general purpose large language model and reasoning model built and trained by OpenAI. It supports multimodal inputs and features a 128K token context window. The model is cost-optimized for reasoning and chat workloads and excels at well-defined tasks that require reliable reasoning, precise language, and rapid output for text and images. This endpoint is hosted by Databricks.","source":"https://www.databricks.com/product/pricing/proprietary-foundation-model-serving","capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.5e-7,"output_cost_per_token":2e-6,"input_dbu_cost_per_token":3.571e-6,"output_dbu_cost_per_token":0.000028571,"cache_read_input_token_cost":2.5e-8,"input_cost_per_token_priority":4.5e-7,"output_cost_per_token_priority":3.6e-6,"cache_creation_input_token_cost":2.5e-7,"cache_creation_input_token_cost_priority":4.5e-7},"list_pricing":{"input_cost_per_token":2.5e-7,"output_cost_per_token":2e-6,"input_dbu_cost_per_token":3.571e-6,"output_dbu_cost_per_token":0.000028571,"cache_read_input_token_cost":2.5e-8,"input_cost_per_token_priority":4.5e-7,"output_cost_per_token_priority":3.6e-6,"cache_creation_input_token_cost":2.5e-7,"cache_creation_input_token_cost_priority":4.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"openai/gpt-5-mini","object":"model","created":1754587407,"owned_by":"openai","model_name":"gpt-5-mini","context_length":400000,"max_input_tokens":272000,"max_output_tokens":128000,"quantization":null,"retirement_date":"2026-12-11","description":"GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2.5e-7,"output_cost_per_token":2e-6,"input_cost_per_token_flex":1.25e-7,"output_cost_per_token_flex":1e-6,"cache_read_input_token_cost":2.5e-8,"input_cost_per_token_batches":1.25e-7,"input_cost_per_token_priority":4.5e-7,"output_cost_per_token_batches":1e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"output_cost_per_token_priority":3.6e-6,"cache_read_input_token_cost_flex":1.25e-8,"cache_read_input_token_cost_batches":1.25e-8,"cache_read_input_token_cost_priority":4.5e-8},"list_pricing":{"input_cost_per_token":2.5e-7,"output_cost_per_token":2e-6,"input_cost_per_token_flex":1.25e-7,"output_cost_per_token_flex":1e-6,"cache_read_input_token_cost":2.5e-8,"input_cost_per_token_batches":1.25e-7,"input_cost_per_token_priority":4.5e-7,"output_cost_per_token_batches":1e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"output_cost_per_token_priority":3.6e-6,"cache_read_input_token_cost_flex":1.25e-8,"cache_read_input_token_cost_batches":1.25e-8,"cache_read_input_token_cost_priority":4.5e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":6},{"id":"gpt-5-nano","object":"model","created":1784721580,"owned_by":"openai","mode":"chat","context_length":400000,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":5e-8,"output_cost_per_token":4e-7,"input_dbu_cost_per_token":7.14e-7,"output_dbu_cost_per_token":5.714000000000001e-6,"cache_read_input_token_cost":5e-9,"cache_creation_input_token_cost":5e-8},"pricing_endpoint":"databricks/databricks-gpt-5-nano","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"azure/gpt-5-nano@eu","object":"model","created":1784721580,"owned_by":"azure","model_name":"gpt-5-nano","context_length":400000,"max_input_tokens":272000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":5.5e-8,"output_cost_per_token":4.4e-7,"cache_read_input_token_cost":5.5000000000000004e-9,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014}},"list_pricing":{"input_cost_per_token":5.5e-8,"output_cost_per_token":4.4e-7,"cache_read_input_token_cost":5.5000000000000004e-9,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014}},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"azure/gpt-5-nano","object":"model","created":1784721580,"owned_by":"azure","model_name":"gpt-5-nano","context_length":400000,"max_input_tokens":272000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":5e-8,"output_cost_per_token":4e-7,"cache_read_input_token_cost":5e-9,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014}},"list_pricing":{"input_cost_per_token":5e-8,"output_cost_per_token":4e-7,"cache_read_input_token_cost":5e-9,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014}},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"azure/gpt-5-nano@us","object":"model","created":1784721580,"owned_by":"azure","model_name":"gpt-5-nano","context_length":400000,"max_input_tokens":272000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":5.5e-8,"output_cost_per_token":4.4e-7,"cache_read_input_token_cost":5.5000000000000004e-9,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014}},"list_pricing":{"input_cost_per_token":5.5e-8,"output_cost_per_token":4.4e-7,"cache_read_input_token_cost":5.5000000000000004e-9,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014}},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"databricks/databricks-gpt-5-nano@eu","object":"model","created":1769507058,"owned_by":"databricks","model_name":"databricks-gpt-5-nano","context_length":400000,"max_input_tokens":272000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5 nano is a state-of-the-art, general purpose large language model and reasoning model built and trained by OpenAI. It supports multimodal inputs and features a 128K token context window. The model excels at high-throughput tasks like simple instruction-following or classification for routine business processes or mobile applications. This endpoint is hosted by Databricks.","source":"https://www.databricks.com/product/pricing/proprietary-foundation-model-serving","capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-8,"output_cost_per_token":4e-7,"input_dbu_cost_per_token":7.14e-7,"output_dbu_cost_per_token":5.714000000000001e-6,"cache_read_input_token_cost":5e-9,"cache_creation_input_token_cost":5e-8},"list_pricing":{"input_cost_per_token":5e-8,"output_cost_per_token":4e-7,"input_dbu_cost_per_token":7.14e-7,"output_dbu_cost_per_token":5.714000000000001e-6,"cache_read_input_token_cost":5e-9,"cache_creation_input_token_cost":5e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"databricks/databricks-gpt-5-nano","object":"model","created":1769507058,"owned_by":"databricks","model_name":"databricks-gpt-5-nano","context_length":400000,"max_input_tokens":272000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5 nano is a state-of-the-art, general purpose large language model and reasoning model built and trained by OpenAI. It supports multimodal inputs and features a 128K token context window. The model excels at high-throughput tasks like simple instruction-following or classification for routine business processes or mobile applications. This endpoint is hosted by Databricks.","source":"https://www.databricks.com/product/pricing/proprietary-foundation-model-serving","capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-8,"output_cost_per_token":4e-7,"input_dbu_cost_per_token":7.14e-7,"output_dbu_cost_per_token":5.714000000000001e-6,"cache_read_input_token_cost":5e-9,"cache_creation_input_token_cost":5e-8},"list_pricing":{"input_cost_per_token":5e-8,"output_cost_per_token":4e-7,"input_dbu_cost_per_token":7.14e-7,"output_dbu_cost_per_token":5.714000000000001e-6,"cache_read_input_token_cost":5e-9,"cache_creation_input_token_cost":5e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"openai/gpt-5-nano","object":"model","created":1754587402,"owned_by":"openai","model_name":"gpt-5-nano","context_length":400000,"max_input_tokens":272000,"max_output_tokens":128000,"quantization":null,"retirement_date":"2026-12-11","description":"GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":5e-8,"output_cost_per_token":4e-7,"input_cost_per_token_flex":2.5e-8,"output_cost_per_token_flex":2e-7,"cache_read_input_token_cost":5e-9,"input_cost_per_token_batches":2.5e-8,"output_cost_per_token_batches":2e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_read_input_token_cost_flex":2.5e-9,"cache_read_input_token_cost_batches":2.5e-9},"list_pricing":{"input_cost_per_token":5e-8,"output_cost_per_token":4e-7,"input_cost_per_token_flex":2.5e-8,"output_cost_per_token_flex":2e-7,"cache_read_input_token_cost":5e-9,"input_cost_per_token_batches":2.5e-8,"output_cost_per_token_batches":2e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_read_input_token_cost_flex":2.5e-9,"cache_read_input_token_cost_batches":2.5e-9},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":6},{"id":"gpt-5.1","object":"model","created":1784721580,"owned_by":"openai","mode":"chat","context_length":400000,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":0.00001,"input_dbu_cost_per_token":0.000017857,"output_dbu_cost_per_token":0.000142857,"cache_read_input_token_cost":1.25e-7,"input_cost_per_token_priority":2.5e-6,"output_cost_per_token_priority":0.00002,"cache_creation_input_token_cost":1.25e-6,"cache_creation_input_token_cost_priority":2.5e-6},"pricing_endpoint":"databricks/databricks-gpt-5-1","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"azure/gpt-5.1@eu","object":"model","created":1784721580,"owned_by":"azure","model_name":"gpt-5.1","context_length":400000,"max_input_tokens":272000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adherence, and a more natural conversational style compared to GPT-5.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.3750000000000002e-6,"output_cost_per_token":0.000011000000000000001,"cache_read_input_token_cost":1.375e-7,"input_cost_per_token_priority":2.7500000000000004e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.000022000000000000003,"cache_read_input_token_cost_priority":2.75e-7},"list_pricing":{"input_cost_per_token":1.3750000000000002e-6,"output_cost_per_token":0.000011000000000000001,"cache_read_input_token_cost":1.375e-7,"input_cost_per_token_priority":2.7500000000000004e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.000022000000000000003,"cache_read_input_token_cost_priority":2.75e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"azure/gpt-5.1","object":"model","created":1784721580,"owned_by":"azure","model_name":"gpt-5.1","context_length":400000,"max_input_tokens":272000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adherence, and a more natural conversational style compared to GPT-5.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":0.00001,"cache_read_input_token_cost":1.25e-7,"input_cost_per_token_priority":2.5e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.00002,"cache_read_input_token_cost_priority":2.5e-7},"list_pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":0.00001,"cache_read_input_token_cost":1.25e-7,"input_cost_per_token_priority":2.5e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.00002,"cache_read_input_token_cost_priority":2.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"azure/gpt-5.1@us","object":"model","created":1784721580,"owned_by":"azure","model_name":"gpt-5.1","context_length":400000,"max_input_tokens":272000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adherence, and a more natural conversational style compared to GPT-5.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.3750000000000002e-6,"output_cost_per_token":0.000011000000000000001,"cache_read_input_token_cost":1.375e-7,"input_cost_per_token_priority":2.7500000000000004e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.000022000000000000003,"cache_read_input_token_cost_priority":2.75e-7},"list_pricing":{"input_cost_per_token":1.3750000000000002e-6,"output_cost_per_token":0.000011000000000000001,"cache_read_input_token_cost":1.375e-7,"input_cost_per_token_priority":2.7500000000000004e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.000022000000000000003,"cache_read_input_token_cost_priority":2.75e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"databricks/databricks-gpt-5-1@eu","object":"model","created":1769507058,"owned_by":"databricks","model_name":"databricks-gpt-5-1","context_length":400000,"max_input_tokens":272000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5.1 is a general purpose large language model with reasoning capabilities developed by OpenAI. This model features both Instant and Thinking modes for fast conversation or deep reasoning, automatically adjusting for simple or complex tasks. The model excels at content creation, tutoring, technical support, and coding, with less reliance on strict prompt engineering than prior versions. It supports multimodal inputs and features a 128K token context window. This endpoint is hosted by Databricks.","source":"https://www.databricks.com/product/pricing/proprietary-foundation-model-serving","capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":0.00001,"input_dbu_cost_per_token":0.000017857,"output_dbu_cost_per_token":0.000142857,"cache_read_input_token_cost":1.25e-7,"input_cost_per_token_priority":2.5e-6,"output_cost_per_token_priority":0.00002,"cache_creation_input_token_cost":1.25e-6,"cache_creation_input_token_cost_priority":2.5e-6},"list_pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":0.00001,"input_dbu_cost_per_token":0.000017857,"output_dbu_cost_per_token":0.000142857,"cache_read_input_token_cost":1.25e-7,"input_cost_per_token_priority":2.5e-6,"output_cost_per_token_priority":0.00002,"cache_creation_input_token_cost":1.25e-6,"cache_creation_input_token_cost_priority":2.5e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"databricks/databricks-gpt-5-1","object":"model","created":1769507058,"owned_by":"databricks","model_name":"databricks-gpt-5-1","context_length":400000,"max_input_tokens":272000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5.1 is a general purpose large language model with reasoning capabilities developed by OpenAI. This model features both Instant and Thinking modes for fast conversation or deep reasoning, automatically adjusting for simple or complex tasks. The model excels at content creation, tutoring, technical support, and coding, with less reliance on strict prompt engineering than prior versions. It supports multimodal inputs and features a 128K token context window. This endpoint is hosted by Databricks.","source":"https://www.databricks.com/product/pricing/proprietary-foundation-model-serving","capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":0.00001,"input_dbu_cost_per_token":0.000017857,"output_dbu_cost_per_token":0.000142857,"cache_read_input_token_cost":1.25e-7,"input_cost_per_token_priority":2.5e-6,"output_cost_per_token_priority":0.00002,"cache_creation_input_token_cost":1.25e-6,"cache_creation_input_token_cost_priority":2.5e-6},"list_pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":0.00001,"input_dbu_cost_per_token":0.000017857,"output_dbu_cost_per_token":0.000142857,"cache_read_input_token_cost":1.25e-7,"input_cost_per_token_priority":2.5e-6,"output_cost_per_token_priority":0.00002,"cache_creation_input_token_cost":1.25e-6,"cache_creation_input_token_cost_priority":2.5e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"openai/gpt-5.1","object":"model","created":1763060305,"owned_by":"openai","model_name":"gpt-5.1","context_length":400000,"max_input_tokens":272000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adherence, and a more natural conversational style compared to GPT-5.","source":null,"capabilities":{"input_modalities":["image","text","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":0.00001,"input_cost_per_token_flex":6.25e-7,"output_cost_per_token_flex":5e-6,"cache_read_input_token_cost":1.25e-7,"input_cost_per_token_batches":6.25e-7,"input_cost_per_token_priority":2.5e-6,"output_cost_per_token_batches":5e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"output_cost_per_token_priority":0.00002,"cache_read_input_token_cost_flex":6.25e-8,"cache_read_input_token_cost_batches":6.25e-8,"cache_read_input_token_cost_priority":2.5e-7},"list_pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":0.00001,"input_cost_per_token_flex":6.25e-7,"output_cost_per_token_flex":5e-6,"cache_read_input_token_cost":1.25e-7,"input_cost_per_token_batches":6.25e-7,"input_cost_per_token_priority":2.5e-6,"output_cost_per_token_batches":5e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"output_cost_per_token_priority":0.00002,"cache_read_input_token_cost_flex":6.25e-8,"cache_read_input_token_cost_batches":6.25e-8,"cache_read_input_token_cost_priority":2.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":6},{"id":"gemini-3.5-flash-lite","object":"model","created":1784646726,"owned_by":"google","mode":"chat","context_length":1048576,"capabilities":{"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":2.5e-6,"input_cost_per_token_flex":1.5e-7,"input_cost_per_audio_token":3e-7,"input_cost_per_image_token":3e-7,"output_cost_per_token_flex":1.25e-6,"cache_read_input_token_cost":3e-8,"input_cost_per_token_priority":5.4e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":4.5e-6,"cache_creation_input_token_cost":8.33333333333333e-8,"output_cost_per_reasoning_token":2.5e-6,"cache_read_input_token_cost_flex":2e-8,"cache_read_input_audio_token_cost":3e-8,"cache_read_input_token_cost_priority":5e-8,"google_maps_grounding_cost_per_query":0.014},"pricing_endpoint":"google/gemini-3.5-flash-lite","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"google/gemini-3.5-flash-lite","object":"model","created":1784646726,"owned_by":"google","model_name":"gemini-3.5-flash-lite","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"Gemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities. It is suited for subagents that execute focused tasks within complex, multi-agent workflows.","source":null,"capabilities":{"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":2.5e-6,"input_cost_per_token_flex":1.5e-7,"input_cost_per_audio_token":3e-7,"input_cost_per_image_token":3e-7,"output_cost_per_token_flex":1.25e-6,"cache_read_input_token_cost":3e-8,"input_cost_per_token_priority":5.4e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":4.5e-6,"cache_creation_input_token_cost":8.33333333333333e-8,"output_cost_per_reasoning_token":2.5e-6,"cache_read_input_token_cost_flex":2e-8,"cache_read_input_audio_token_cost":3e-8,"cache_read_input_token_cost_priority":5e-8,"google_maps_grounding_cost_per_query":0.014},"list_pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":2.5e-6,"input_cost_per_token_flex":1.5e-7,"input_cost_per_audio_token":3e-7,"input_cost_per_image_token":3e-7,"output_cost_per_token_flex":1.25e-6,"cache_read_input_token_cost":3e-8,"input_cost_per_token_priority":5.4e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":4.5e-6,"cache_creation_input_token_cost":8.33333333333333e-8,"output_cost_per_reasoning_token":2.5e-6,"cache_read_input_token_cost_flex":2e-8,"cache_read_input_audio_token_cost":3e-8,"cache_read_input_token_cost_priority":5e-8,"google_maps_grounding_cost_per_query":0.014},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"vertex/gemini-3.5-flash-lite@eu","object":"model","created":1784646726,"owned_by":"vertex","model_name":"gemini-3.5-flash-lite","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"Gemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities. It is suited for subagents that execute focused tasks within complex, multi-agent workflows.","source":null,"capabilities":{"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":3.3e-7,"output_cost_per_token":2.7500000000000004e-6,"input_cost_per_token_flex":1.65e-7,"input_cost_per_audio_token":3.3e-7,"input_cost_per_image_token":3.3e-7,"output_cost_per_token_flex":1.3750000000000002e-6,"cache_read_input_token_cost":3.3e-8,"input_cost_per_token_priority":5.94e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":4.950000000000001e-6,"cache_creation_input_token_cost":9.166666666666664e-8,"output_cost_per_reasoning_token":2.7500000000000004e-6,"cache_read_input_token_cost_flex":1.65e-8,"cache_read_input_audio_token_cost":3.3e-8,"cache_read_input_token_cost_priority":5.94e-8,"google_maps_grounding_cost_per_query":0.015400000000000002},"list_pricing":{"input_cost_per_token":3.3e-7,"output_cost_per_token":2.7500000000000004e-6,"input_cost_per_token_flex":1.65e-7,"input_cost_per_audio_token":3.3e-7,"input_cost_per_image_token":3.3e-7,"output_cost_per_token_flex":1.3750000000000002e-6,"cache_read_input_token_cost":3.3e-8,"input_cost_per_token_priority":5.94e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":4.950000000000001e-6,"cache_creation_input_token_cost":9.166666666666664e-8,"output_cost_per_reasoning_token":2.7500000000000004e-6,"cache_read_input_token_cost_flex":1.65e-8,"cache_read_input_audio_token_cost":3.3e-8,"cache_read_input_token_cost_priority":5.94e-8,"google_maps_grounding_cost_per_query":0.015400000000000002},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"vertex/gemini-3.5-flash-lite","object":"model","created":1784646726,"owned_by":"vertex","model_name":"gemini-3.5-flash-lite","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"Gemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities. It is suited for subagents that execute focused tasks within complex, multi-agent workflows.","source":null,"capabilities":{"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":2.5e-6,"input_cost_per_token_flex":1.5e-7,"input_cost_per_audio_token":3e-7,"input_cost_per_image_token":3e-7,"output_cost_per_token_flex":1.25e-6,"cache_read_input_token_cost":3e-8,"input_cost_per_token_priority":5.4e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":4.5e-6,"cache_creation_input_token_cost":8.33333333333333e-8,"output_cost_per_reasoning_token":2.5e-6,"cache_read_input_token_cost_flex":1.5e-8,"cache_read_input_audio_token_cost":3e-8,"cache_read_input_token_cost_priority":5.4e-8,"google_maps_grounding_cost_per_query":0.014},"list_pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":2.5e-6,"input_cost_per_token_flex":1.5e-7,"input_cost_per_audio_token":3e-7,"input_cost_per_image_token":3e-7,"output_cost_per_token_flex":1.25e-6,"cache_read_input_token_cost":3e-8,"input_cost_per_token_priority":5.4e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":4.5e-6,"cache_creation_input_token_cost":8.33333333333333e-8,"output_cost_per_reasoning_token":2.5e-6,"cache_read_input_token_cost_flex":1.5e-8,"cache_read_input_audio_token_cost":3e-8,"cache_read_input_token_cost_priority":5.4e-8,"google_maps_grounding_cost_per_query":0.014},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"vertex/gemini-3.5-flash-lite@us","object":"model","created":1784646726,"owned_by":"vertex","model_name":"gemini-3.5-flash-lite","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"Gemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities. It is suited for subagents that execute focused tasks within complex, multi-agent workflows.","source":null,"capabilities":{"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":3.3e-7,"output_cost_per_token":2.7500000000000004e-6,"input_cost_per_token_flex":1.65e-7,"input_cost_per_audio_token":3.3e-7,"input_cost_per_image_token":3.3e-7,"output_cost_per_token_flex":1.3750000000000002e-6,"cache_read_input_token_cost":3.3e-8,"input_cost_per_token_priority":5.94e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":4.950000000000001e-6,"cache_creation_input_token_cost":9.166666666666664e-8,"output_cost_per_reasoning_token":2.7500000000000004e-6,"cache_read_input_token_cost_flex":1.65e-8,"cache_read_input_audio_token_cost":3.3e-8,"cache_read_input_token_cost_priority":5.94e-8,"google_maps_grounding_cost_per_query":0.015400000000000002},"list_pricing":{"input_cost_per_token":3.3e-7,"output_cost_per_token":2.7500000000000004e-6,"input_cost_per_token_flex":1.65e-7,"input_cost_per_audio_token":3.3e-7,"input_cost_per_image_token":3.3e-7,"output_cost_per_token_flex":1.3750000000000002e-6,"cache_read_input_token_cost":3.3e-8,"input_cost_per_token_priority":5.94e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":4.950000000000001e-6,"cache_creation_input_token_cost":9.166666666666664e-8,"output_cost_per_reasoning_token":2.7500000000000004e-6,"cache_read_input_token_cost_flex":1.65e-8,"cache_read_input_audio_token_cost":3.3e-8,"cache_read_input_token_cost_priority":5.94e-8,"google_maps_grounding_cost_per_query":0.015400000000000002},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":4},{"id":"grok-4.5","object":"model","created":1783523154,"owned_by":"xai","mode":"chat","context_length":500000,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":6e-6,"input_cost_per_image_token":2e-6,"cache_read_input_token_cost":3e-7,"search_context_cost_per_query":{"search_context_size_low":0.005,"search_context_size_high":0.005,"search_context_size_medium":0.005},"input_cost_per_token_above_200k_tokens":4e-6,"output_cost_per_token_above_200k_tokens":0.000012,"cache_read_input_token_cost_above_200k_tokens":6e-7},"pricing_endpoint":"xai/grok-4.5","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"xai/grok-4.5","object":"model","created":1783523154,"owned_by":"xai","model_name":"grok-4.5","context_length":500000,"max_input_tokens":500000,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"Grok 4.5 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":6e-6,"input_cost_per_image_token":2e-6,"cache_read_input_token_cost":3e-7,"search_context_cost_per_query":{"search_context_size_low":0.005,"search_context_size_high":0.005,"search_context_size_medium":0.005},"input_cost_per_token_above_200k_tokens":4e-6,"output_cost_per_token_above_200k_tokens":0.000012,"cache_read_input_token_cost_above_200k_tokens":6e-7},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":6e-6,"input_cost_per_image_token":2e-6,"cache_read_input_token_cost":3e-7,"search_context_cost_per_query":{"search_context_size_low":0.005,"search_context_size_high":0.005,"search_context_size_medium":0.005},"input_cost_per_token_above_200k_tokens":4e-6,"output_cost_per_token_above_200k_tokens":0.000012,"cache_read_input_token_cost_above_200k_tokens":6e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"claude-fable-5","object":"model","created":1783401184,"owned_by":"anthropic","mode":"chat","context_length":1000000,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":0.00001,"output_cost_per_token":0.00005,"provider_specific_entry":{"us":1.1},"cache_read_input_token_cost":1e-6,"input_cost_per_token_batches":5e-6,"output_cost_per_token_batches":0.000025,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":0.0000125,"cache_read_input_token_cost_batches":5e-7,"cache_creation_input_token_cost_above_1hr":0.00002},"pricing_endpoint":"anthropic/claude-fable-5","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"deepinfra/anthropic/claude-fable-5","object":"model","created":1783401184,"owned_by":"deepinfra","model_name":"anthropic/claude-fable-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":0.00001,"output_cost_per_token":0.00005},"list_pricing":{"input_cost_per_token":0.00001,"output_cost_per_token":0.00005},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null},{"id":"anthropic/claude-fable-5","object":"model","created":1781007515,"owned_by":"anthropic","model_name":"claude-fable-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":0.00001,"output_cost_per_token":0.00005,"provider_specific_entry":{"us":1.1},"cache_read_input_token_cost":1e-6,"input_cost_per_token_batches":5e-6,"output_cost_per_token_batches":0.000025,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":0.0000125,"cache_read_input_token_cost_batches":5e-7,"cache_creation_input_token_cost_above_1hr":0.00002},"list_pricing":{"input_cost_per_token":0.00001,"output_cost_per_token":0.00005,"provider_specific_entry":{"us":1.1},"cache_read_input_token_cost":1e-6,"input_cost_per_token_batches":5e-6,"output_cost_per_token_batches":0.000025,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":0.0000125,"cache_read_input_token_cost_batches":5e-7,"cache_creation_input_token_cost_above_1hr":0.00002},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null},{"id":"vertex/claude-fable-5@eu","object":"model","created":1781007515,"owned_by":"vertex","model_name":"claude-fable-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":0.000011000000000000001,"output_cost_per_token":0.00005500000000000001,"cache_read_input_token_cost":1.1e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":0.000013750000000000002,"cache_creation_input_token_cost_above_1hr":0.000022000000000000003},"list_pricing":{"input_cost_per_token":0.000011000000000000001,"output_cost_per_token":0.00005500000000000001,"cache_read_input_token_cost":1.1e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":0.000013750000000000002,"cache_creation_input_token_cost_above_1hr":0.000022000000000000003},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"vertex/claude-fable-5","object":"model","created":1781007515,"owned_by":"vertex","model_name":"claude-fable-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":0.00001,"output_cost_per_token":0.00005,"cache_read_input_token_cost":1e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":0.0000125,"cache_creation_input_token_cost_above_1hr":0.00002},"list_pricing":{"input_cost_per_token":0.00001,"output_cost_per_token":0.00005,"cache_read_input_token_cost":1e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":0.0000125,"cache_creation_input_token_cost_above_1hr":0.00002},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"vertex/claude-fable-5@us","object":"model","created":1781007515,"owned_by":"vertex","model_name":"claude-fable-5","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":0.000011000000000000001,"output_cost_per_token":0.00005500000000000001,"cache_read_input_token_cost":1.1e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":0.000013750000000000002,"cache_creation_input_token_cost_above_1hr":0.000022000000000000003},"list_pricing":{"input_cost_per_token":0.000011000000000000001,"output_cost_per_token":0.00005500000000000001,"cache_read_input_token_cost":1.1e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":0.000013750000000000002,"cache_creation_input_token_cost_above_1hr":0.000022000000000000003},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":5},{"id":"gemini-3.1-flash-lite-image","object":"model","created":1782837225,"owned_by":"google","mode":"chat","context_length":65536,"capabilities":{"input_modalities":["image","text"],"output_modalities":["image","text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.5e-7,"output_cost_per_token":1.5e-6,"output_cost_per_image_token":0.00003,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014}},"pricing_endpoint":"google/gemini-3.1-flash-lite-image","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"google/gemini-3.1-flash-lite-image","object":"model","created":1782837225,"owned_by":"google","model_name":"gemini-3.1-flash-lite-image","context_length":65536,"max_input_tokens":65536,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) is Google's fastest, most cost-efficient Gemini image model, built for high-velocity developer pipelines and rapid-fire visual exploration.","source":null,"capabilities":{"input_modalities":["image","text"],"output_modalities":["image","text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.5e-7,"output_cost_per_token":1.5e-6,"output_cost_per_image_token":0.00003,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014}},"list_pricing":{"input_cost_per_token":2.5e-7,"output_cost_per_token":1.5e-6,"output_cost_per_image_token":0.00003,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014}},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"vertex/gemini-3.1-flash-lite-image","object":"model","created":1782837225,"owned_by":"vertex","model_name":"gemini-3.1-flash-lite-image","context_length":65536,"max_input_tokens":null,"max_output_tokens":66000,"quantization":null,"retirement_date":null,"description":"Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) is Google's fastest, most cost-efficient Gemini image model, built for high-velocity developer pipelines and rapid-fire visual exploration.","source":null,"capabilities":{"input_modalities":["image","text"],"output_modalities":["image","text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.5e-7,"output_cost_per_token":1.5e-6,"output_cost_per_image_token":0.00003,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014}},"list_pricing":{"input_cost_per_token":2.5e-7,"output_cost_per_token":1.5e-6,"output_cost_per_image_token":0.00003,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014}},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"mistral-medium-2508","object":"model","created":1782745560,"owned_by":"mistral","mode":"chat","context_length":131072,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4e-7,"output_cost_per_token":2e-6},"pricing_endpoint":"mistral/mistral-medium-2508","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"mistral/mistral-medium-2508@eu","object":"model","created":1782745560,"owned_by":"mistral","model_name":"mistral-medium-2508","context_length":131072,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":"2026-08-31","description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4.4e-7,"output_cost_per_token":2.2e-6},"list_pricing":{"input_cost_per_token":4.4e-7,"output_cost_per_token":2.2e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"mistral/mistral-medium-2508","object":"model","created":1782745560,"owned_by":"mistral","model_name":"mistral-medium-2508","context_length":131072,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":"2026-08-31","description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4e-7,"output_cost_per_token":2e-6},"list_pricing":{"input_cost_per_token":4e-7,"output_cost_per_token":2e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"mistral-medium-2604","object":"model","created":1782745560,"owned_by":"mistral","mode":"chat","context_length":262144,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-6,"output_cost_per_token":7.5e-6,"cache_read_input_token_cost":1.5e-7,"input_cost_per_token_batches":7.5e-7,"output_cost_per_token_batches":3.75e-6,"cache_read_input_token_cost_batches":7.5e-8},"pricing_endpoint":"mistral/mistral-medium-2604","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"mistral/mistral-medium-2604@eu","object":"model","created":1782745560,"owned_by":"mistral","model_name":"mistral-medium-2604","context_length":262144,"max_input_tokens":262144,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.65e-6,"output_cost_per_token":8.25e-6,"cache_read_input_token_cost":1.65e-7,"input_cost_per_token_batches":8.25e-7,"output_cost_per_token_batches":4.125e-6,"cache_read_input_token_cost_batches":8.25e-8},"list_pricing":{"input_cost_per_token":1.65e-6,"output_cost_per_token":8.25e-6,"cache_read_input_token_cost":1.65e-7,"input_cost_per_token_batches":8.25e-7,"output_cost_per_token_batches":4.125e-6,"cache_read_input_token_cost_batches":8.25e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"mistral/mistral-medium-2604","object":"model","created":1782745560,"owned_by":"mistral","model_name":"mistral-medium-2604","context_length":262144,"max_input_tokens":262144,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-6,"output_cost_per_token":7.5e-6,"cache_read_input_token_cost":1.5e-7,"input_cost_per_token_batches":7.5e-7,"output_cost_per_token_batches":3.75e-6,"cache_read_input_token_cost_batches":7.5e-8},"list_pricing":{"input_cost_per_token":1.5e-6,"output_cost_per_token":7.5e-6,"cache_read_input_token_cost":1.5e-7,"input_cost_per_token_batches":7.5e-7,"output_cost_per_token_batches":3.75e-6,"cache_read_input_token_cost_batches":7.5e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"ornith-1.0-35b","object":"model","created":1782745560,"owned_by":"","mode":"chat","context_length":262144,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.0000000000000001e-7,"output_cost_per_token":7.499999999999999e-7,"cache_read_input_token_cost":5.0000000000000004e-8},"pricing_endpoint":"deepinfra/deepreinforce-ai/Ornith-1.0-35B","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"deepinfra/deepreinforce-ai/Ornith-1.0-35B","object":"model","created":1782745560,"owned_by":"deepinfra","model_name":"deepreinforce-ai/Ornith-1.0-35B","context_length":262144,"max_input_tokens":null,"max_output_tokens":262144,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.0000000000000001e-7,"output_cost_per_token":7.499999999999999e-7,"cache_read_input_token_cost":5.0000000000000004e-8},"list_pricing":{"input_cost_per_token":1.0000000000000001e-7,"output_cost_per_token":7.499999999999999e-7,"cache_read_input_token_cost":5.0000000000000004e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"gemma-2b-it-lora","object":"model","created":1782278004,"owned_by":"google","mode":"chat","context_length":8192,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":0.0,"output_cost_per_token":0.0},"pricing_endpoint":"cloudflare/@cf/google/gemma-2b-it-lora","regions":[{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"cloudflare/@cf/google/gemma-2b-it-lora","object":"model","created":1782278004,"owned_by":"cloudflare","model_name":"@cf/google/gemma-2b-it-lora","context_length":8192,"max_input_tokens":8192,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":0.0,"output_cost_per_token":0.0},"list_pricing":{"input_cost_per_token":0.0,"output_cost_per_token":0.0},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"gemma-7b-it-lora","object":"model","created":1782278004,"owned_by":"google","mode":"chat","context_length":3500,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":0.0,"output_cost_per_token":0.0},"pricing_endpoint":"cloudflare/@cf/google/gemma-7b-it-lora","regions":[{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"cloudflare/@cf/google/gemma-7b-it-lora","object":"model","created":1782278004,"owned_by":"cloudflare","model_name":"@cf/google/gemma-7b-it-lora","context_length":3500,"max_input_tokens":3500,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":0.0,"output_cost_per_token":0.0},"list_pricing":{"input_cost_per_token":0.0,"output_cost_per_token":0.0},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"llama-2-7b-chat-hf-lora","object":"model","created":1782278004,"owned_by":"meta","mode":"chat","context_length":8192,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":0.0,"output_cost_per_token":0.0},"pricing_endpoint":"cloudflare/@cf/meta-llama/llama-2-7b-chat-hf-lora","regions":[{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"cloudflare/@cf/meta-llama/llama-2-7b-chat-hf-lora","object":"model","created":1782278004,"owned_by":"cloudflare","model_name":"@cf/meta-llama/llama-2-7b-chat-hf-lora","context_length":8192,"max_input_tokens":8192,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":0.0,"output_cost_per_token":0.0},"list_pricing":{"input_cost_per_token":0.0,"output_cost_per_token":0.0},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"mistral-7b-instruct-v0.2-lora","object":"model","created":1782278004,"owned_by":"mistral","mode":"chat","context_length":15000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":0.0,"output_cost_per_token":0.0},"pricing_endpoint":"cloudflare/@cf/mistral/mistral-7b-instruct-v0.2-lora","regions":[{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"cloudflare/@cf/mistral/mistral-7b-instruct-v0.2-lora","object":"model","created":1782278004,"owned_by":"cloudflare","model_name":"@cf/mistral/mistral-7b-instruct-v0.2-lora","context_length":15000,"max_input_tokens":15000,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":0.0,"output_cost_per_token":0.0},"list_pricing":{"input_cost_per_token":0.0,"output_cost_per_token":0.0},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"grok-4.20-multi-agent-0309","object":"model","created":1782123085,"owned_by":"xai","mode":"chat","context_length":1000000,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":2.5e-6,"input_cost_per_image_token":1.25e-6,"cache_read_input_token_cost":2e-7,"input_cost_per_token_above_200k_tokens":2.5e-6,"output_cost_per_token_above_200k_tokens":5e-6,"cache_read_input_token_cost_above_200k_tokens":4e-7},"pricing_endpoint":"xai/grok-4.20-multi-agent-0309","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"xai/grok-4.20-multi-agent-0309","object":"model","created":1782123085,"owned_by":"xai","model_name":"grok-4.20-multi-agent-0309","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":2.5e-6,"input_cost_per_image_token":1.25e-6,"cache_read_input_token_cost":2e-7,"input_cost_per_token_above_200k_tokens":2.5e-6,"output_cost_per_token_above_200k_tokens":5e-6,"cache_read_input_token_cost_above_200k_tokens":4e-7},"list_pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":2.5e-6,"input_cost_per_image_token":1.25e-6,"cache_read_input_token_cost":2e-7,"input_cost_per_token_above_200k_tokens":2.5e-6,"output_cost_per_token_above_200k_tokens":5e-6,"cache_read_input_token_cost_above_200k_tokens":4e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"llama-prompt-guard-2-22m","object":"model","created":1782123085,"owned_by":"meta","mode":"chat","context_length":512,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-8,"output_cost_per_token":3e-8,"cache_read_input_token_cost":1.5e-8},"pricing_endpoint":"groq/meta-llama/llama-prompt-guard-2-22m","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"groq/meta-llama/llama-prompt-guard-2-22m","object":"model","created":1782123085,"owned_by":"groq","model_name":"meta-llama/llama-prompt-guard-2-22m","context_length":512,"max_input_tokens":512,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-8,"output_cost_per_token":3e-8,"cache_read_input_token_cost":1.5e-8},"list_pricing":{"input_cost_per_token":3e-8,"output_cost_per_token":3e-8,"cache_read_input_token_cost":1.5e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":1},{"id":"llama-prompt-guard-2-86m","object":"model","created":1782123085,"owned_by":"meta","mode":"chat","context_length":512,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4e-8,"output_cost_per_token":4e-8,"cache_read_input_token_cost":2e-8},"pricing_endpoint":"groq/meta-llama/llama-prompt-guard-2-86m","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"groq/meta-llama/llama-prompt-guard-2-86m","object":"model","created":1782123085,"owned_by":"groq","model_name":"meta-llama/llama-prompt-guard-2-86m","context_length":512,"max_input_tokens":512,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4e-8,"output_cost_per_token":4e-8,"cache_read_input_token_cost":2e-8},"list_pricing":{"input_cost_per_token":4e-8,"output_cost_per_token":4e-8,"cache_read_input_token_cost":2e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":1},{"id":"claude-haiku-4.5","object":"model","created":1782119040,"owned_by":"anthropic","mode":"chat","context_length":200000,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":5e-6,"cache_read_input_token_cost":1e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":1.25e-6,"cache_creation_input_token_cost_above_1hr":2e-6},"pricing_endpoint":"anthropic/claude-haiku-4-5","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"deepinfra/anthropic/claude-haiku-4-5","object":"model","created":1782119040,"owned_by":"deepinfra","model_name":"anthropic/claude-haiku-4-5","context_length":200000,"max_input_tokens":200000,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":5e-6},"list_pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":5e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null},{"id":"databricks/databricks-claude-haiku-4-5@eu","object":"model","created":1769507058,"owned_by":"databricks","model_name":"databricks-claude-haiku-4-5","context_length":200000,"max_input_tokens":200000,"max_output_tokens":64000,"quantization":null,"retirement_date":null,"description":"Claude Haiku 4.5 is Anthropic's fastest and most cost efficient hybrid reasoning model, optimized for real-time use and high-volume workloads. It features two modes: quick responses for time-sensitive interactions and extended reasoning for complex problem-solving. Haiku 4.5 excels in environments like coding assistance, automated agent workflows, and enterprise-scale analysis. This endpoint is hosted by Databricks.","source":"https://www.databricks.com/product/pricing/proprietary-foundation-model-serving","capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":5e-6,"input_dbu_cost_per_token":0.000014286,"output_dbu_cost_per_token":0.000071429,"cache_read_input_token_cost":1e-7,"cache_creation_input_token_cost":1.25e-6,"cache_creation_input_token_cost_above_1hr":2e-6},"list_pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":5e-6,"input_dbu_cost_per_token":0.000014286,"output_dbu_cost_per_token":0.000071429,"cache_read_input_token_cost":1e-7,"cache_creation_input_token_cost":1.25e-6,"cache_creation_input_token_cost_above_1hr":2e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"databricks/databricks-claude-haiku-4-5","object":"model","created":1769507058,"owned_by":"databricks","model_name":"databricks-claude-haiku-4-5","context_length":200000,"max_input_tokens":200000,"max_output_tokens":64000,"quantization":null,"retirement_date":null,"description":"Claude Haiku 4.5 is Anthropic's fastest and most cost efficient hybrid reasoning model, optimized for real-time use and high-volume workloads. It features two modes: quick responses for time-sensitive interactions and extended reasoning for complex problem-solving. Haiku 4.5 excels in environments like coding assistance, automated agent workflows, and enterprise-scale analysis. This endpoint is hosted by Databricks.","source":"https://www.databricks.com/product/pricing/proprietary-foundation-model-serving","capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":5e-6,"input_dbu_cost_per_token":0.000014286,"output_dbu_cost_per_token":0.000071429,"cache_read_input_token_cost":1e-7,"cache_creation_input_token_cost":1.25e-6,"cache_creation_input_token_cost_above_1hr":2e-6},"list_pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":5e-6,"input_dbu_cost_per_token":0.000014286,"output_dbu_cost_per_token":0.000071429,"cache_read_input_token_cost":1e-7,"cache_creation_input_token_cost":1.25e-6,"cache_creation_input_token_cost_above_1hr":2e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"anthropic/claude-haiku-4-5","object":"model","created":1760547638,"owned_by":"anthropic","model_name":"claude-haiku-4-5","context_length":200000,"max_input_tokens":200000,"max_output_tokens":64000,"quantization":null,"retirement_date":null,"description":"Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4’s performance...","source":null,"capabilities":{"input_modalities":["file","image","text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":5e-6,"cache_read_input_token_cost":1e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":1.25e-6,"cache_creation_input_token_cost_above_1hr":2e-6},"list_pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":5e-6,"cache_read_input_token_cost":1e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":1.25e-6,"cache_creation_input_token_cost_above_1hr":2e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null},{"id":"vertex/claude-haiku-4-5@eu","object":"model","created":1760547638,"owned_by":"vertex","model_name":"claude-haiku-4-5","context_length":200000,"max_input_tokens":200000,"max_output_tokens":64000,"quantization":null,"retirement_date":null,"description":"Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.1e-6,"output_cost_per_token":5.500000000000001e-6,"cache_read_input_token_cost":1.1e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":1.3750000000000002e-6,"cache_creation_input_token_cost_above_1hr":2.2e-6},"list_pricing":{"input_cost_per_token":1.1e-6,"output_cost_per_token":5.500000000000001e-6,"cache_read_input_token_cost":1.1e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":1.3750000000000002e-6,"cache_creation_input_token_cost_above_1hr":2.2e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"vertex/claude-haiku-4-5","object":"model","created":1760547638,"owned_by":"vertex","model_name":"claude-haiku-4-5","context_length":200000,"max_input_tokens":200000,"max_output_tokens":64000,"quantization":null,"retirement_date":null,"description":"Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":5e-6,"cache_read_input_token_cost":1e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":1.25e-6,"cache_creation_input_token_cost_above_1hr":2e-6},"list_pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":5e-6,"cache_read_input_token_cost":1e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":1.25e-6,"cache_creation_input_token_cost_above_1hr":2e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"vertex/claude-haiku-4-5@us","object":"model","created":1760547638,"owned_by":"vertex","model_name":"claude-haiku-4-5","context_length":200000,"max_input_tokens":200000,"max_output_tokens":64000,"quantization":null,"retirement_date":null,"description":"Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.1e-6,"output_cost_per_token":5.500000000000001e-6,"cache_read_input_token_cost":1.1e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":1.3750000000000002e-6,"cache_creation_input_token_cost_above_1hr":2.2e-6},"list_pricing":{"input_cost_per_token":1.1e-6,"output_cost_per_token":5.500000000000001e-6,"cache_read_input_token_cost":1.1e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":1.3750000000000002e-6,"cache_creation_input_token_cost_above_1hr":2.2e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":7},{"id":"claude-opus-4.7","object":"model","created":1782119040,"owned_by":"anthropic","mode":"chat","context_length":1000000,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-6,"output_cost_per_token":0.000025,"provider_specific_entry":{"us":1.1},"cache_read_input_token_cost":5e-7,"input_cost_per_token_batches":2.5e-6,"output_cost_per_token_batches":0.0000125,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.25e-6,"cache_read_input_token_cost_batches":2.5e-7,"cache_creation_input_token_cost_above_1hr":0.00001},"pricing_endpoint":"anthropic/claude-opus-4-7","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"deepinfra/anthropic/claude-opus-4-7","object":"model","created":1782119040,"owned_by":"deepinfra","model_name":"anthropic/claude-opus-4-7","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-6,"output_cost_per_token":0.000025},"list_pricing":{"input_cost_per_token":5e-6,"output_cost_per_token":0.000025},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null},{"id":"databricks/databricks-claude-opus-4-7@eu","object":"model","created":1780933448,"owned_by":"databricks","model_name":"databricks-claude-opus-4-7","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Opus 4.7 is Anthropic's most capable hybrid reasoning model, advancing the Opus series with improved accuracy, efficiency, and enhanced vision capabilities. This model delivers stronger performance on complex extraction and agentic reasoning tasks while using fewer output tokens than its predecessor. Claude Opus 4.7 features a 1 million token context window and increased image resolution support, making it ideal for enterprise applications that require deep analysis, document understanding, and sophisticated multi-step workflows. This model is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-6,"output_cost_per_token":0.000025,"input_dbu_cost_per_token":0.000071429,"output_dbu_cost_per_token":0.00035714,"cache_read_input_token_cost":5e-7,"cache_creation_input_token_cost":6.25e-6,"cache_creation_input_token_cost_above_1hr":0.00001},"list_pricing":{"input_cost_per_token":5e-6,"output_cost_per_token":0.000025,"input_dbu_cost_per_token":0.000071429,"output_dbu_cost_per_token":0.00035714,"cache_read_input_token_cost":5e-7,"cache_creation_input_token_cost":6.25e-6,"cache_creation_input_token_cost_above_1hr":0.00001},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"databricks/databricks-claude-opus-4-7","object":"model","created":1780933448,"owned_by":"databricks","model_name":"databricks-claude-opus-4-7","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Opus 4.7 is Anthropic's most capable hybrid reasoning model, advancing the Opus series with improved accuracy, efficiency, and enhanced vision capabilities. This model delivers stronger performance on complex extraction and agentic reasoning tasks while using fewer output tokens than its predecessor. Claude Opus 4.7 features a 1 million token context window and increased image resolution support, making it ideal for enterprise applications that require deep analysis, document understanding, and sophisticated multi-step workflows. This model is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-6,"output_cost_per_token":0.000025,"input_dbu_cost_per_token":0.000071429,"output_dbu_cost_per_token":0.00035714,"cache_read_input_token_cost":5e-7,"cache_creation_input_token_cost":6.25e-6,"cache_creation_input_token_cost_above_1hr":0.00001},"list_pricing":{"input_cost_per_token":5e-6,"output_cost_per_token":0.000025,"input_dbu_cost_per_token":0.000071429,"output_dbu_cost_per_token":0.00035714,"cache_read_input_token_cost":5e-7,"cache_creation_input_token_cost":6.25e-6,"cache_creation_input_token_cost_above_1hr":0.00001},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"amazon/anthropic.claude-opus-4-7@eu","object":"model","created":1776351100,"owned_by":"amazon","model_name":"anthropic.claude-opus-4-7","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5.500000000000001e-6,"output_cost_per_token":0.000027500000000000004,"cache_read_input_token_cost":5.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.875000000000001e-6,"cache_creation_input_token_cost_above_1hr":0.000011000000000000001},"list_pricing":{"input_cost_per_token":5.500000000000001e-6,"output_cost_per_token":0.000027500000000000004,"cache_read_input_token_cost":5.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.875000000000001e-6,"cache_creation_input_token_cost_above_1hr":0.000011000000000000001},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/anthropic.claude-opus-4-7","object":"model","created":1776351100,"owned_by":"amazon","model_name":"anthropic.claude-opus-4-7","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-6,"output_cost_per_token":0.000025,"cache_read_input_token_cost":5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.25e-6,"cache_creation_input_token_cost_above_1hr":0.00001},"list_pricing":{"input_cost_per_token":5e-6,"output_cost_per_token":0.000025,"cache_read_input_token_cost":5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.25e-6,"cache_creation_input_token_cost_above_1hr":0.00001},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/anthropic.claude-opus-4-7@us","object":"model","created":1776351100,"owned_by":"amazon","model_name":"anthropic.claude-opus-4-7","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5.500000000000001e-6,"output_cost_per_token":0.000027500000000000004,"cache_read_input_token_cost":5.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.875000000000001e-6,"cache_creation_input_token_cost_above_1hr":0.000011000000000000001},"list_pricing":{"input_cost_per_token":5.500000000000001e-6,"output_cost_per_token":0.000027500000000000004,"cache_read_input_token_cost":5.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.875000000000001e-6,"cache_creation_input_token_cost_above_1hr":0.000011000000000000001},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"anthropic/claude-opus-4-7","object":"model","created":1776351100,"owned_by":"anthropic","model_name":"claude-opus-4-7","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-6,"output_cost_per_token":0.000025,"provider_specific_entry":{"us":1.1},"cache_read_input_token_cost":5e-7,"input_cost_per_token_batches":2.5e-6,"output_cost_per_token_batches":0.0000125,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.25e-6,"cache_read_input_token_cost_batches":2.5e-7,"cache_creation_input_token_cost_above_1hr":0.00001},"list_pricing":{"input_cost_per_token":5e-6,"output_cost_per_token":0.000025,"provider_specific_entry":{"us":1.1},"cache_read_input_token_cost":5e-7,"input_cost_per_token_batches":2.5e-6,"output_cost_per_token_batches":0.0000125,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.25e-6,"cache_read_input_token_cost_batches":2.5e-7,"cache_creation_input_token_cost_above_1hr":0.00001},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null},{"id":"vertex/claude-opus-4-7@eu","object":"model","created":1776351100,"owned_by":"vertex","model_name":"claude-opus-4-7","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5.500000000000001e-6,"output_cost_per_token":0.000027500000000000004,"cache_read_input_token_cost":5.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.875000000000001e-6,"cache_creation_input_token_cost_above_1hr":0.000011000000000000001},"list_pricing":{"input_cost_per_token":5.500000000000001e-6,"output_cost_per_token":0.000027500000000000004,"cache_read_input_token_cost":5.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.875000000000001e-6,"cache_creation_input_token_cost_above_1hr":0.000011000000000000001},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"vertex/claude-opus-4-7","object":"model","created":1776351100,"owned_by":"vertex","model_name":"claude-opus-4-7","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-6,"output_cost_per_token":0.000025,"cache_read_input_token_cost":5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.25e-6,"cache_creation_input_token_cost_above_1hr":0.00001},"list_pricing":{"input_cost_per_token":5e-6,"output_cost_per_token":0.000025,"cache_read_input_token_cost":5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.25e-6,"cache_creation_input_token_cost_above_1hr":0.00001},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"vertex/claude-opus-4-7@us","object":"model","created":1776351100,"owned_by":"vertex","model_name":"claude-opus-4-7","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5.500000000000001e-6,"output_cost_per_token":0.000027500000000000004,"cache_read_input_token_cost":5.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.875000000000001e-6,"cache_creation_input_token_cost_above_1hr":0.000011000000000000001},"list_pricing":{"input_cost_per_token":5.500000000000001e-6,"output_cost_per_token":0.000027500000000000004,"cache_read_input_token_cost":5.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.875000000000001e-6,"cache_creation_input_token_cost_above_1hr":0.000011000000000000001},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":10},{"id":"claude-opus-4.8","object":"model","created":1782119040,"owned_by":"anthropic","mode":"chat","context_length":1000000,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-6,"output_cost_per_token":0.000025,"provider_specific_entry":{"us":1.1,"fast":2.0},"cache_read_input_token_cost":5e-7,"input_cost_per_token_batches":2.5e-6,"output_cost_per_token_batches":0.0000125,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.25e-6,"cache_read_input_token_cost_batches":2.5e-7,"cache_creation_input_token_cost_above_1hr":0.00001},"pricing_endpoint":"anthropic/claude-opus-4-8","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"deepinfra/anthropic/claude-opus-4-8","object":"model","created":1782119040,"owned_by":"deepinfra","model_name":"anthropic/claude-opus-4-8","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-6,"output_cost_per_token":0.000025},"list_pricing":{"input_cost_per_token":5e-6,"output_cost_per_token":0.000025},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null},{"id":"databricks/databricks-claude-opus-4-8@eu","object":"model","created":1780933263,"owned_by":"databricks","model_name":"databricks-claude-opus-4-8","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Opus 4.8 is Anthropic's next-generation Opus model, hosted by Databricks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-6,"output_cost_per_token":0.000025,"input_dbu_cost_per_token":0.000071429,"output_dbu_cost_per_token":0.00035714,"cache_read_input_token_cost":5e-7,"cache_creation_input_token_cost":6.25e-6,"cache_creation_input_token_cost_above_1hr":0.00001},"list_pricing":{"input_cost_per_token":5e-6,"output_cost_per_token":0.000025,"input_dbu_cost_per_token":0.000071429,"output_dbu_cost_per_token":0.00035714,"cache_read_input_token_cost":5e-7,"cache_creation_input_token_cost":6.25e-6,"cache_creation_input_token_cost_above_1hr":0.00001},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"databricks/databricks-claude-opus-4-8","object":"model","created":1780933263,"owned_by":"databricks","model_name":"databricks-claude-opus-4-8","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Opus 4.8 is Anthropic's next-generation Opus model, hosted by Databricks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-6,"output_cost_per_token":0.000025,"input_dbu_cost_per_token":0.000071429,"output_dbu_cost_per_token":0.00035714,"cache_read_input_token_cost":5e-7,"cache_creation_input_token_cost":6.25e-6,"cache_creation_input_token_cost_above_1hr":0.00001},"list_pricing":{"input_cost_per_token":5e-6,"output_cost_per_token":0.000025,"input_dbu_cost_per_token":0.000071429,"output_dbu_cost_per_token":0.00035714,"cache_read_input_token_cost":5e-7,"cache_creation_input_token_cost":6.25e-6,"cache_creation_input_token_cost_above_1hr":0.00001},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"amazon/anthropic.claude-opus-4-8@eu","object":"model","created":1779905091,"owned_by":"amazon","model_name":"anthropic.claude-opus-4-8","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5.500000000000001e-6,"output_cost_per_token":0.000027500000000000004,"cache_read_input_token_cost":5.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.875000000000001e-6,"cache_creation_input_token_cost_above_1hr":0.000011000000000000001},"list_pricing":{"input_cost_per_token":5.500000000000001e-6,"output_cost_per_token":0.000027500000000000004,"cache_read_input_token_cost":5.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.875000000000001e-6,"cache_creation_input_token_cost_above_1hr":0.000011000000000000001},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/anthropic.claude-opus-4-8","object":"model","created":1779905091,"owned_by":"amazon","model_name":"anthropic.claude-opus-4-8","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-6,"output_cost_per_token":0.000025,"cache_read_input_token_cost":5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.25e-6,"cache_creation_input_token_cost_above_1hr":0.00001},"list_pricing":{"input_cost_per_token":5e-6,"output_cost_per_token":0.000025,"cache_read_input_token_cost":5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.25e-6,"cache_creation_input_token_cost_above_1hr":0.00001},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/anthropic.claude-opus-4-8@us","object":"model","created":1779905091,"owned_by":"amazon","model_name":"anthropic.claude-opus-4-8","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5.500000000000001e-6,"output_cost_per_token":0.000027500000000000004,"cache_read_input_token_cost":5.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.875000000000001e-6,"cache_creation_input_token_cost_above_1hr":0.000011000000000000001},"list_pricing":{"input_cost_per_token":5.500000000000001e-6,"output_cost_per_token":0.000027500000000000004,"cache_read_input_token_cost":5.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.875000000000001e-6,"cache_creation_input_token_cost_above_1hr":0.000011000000000000001},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"anthropic/claude-opus-4-8","object":"model","created":1779905091,"owned_by":"anthropic","model_name":"claude-opus-4-8","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-6,"output_cost_per_token":0.000025,"provider_specific_entry":{"us":1.1,"fast":2.0},"cache_read_input_token_cost":5e-7,"input_cost_per_token_batches":2.5e-6,"output_cost_per_token_batches":0.0000125,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.25e-6,"cache_read_input_token_cost_batches":2.5e-7,"cache_creation_input_token_cost_above_1hr":0.00001},"list_pricing":{"input_cost_per_token":5e-6,"output_cost_per_token":0.000025,"provider_specific_entry":{"us":1.1,"fast":2.0},"cache_read_input_token_cost":5e-7,"input_cost_per_token_batches":2.5e-6,"output_cost_per_token_batches":0.0000125,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.25e-6,"cache_read_input_token_cost_batches":2.5e-7,"cache_creation_input_token_cost_above_1hr":0.00001},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null},{"id":"vertex/claude-opus-4-8@eu","object":"model","created":1779905091,"owned_by":"vertex","model_name":"claude-opus-4-8","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5.500000000000001e-6,"output_cost_per_token":0.000027500000000000004,"cache_read_input_token_cost":5.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.875000000000001e-6,"cache_creation_input_token_cost_above_1hr":0.000011000000000000001},"list_pricing":{"input_cost_per_token":5.500000000000001e-6,"output_cost_per_token":0.000027500000000000004,"cache_read_input_token_cost":5.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.875000000000001e-6,"cache_creation_input_token_cost_above_1hr":0.000011000000000000001},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"vertex/claude-opus-4-8","object":"model","created":1779905091,"owned_by":"vertex","model_name":"claude-opus-4-8","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-6,"output_cost_per_token":0.000025,"cache_read_input_token_cost":5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.25e-6,"cache_creation_input_token_cost_above_1hr":0.00001},"list_pricing":{"input_cost_per_token":5e-6,"output_cost_per_token":0.000025,"cache_read_input_token_cost":5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.25e-6,"cache_creation_input_token_cost_above_1hr":0.00001},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"vertex/claude-opus-4-8@us","object":"model","created":1779905091,"owned_by":"vertex","model_name":"claude-opus-4-8","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5.500000000000001e-6,"output_cost_per_token":0.000027500000000000004,"cache_read_input_token_cost":5.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.875000000000001e-6,"cache_creation_input_token_cost_above_1hr":0.000011000000000000001},"list_pricing":{"input_cost_per_token":5.500000000000001e-6,"output_cost_per_token":0.000027500000000000004,"cache_read_input_token_cost":5.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.875000000000001e-6,"cache_creation_input_token_cost_above_1hr":0.000011000000000000001},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":10},{"id":"claude-sonnet-4.6","object":"model","created":1782119040,"owned_by":"anthropic","mode":"chat","context_length":1000000,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"provider_specific_entry":{"us":1.1},"cache_read_input_token_cost":3e-7,"input_cost_per_token_batches":1.5e-6,"output_cost_per_token_batches":7.5e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":3.75e-6,"cache_read_input_token_cost_batches":1.5e-7,"cache_creation_input_token_cost_above_1hr":6e-6},"pricing_endpoint":"anthropic/claude-sonnet-4-6","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"deepinfra/anthropic/claude-sonnet-4-6","object":"model","created":1782119040,"owned_by":"deepinfra","model_name":"anthropic/claude-sonnet-4-6","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.9999999999999997e-6,"output_cost_per_token":0.000015},"list_pricing":{"input_cost_per_token":2.9999999999999997e-6,"output_cost_per_token":0.000015},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null},{"id":"databricks/databricks-claude-sonnet-4-6@eu","object":"model","created":1780933650,"owned_by":"databricks","model_name":"databricks-claude-sonnet-4-6","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with memory, polished document creation, and confident computer use for web QA and workflow automation. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"input_dbu_cost_per_token":0.000042857,"output_dbu_cost_per_token":0.00021429,"cache_read_input_token_cost":3e-7,"cache_creation_input_token_cost":3.75e-6,"cache_creation_input_token_cost_above_1hr":6e-6},"list_pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"input_dbu_cost_per_token":0.000042857,"output_dbu_cost_per_token":0.00021429,"cache_read_input_token_cost":3e-7,"cache_creation_input_token_cost":3.75e-6,"cache_creation_input_token_cost_above_1hr":6e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"databricks/databricks-claude-sonnet-4-6","object":"model","created":1780933650,"owned_by":"databricks","model_name":"databricks-claude-sonnet-4-6","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with memory, polished document creation, and confident computer use for web QA and workflow automation. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"input_dbu_cost_per_token":0.000042857,"output_dbu_cost_per_token":0.00021429,"cache_read_input_token_cost":3e-7,"cache_creation_input_token_cost":3.75e-6,"cache_creation_input_token_cost_above_1hr":6e-6},"list_pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"input_dbu_cost_per_token":0.000042857,"output_dbu_cost_per_token":0.00021429,"cache_read_input_token_cost":3e-7,"cache_creation_input_token_cost":3.75e-6,"cache_creation_input_token_cost_above_1hr":6e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"amazon/anthropic.claude-sonnet-4-6@eu","object":"model","created":1771342990,"owned_by":"amazon","model_name":"anthropic.claude-sonnet-4-6","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.3e-6,"output_cost_per_token":0.0000165,"cache_read_input_token_cost":3.3e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":4.125e-6,"cache_creation_input_token_cost_above_1hr":6.6e-6},"list_pricing":{"input_cost_per_token":3.3e-6,"output_cost_per_token":0.0000165,"cache_read_input_token_cost":3.3e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":4.125e-6,"cache_creation_input_token_cost_above_1hr":6.6e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/anthropic.claude-sonnet-4-6","object":"model","created":1771342990,"owned_by":"amazon","model_name":"anthropic.claude-sonnet-4-6","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"cache_read_input_token_cost":3e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":3.75e-6,"cache_creation_input_token_cost_above_1hr":6e-6},"list_pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"cache_read_input_token_cost":3e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":3.75e-6,"cache_creation_input_token_cost_above_1hr":6e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/anthropic.claude-sonnet-4-6@us","object":"model","created":1771342990,"owned_by":"amazon","model_name":"anthropic.claude-sonnet-4-6","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.3e-6,"output_cost_per_token":0.0000165,"cache_read_input_token_cost":3.3e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":4.125e-6,"cache_creation_input_token_cost_above_1hr":6.6e-6},"list_pricing":{"input_cost_per_token":3.3e-6,"output_cost_per_token":0.0000165,"cache_read_input_token_cost":3.3e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":4.125e-6,"cache_creation_input_token_cost_above_1hr":6.6e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"anthropic/claude-sonnet-4-6","object":"model","created":1771342990,"owned_by":"anthropic","model_name":"claude-sonnet-4-6","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"provider_specific_entry":{"us":1.1},"cache_read_input_token_cost":3e-7,"input_cost_per_token_batches":1.5e-6,"output_cost_per_token_batches":7.5e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":3.75e-6,"cache_read_input_token_cost_batches":1.5e-7,"cache_creation_input_token_cost_above_1hr":6e-6},"list_pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"provider_specific_entry":{"us":1.1},"cache_read_input_token_cost":3e-7,"input_cost_per_token_batches":1.5e-6,"output_cost_per_token_batches":7.5e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":3.75e-6,"cache_read_input_token_cost_batches":1.5e-7,"cache_creation_input_token_cost_above_1hr":6e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null},{"id":"vertex/claude-sonnet-4-6@eu","object":"model","created":1771342990,"owned_by":"vertex","model_name":"claude-sonnet-4-6","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.3e-6,"output_cost_per_token":0.0000165,"cache_read_input_token_cost":3.3e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":4.125e-6,"cache_creation_input_token_cost_above_1hr":6.6e-6},"list_pricing":{"input_cost_per_token":3.3e-6,"output_cost_per_token":0.0000165,"cache_read_input_token_cost":3.3e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":4.125e-6,"cache_creation_input_token_cost_above_1hr":6.6e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"vertex/claude-sonnet-4-6","object":"model","created":1771342990,"owned_by":"vertex","model_name":"claude-sonnet-4-6","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"cache_read_input_token_cost":3e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":3.75e-6,"cache_creation_input_token_cost_above_1hr":6e-6},"list_pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"cache_read_input_token_cost":3e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":3.75e-6,"cache_creation_input_token_cost_above_1hr":6e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"vertex/claude-sonnet-4-6@us","object":"model","created":1771342990,"owned_by":"vertex","model_name":"claude-sonnet-4-6","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.3e-6,"output_cost_per_token":0.0000165,"cache_read_input_token_cost":3.3e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":4.125e-6,"cache_creation_input_token_cost_above_1hr":6.6e-6},"list_pricing":{"input_cost_per_token":3.3e-6,"output_cost_per_token":0.0000165,"cache_read_input_token_cost":3.3e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":4.125e-6,"cache_creation_input_token_cost_above_1hr":6.6e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":10},{"id":"deepseek-r1-distill-qwen-32b","object":"model","created":1782119040,"owned_by":"deepseek","mode":"chat","context_length":131072,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.7e-7,"output_cost_per_token":2.7e-7},"pricing_endpoint":"deepinfra/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B","regions":[{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"cloudflare/@cf/deepseek-ai/deepseek-r1-distill-qwen-32b","object":"model","created":1782119040,"owned_by":"cloudflare","model_name":"@cf/deepseek-ai/deepseek-r1-distill-qwen-32b","context_length":80000,"max_input_tokens":80000,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4.97e-7,"output_cost_per_token":4.881e-6},"list_pricing":{"input_cost_per_token":4.97e-7,"output_cost_per_token":4.881e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"deepinfra/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B","object":"model","created":1780377273,"owned_by":"deepinfra","model_name":"deepseek-ai/DeepSeek-R1-Distill-Qwen-32B","context_length":131072,"max_input_tokens":131072,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.7e-7,"output_cost_per_token":2.7e-7},"list_pricing":{"input_cost_per_token":2.7e-7,"output_cost_per_token":2.7e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"gemini-3.1-pro","object":"model","created":1782119040,"owned_by":"google","mode":"chat","context_length":1000000,"capabilities":{"input_modalities":["text","image","audio"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.000011999999999999999},"pricing_endpoint":"deepinfra/google/gemini-3.1-pro","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"deepinfra/google/gemini-3.1-pro","object":"model","created":1782119040,"owned_by":"deepinfra","model_name":"google/gemini-3.1-pro","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage across complex workflows.","source":null,"capabilities":{"input_modalities":["text","image","audio"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.000011999999999999999},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.000011999999999999999},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":1},{"id":"gemma-4-31b-it-turbo","object":"model","created":1782119040,"owned_by":"google","mode":"chat","context_length":262144,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":9e-8,"output_cost_per_token":3.4e-7,"cache_read_input_token_cost":5.000000039999999e-8},"pricing_endpoint":"deepinfra/google/gemma-4-31B-it-turbo","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"deepinfra/google/gemma-4-31B-it-turbo","object":"model","created":1782119040,"owned_by":"deepinfra","model_name":"google/gemma-4-31B-it-turbo","context_length":262144,"max_input_tokens":262144,"max_output_tokens":null,"quantization":"fp4","retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":9e-8,"output_cost_per_token":3.4e-7,"cache_read_input_token_cost":5.000000039999999e-8},"list_pricing":{"input_cost_per_token":9e-8,"output_cost_per_token":3.4e-7,"cache_read_input_token_cost":5.000000039999999e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"gemma-sea-lion-v4-27b-it","object":"model","created":1782119040,"owned_by":"google","mode":"chat","context_length":128000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.5099999999999995e-7,"output_cost_per_token":5.550000000000001e-7},"pricing_endpoint":"cloudflare/@cf/aisingapore/gemma-sea-lion-v4-27b-it","regions":[{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"cloudflare/@cf/aisingapore/gemma-sea-lion-v4-27b-it","object":"model","created":1782119040,"owned_by":"cloudflare","model_name":"@cf/aisingapore/gemma-sea-lion-v4-27b-it","context_length":128000,"max_input_tokens":128000,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.5099999999999995e-7,"output_cost_per_token":5.550000000000001e-7},"list_pricing":{"input_cost_per_token":3.5099999999999995e-7,"output_cost_per_token":5.550000000000001e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"gpt-oss-120b-turbo","object":"model","created":1782119040,"owned_by":"openai","mode":"chat","context_length":131072,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7},"pricing_endpoint":"deepinfra/openai/gpt-oss-120b-Turbo","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"deepinfra/openai/gpt-oss-120b-Turbo","object":"model","created":1782119040,"owned_by":"deepinfra","model_name":"openai/gpt-oss-120b-Turbo","context_length":131072,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"llama-3.3-70b-instruct-fp8-fast","object":"model","created":1782119040,"owned_by":"meta","mode":"chat","context_length":24000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.93e-7,"output_cost_per_token":2.2530000000000003e-6},"pricing_endpoint":"cloudflare/@cf/meta/llama-3.3-70b-instruct-fp8-fast","regions":[{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"cloudflare/@cf/meta/llama-3.3-70b-instruct-fp8-fast","object":"model","created":1782119040,"owned_by":"cloudflare","model_name":"@cf/meta/llama-3.3-70b-instruct-fp8-fast","context_length":24000,"max_input_tokens":24000,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.93e-7,"output_cost_per_token":2.2530000000000003e-6},"list_pricing":{"input_cost_per_token":2.93e-7,"output_cost_per_token":2.2530000000000003e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"llama-4-scout-17b-16e-instruct","object":"model","created":1782119040,"owned_by":"meta","mode":"chat","context_length":327680,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.0000000000000001e-7,"output_cost_per_token":3e-7},"pricing_endpoint":"deepinfra/meta-llama/Llama-4-Scout-17B-16E-Instruct","regions":[{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"cloudflare/@cf/meta/llama-4-scout-17b-16e-instruct","object":"model","created":1782119040,"owned_by":"cloudflare","model_name":"@cf/meta/llama-4-scout-17b-16e-instruct","context_length":131000,"max_input_tokens":131000,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.7e-7,"output_cost_per_token":8.5e-7},"list_pricing":{"input_cost_per_token":2.7e-7,"output_cost_per_token":8.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"deepinfra/meta-llama/Llama-4-Scout-17B-16E-Instruct","object":"model","created":1767692616,"owned_by":"deepinfra","model_name":"meta-llama/Llama-4-Scout-17B-16E-Instruct","context_length":327680,"max_input_tokens":327680,"max_output_tokens":null,"quantization":"fp8","retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.0000000000000001e-7,"output_cost_per_token":3e-7},"list_pricing":{"input_cost_per_token":1.0000000000000001e-7,"output_cost_per_token":3e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"llama-guard-3-8b","object":"model","created":1782119040,"owned_by":"meta","mode":"chat","context_length":131072,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5.5e-8,"output_cost_per_token":5.5e-8},"pricing_endpoint":"deepinfra/meta-llama/Llama-Guard-3-8B","regions":[{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"cloudflare/@cf/meta/llama-guard-3-8b","object":"model","created":1782119040,"owned_by":"cloudflare","model_name":"@cf/meta/llama-guard-3-8b","context_length":131072,"max_input_tokens":131072,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4.839999999999999e-7,"output_cost_per_token":3e-8},"list_pricing":{"input_cost_per_token":4.839999999999999e-7,"output_cost_per_token":3e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"deepinfra/meta-llama/Llama-Guard-3-8B","object":"model","created":1780377273,"owned_by":"deepinfra","model_name":"meta-llama/Llama-Guard-3-8B","context_length":131072,"max_input_tokens":131072,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5.5e-8,"output_cost_per_token":5.5e-8},"list_pricing":{"input_cost_per_token":5.5e-8,"output_cost_per_token":5.5e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"minimax-m2.7-turbo","object":"model","created":1782119040,"owned_by":"minimax","mode":"chat","context_length":196608,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.8e-7,"output_cost_per_token":1.7e-6,"cache_read_input_token_cost":7.000000140000002e-8},"pricing_endpoint":"deepinfra/MiniMaxAI/MiniMax-M2.7-Turbo","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"deepinfra/MiniMaxAI/MiniMax-M2.7-Turbo","object":"model","created":1782119040,"owned_by":"deepinfra","model_name":"MiniMaxAI/MiniMax-M2.7-Turbo","context_length":196608,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.8e-7,"output_cost_per_token":1.7e-6,"cache_read_input_token_cost":7.000000140000002e-8},"list_pricing":{"input_cost_per_token":3.8e-7,"output_cost_per_token":1.7e-6,"cache_read_input_token_cost":7.000000140000002e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"nemotron-3-120b-a12b","object":"model","created":1782119040,"owned_by":"nvidia","mode":"chat","context_length":256000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":1.5e-6},"pricing_endpoint":"cloudflare/@cf/nvidia/nemotron-3-120b-a12b","regions":[{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"cloudflare/@cf/nvidia/nemotron-3-120b-a12b","object":"model","created":1782119040,"owned_by":"cloudflare","model_name":"@cf/nvidia/nemotron-3-120b-a12b","context_length":256000,"max_input_tokens":256000,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":1.5e-6},"list_pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":1.5e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"nemotron-3-nano-30b-a3b","object":"model","created":1782119040,"owned_by":"nvidia","mode":"chat","context_length":262144,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-8,"output_cost_per_token":2e-7,"cache_read_input_token_cost":2.5e-8},"pricing_endpoint":"deepinfra/nvidia/Nemotron-3-Nano-30B-A3B","regions":[{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"nebius/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B","object":"model","created":1782119040,"owned_by":"nebius","model_name":"nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B","context_length":262144,"max_input_tokens":262144,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6e-8,"output_cost_per_token":2.4e-7,"cache_read_input_token_cost":6e-8},"list_pricing":{"input_cost_per_token":6e-8,"output_cost_per_token":2.4e-7,"cache_read_input_token_cost":6e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"deepinfra/nvidia/Nemotron-3-Nano-30B-A3B","object":"model","created":1765731275,"owned_by":"deepinfra","model_name":"nvidia/Nemotron-3-Nano-30B-A3B","context_length":262144,"max_input_tokens":null,"max_output_tokens":228000,"quantization":null,"retirement_date":null,"description":"NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully...","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-8,"output_cost_per_token":2e-7,"cache_read_input_token_cost":2.5e-8},"list_pricing":{"input_cost_per_token":5e-8,"output_cost_per_token":2e-7,"cache_read_input_token_cost":2.5e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"nemotron-3-nano-omni-30b-a3b-reasoning","object":"model","created":1782119040,"owned_by":"nvidia","mode":"chat","context_length":262144,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.0000000000000002e-7,"output_cost_per_token":8.000000000000001e-7},"pricing_endpoint":"deepinfra/nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"deepinfra/nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning","object":"model","created":1782119040,"owned_by":"deepinfra","model_name":"nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning","context_length":262144,"max_input_tokens":null,"max_output_tokens":262144,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.0000000000000002e-7,"output_cost_per_token":8.000000000000001e-7},"list_pricing":{"input_cost_per_token":2.0000000000000002e-7,"output_cost_per_token":8.000000000000001e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"nemotron-3-ultra-550b-a55b-bf16","object":"model","created":1782119040,"owned_by":"nvidia","mode":"chat","context_length":262144,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":5e-6,"cache_read_input_token_cost":3e-7},"pricing_endpoint":"deepinfra/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"deepinfra/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","object":"model","created":1782119040,"owned_by":"deepinfra","model_name":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","context_length":262144,"max_input_tokens":null,"max_output_tokens":262144,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":5e-6,"cache_read_input_token_cost":3e-7},"list_pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":5e-6,"cache_read_input_token_cost":3e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"nemotron-content-safety-3.5","object":"model","created":1782119040,"owned_by":"nvidia","mode":"chat","context_length":131072,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.0000000000000002e-7,"output_cost_per_token":2.0000000000000002e-7},"pricing_endpoint":"deepinfra/nvidia/Nemotron-Content-Safety-3.5","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"deepinfra/nvidia/Nemotron-Content-Safety-3.5","object":"model","created":1782119040,"owned_by":"deepinfra","model_name":"nvidia/Nemotron-Content-Safety-3.5","context_length":131072,"max_input_tokens":131072,"max_output_tokens":null,"quantization":"bf16","retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.0000000000000002e-7,"output_cost_per_token":2.0000000000000002e-7},"list_pricing":{"input_cost_per_token":2.0000000000000002e-7,"output_cost_per_token":2.0000000000000002e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"qwen3-30b-a3b-fp8","object":"model","created":1782119040,"owned_by":"qwen","mode":"chat","context_length":32768,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5.09e-8,"output_cost_per_token":3.35e-7},"pricing_endpoint":"cloudflare/@cf/qwen/qwen3-30b-a3b-fp8","regions":[{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"cloudflare/@cf/qwen/qwen3-30b-a3b-fp8","object":"model","created":1782119040,"owned_by":"cloudflare","model_name":"@cf/qwen/qwen3-30b-a3b-fp8","context_length":32768,"max_input_tokens":32768,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"Qwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to excel in reasoning, multilingual support, and advanced agent tasks.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5.09e-8,"output_cost_per_token":3.35e-7},"list_pricing":{"input_cost_per_token":5.09e-8,"output_cost_per_token":3.35e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"qwen3-max","object":"model","created":1782119040,"owned_by":"qwen","mode":"chat","context_length":256000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.2e-6,"output_cost_per_token":5.999999999999999e-6,"cache_read_input_token_cost":2.4e-7},"pricing_endpoint":"deepinfra/Qwen/Qwen3-Max","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"deepinfra/Qwen/Qwen3-Max","object":"model","created":1782119040,"owned_by":"deepinfra","model_name":"Qwen/Qwen3-Max","context_length":256000,"max_input_tokens":null,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.2e-6,"output_cost_per_token":5.999999999999999e-6,"cache_read_input_token_cost":2.4e-7},"list_pricing":{"input_cost_per_token":1.2e-6,"output_cost_per_token":5.999999999999999e-6,"cache_read_input_token_cost":2.4e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"qwen3-max-thinking","object":"model","created":1782119040,"owned_by":"qwen","mode":"chat","context_length":256000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.2e-6,"output_cost_per_token":5.999999999999999e-6,"cache_read_input_token_cost":2.4e-7},"pricing_endpoint":"deepinfra/Qwen/Qwen3-Max-Thinking","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"deepinfra/Qwen/Qwen3-Max-Thinking","object":"model","created":1782119040,"owned_by":"deepinfra","model_name":"Qwen/Qwen3-Max-Thinking","context_length":256000,"max_input_tokens":null,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.2e-6,"output_cost_per_token":5.999999999999999e-6,"cache_read_input_token_cost":2.4e-7},"list_pricing":{"input_cost_per_token":1.2e-6,"output_cost_per_token":5.999999999999999e-6,"cache_read_input_token_cost":2.4e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"qwen3.7-max","object":"model","created":1782119040,"owned_by":"qwen","mode":"chat","context_length":1000000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.6250000000000001e-6,"output_cost_per_token":4.875e-6,"cache_read_input_token_cost":3.25e-7,"cache_creation_input_token_cost":2.0312500000000002e-6},"pricing_endpoint":"qwen/qwen3.7-max","regions":[{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"deepinfra/Qwen/Qwen3.7-Max","object":"model","created":1782119040,"owned_by":"deepinfra","model_name":"Qwen/Qwen3.7-Max","context_length":256000,"max_input_tokens":256000,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"Qwen3.7-Max is the flagship model in Alibaba's Qwen3.7 series.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.5e-6,"output_cost_per_token":7.5e-6,"cache_read_input_token_cost":5e-7},"list_pricing":{"input_cost_per_token":2.5e-6,"output_cost_per_token":7.5e-6,"cache_read_input_token_cost":5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"qwen/qwen3.7-max","object":"model","created":1779376861,"owned_by":"qwen","model_name":"qwen3.7-max","context_length":1000000,"max_input_tokens":991808,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"The Max model, the largest and most capable in the Qwen3.7 series, currently offers a pure‑text‑only interface for public experimentation. Qwen3.7 is a next‑generation flagship model designed for the agent‑centric era, with its core strengths lying in the breadth and depth of its agent‑level capabilities: it excels at programming, office and productivity tasks, and long‑term autonomous execution.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.6250000000000001e-6,"output_cost_per_token":4.875e-6,"cache_read_input_token_cost":3.25e-7,"cache_creation_input_token_cost":2.0312500000000002e-6},"list_pricing":{"input_cost_per_token":2.5e-6,"output_cost_per_token":7.5e-6,"cache_read_input_token_cost":5e-7,"cache_creation_input_token_cost":3.125e-6},"discount":0.35,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":2},{"id":"qwq-32b","object":"model","created":1782119040,"owned_by":"qwen","mode":"chat","context_length":131072,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":4e-7},"pricing_endpoint":"deepinfra/Qwen/QwQ-32B","regions":[{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"cloudflare/@cf/qwen/qwq-32b","object":"model","created":1782119040,"owned_by":"cloudflare","model_name":"@cf/qwen/qwq-32b","context_length":24000,"max_input_tokens":24000,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6.6e-7,"output_cost_per_token":1e-6},"list_pricing":{"input_cost_per_token":6.6e-7,"output_cost_per_token":1e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"deepinfra/Qwen/QwQ-32B","object":"model","created":1780377273,"owned_by":"deepinfra","model_name":"Qwen/QwQ-32B","context_length":131072,"max_input_tokens":131072,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":4e-7},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":4e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"seed-2.0-code","object":"model","created":1782119040,"owned_by":"bytedance","mode":"chat","context_length":256000,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":2.9999999999999997e-6,"cache_read_input_token_cost":1.0000000000000001e-7},"pricing_endpoint":"deepinfra/ByteDance/Seed-2.0-code","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"deepinfra/ByteDance/Seed-2.0-code","object":"model","created":1782119040,"owned_by":"deepinfra","model_name":"ByteDance/Seed-2.0-code","context_length":256000,"max_input_tokens":256000,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"Seed 2.0 Code is a model from ByteDance Seed optimized for agentic coding.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":2.9999999999999997e-6,"cache_read_input_token_cost":1.0000000000000001e-7},"list_pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":2.9999999999999997e-6,"cache_read_input_token_cost":1.0000000000000001e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"seed-2.0-pro","object":"model","created":1782119040,"owned_by":"bytedance","mode":"chat","context_length":256000,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":2.9999999999999997e-6,"cache_read_input_token_cost":1.0000000000000001e-7},"pricing_endpoint":"deepinfra/ByteDance/Seed-2.0-pro","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"deepinfra/ByteDance/Seed-2.0-pro","object":"model","created":1782119040,"owned_by":"deepinfra","model_name":"ByteDance/Seed-2.0-pro","context_length":256000,"max_input_tokens":256000,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":2.9999999999999997e-6,"cache_read_input_token_cost":1.0000000000000001e-7},"list_pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":2.9999999999999997e-6,"cache_read_input_token_cost":1.0000000000000001e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"claude-haiku-4-5-20251001","object":"model","created":1781775085,"owned_by":"anthropic","mode":"chat","context_length":200000,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":5e-6,"cache_read_input_token_cost":1e-7,"input_cost_per_token_batches":5e-7,"output_cost_per_token_batches":2.5e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":1.25e-6,"cache_read_input_token_cost_batches":5e-8,"cache_creation_input_token_cost_above_1hr":2e-6},"pricing_endpoint":"anthropic/claude-haiku-4-5-20251001","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"amazon/anthropic.claude-haiku-4-5-20251001-v1:0@eu","object":"model","created":1781775085,"owned_by":"amazon","model_name":"anthropic.claude-haiku-4-5-20251001-v1:0","context_length":200000,"max_input_tokens":200000,"max_output_tokens":64000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.1e-6,"output_cost_per_token":5.500000000000001e-6,"cache_read_input_token_cost":1.1e-7,"cache_creation_input_token_cost":1.3750000000000002e-6,"cache_creation_input_token_cost_above_1hr":2.2e-6},"list_pricing":{"input_cost_per_token":1.1e-6,"output_cost_per_token":5.500000000000001e-6,"cache_read_input_token_cost":1.1e-7,"cache_creation_input_token_cost":1.3750000000000002e-6,"cache_creation_input_token_cost_above_1hr":2.2e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/anthropic.claude-haiku-4-5-20251001-v1:0","object":"model","created":1781775085,"owned_by":"amazon","model_name":"anthropic.claude-haiku-4-5-20251001-v1:0","context_length":200000,"max_input_tokens":200000,"max_output_tokens":64000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":5e-6,"cache_read_input_token_cost":1e-7,"cache_creation_input_token_cost":1.25e-6,"cache_creation_input_token_cost_above_1hr":2e-6},"list_pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":5e-6,"cache_read_input_token_cost":1e-7,"cache_creation_input_token_cost":1.25e-6,"cache_creation_input_token_cost_above_1hr":2e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/anthropic.claude-haiku-4-5-20251001-v1:0@us","object":"model","created":1781775085,"owned_by":"amazon","model_name":"anthropic.claude-haiku-4-5-20251001-v1:0","context_length":200000,"max_input_tokens":200000,"max_output_tokens":64000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.1e-6,"output_cost_per_token":5.500000000000001e-6,"cache_read_input_token_cost":1.1e-7,"cache_creation_input_token_cost":1.3750000000000002e-6,"cache_creation_input_token_cost_above_1hr":2.2e-6},"list_pricing":{"input_cost_per_token":1.1e-6,"output_cost_per_token":5.500000000000001e-6,"cache_read_input_token_cost":1.1e-7,"cache_creation_input_token_cost":1.3750000000000002e-6,"cache_creation_input_token_cost_above_1hr":2.2e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"anthropic/claude-haiku-4-5-20251001","object":"model","created":1760547638,"owned_by":"anthropic","model_name":"claude-haiku-4-5-20251001","context_length":200000,"max_input_tokens":200000,"max_output_tokens":64000,"quantization":null,"retirement_date":null,"description":"Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":5e-6,"cache_read_input_token_cost":1e-7,"input_cost_per_token_batches":5e-7,"output_cost_per_token_batches":2.5e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":1.25e-6,"cache_read_input_token_cost_batches":5e-8,"cache_creation_input_token_cost_above_1hr":2e-6},"list_pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":5e-6,"cache_read_input_token_cost":1e-7,"input_cost_per_token_batches":5e-7,"output_cost_per_token_batches":2.5e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":1.25e-6,"cache_read_input_token_cost_batches":5e-8,"cache_creation_input_token_cost_above_1hr":2e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":4},{"id":"claude-opus-4-1-20250805","object":"model","created":1781775085,"owned_by":"anthropic","mode":"chat","context_length":200000,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":0.0000165,"output_cost_per_token":0.0000825,"cache_read_input_token_cost":1.65e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":0.000020625},"pricing_endpoint":"amazon/anthropic.claude-opus-4-1-20250805-v1:0","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"amazon/anthropic.claude-opus-4-1-20250805-v1:0","object":"model","created":1781775085,"owned_by":"amazon","model_name":"anthropic.claude-opus-4-1-20250805-v1:0","context_length":200000,"max_input_tokens":200000,"max_output_tokens":32000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":0.0000165,"output_cost_per_token":0.0000825,"cache_read_input_token_cost":1.65e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":0.000020625},"list_pricing":{"input_cost_per_token":0.0000165,"output_cost_per_token":0.0000825,"cache_read_input_token_cost":1.65e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":0.000020625},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"claude-opus-4-5-20251101","object":"model","created":1781775085,"owned_by":"anthropic","mode":"chat","context_length":200000,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-6,"output_cost_per_token":0.000025,"cache_read_input_token_cost":5e-7,"input_cost_per_token_batches":2.5e-6,"output_cost_per_token_batches":0.0000125,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.25e-6,"cache_read_input_token_cost_batches":2.5e-7,"cache_creation_input_token_cost_above_1hr":0.00001},"pricing_endpoint":"anthropic/claude-opus-4-5-20251101","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"amazon/anthropic.claude-opus-4-5-20251101-v1:0@eu","object":"model","created":1781775085,"owned_by":"amazon","model_name":"anthropic.claude-opus-4-5-20251101-v1:0","context_length":200000,"max_input_tokens":200000,"max_output_tokens":64000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5.500000000000001e-6,"output_cost_per_token":0.000027500000000000004,"cache_read_input_token_cost":5.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.875000000000001e-6,"cache_creation_input_token_cost_above_1hr":0.000011000000000000001},"list_pricing":{"input_cost_per_token":5.500000000000001e-6,"output_cost_per_token":0.000027500000000000004,"cache_read_input_token_cost":5.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.875000000000001e-6,"cache_creation_input_token_cost_above_1hr":0.000011000000000000001},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/anthropic.claude-opus-4-5-20251101-v1:0","object":"model","created":1781775085,"owned_by":"amazon","model_name":"anthropic.claude-opus-4-5-20251101-v1:0","context_length":200000,"max_input_tokens":200000,"max_output_tokens":64000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-6,"output_cost_per_token":0.000025,"cache_read_input_token_cost":5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.25e-6,"cache_creation_input_token_cost_above_1hr":0.00001},"list_pricing":{"input_cost_per_token":5e-6,"output_cost_per_token":0.000025,"cache_read_input_token_cost":5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.25e-6,"cache_creation_input_token_cost_above_1hr":0.00001},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/anthropic.claude-opus-4-5-20251101-v1:0@us","object":"model","created":1781775085,"owned_by":"amazon","model_name":"anthropic.claude-opus-4-5-20251101-v1:0","context_length":200000,"max_input_tokens":200000,"max_output_tokens":64000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5.500000000000001e-6,"output_cost_per_token":0.000027500000000000004,"cache_read_input_token_cost":5.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.875000000000001e-6,"cache_creation_input_token_cost_above_1hr":0.000011000000000000001},"list_pricing":{"input_cost_per_token":5.500000000000001e-6,"output_cost_per_token":0.000027500000000000004,"cache_read_input_token_cost":5.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.875000000000001e-6,"cache_creation_input_token_cost_above_1hr":0.000011000000000000001},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"anthropic/claude-opus-4-5-20251101","object":"model","created":1764010580,"owned_by":"anthropic","model_name":"claude-opus-4-5-20251101","context_length":200000,"max_input_tokens":200000,"max_output_tokens":64000,"quantization":null,"retirement_date":null,"description":"Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-6,"output_cost_per_token":0.000025,"cache_read_input_token_cost":5e-7,"input_cost_per_token_batches":2.5e-6,"output_cost_per_token_batches":0.0000125,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.25e-6,"cache_read_input_token_cost_batches":2.5e-7,"cache_creation_input_token_cost_above_1hr":0.00001},"list_pricing":{"input_cost_per_token":5e-6,"output_cost_per_token":0.000025,"cache_read_input_token_cost":5e-7,"input_cost_per_token_batches":2.5e-6,"output_cost_per_token_batches":0.0000125,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.25e-6,"cache_read_input_token_cost_batches":2.5e-7,"cache_creation_input_token_cost_above_1hr":0.00001},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":4},{"id":"claude-opus-4.6","object":"model","created":1781775085,"owned_by":"anthropic","mode":"chat","context_length":1000000,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-6,"output_cost_per_token":0.000025,"provider_specific_entry":{"us":1.1},"cache_read_input_token_cost":5e-7,"input_cost_per_token_batches":2.5e-6,"output_cost_per_token_batches":0.0000125,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.25e-6,"cache_read_input_token_cost_batches":2.5e-7,"cache_creation_input_token_cost_above_1hr":0.00001},"pricing_endpoint":"anthropic/claude-opus-4-6","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"amazon/anthropic.claude-opus-4-6-v1@eu","object":"model","created":1781775085,"owned_by":"amazon","model_name":"anthropic.claude-opus-4-6-v1","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5.500000000000001e-6,"output_cost_per_token":0.000027500000000000004,"cache_read_input_token_cost":5.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.875000000000001e-6,"cache_creation_input_token_cost_above_1hr":0.000011000000000000001},"list_pricing":{"input_cost_per_token":5.500000000000001e-6,"output_cost_per_token":0.000027500000000000004,"cache_read_input_token_cost":5.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.875000000000001e-6,"cache_creation_input_token_cost_above_1hr":0.000011000000000000001},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/anthropic.claude-opus-4-6-v1","object":"model","created":1781775085,"owned_by":"amazon","model_name":"anthropic.claude-opus-4-6-v1","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-6,"output_cost_per_token":0.000025,"cache_read_input_token_cost":5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.25e-6,"cache_creation_input_token_cost_above_1hr":0.00001},"list_pricing":{"input_cost_per_token":5e-6,"output_cost_per_token":0.000025,"cache_read_input_token_cost":5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.25e-6,"cache_creation_input_token_cost_above_1hr":0.00001},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/anthropic.claude-opus-4-6-v1@us","object":"model","created":1781775085,"owned_by":"amazon","model_name":"anthropic.claude-opus-4-6-v1","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5.500000000000001e-6,"output_cost_per_token":0.000027500000000000004,"cache_read_input_token_cost":5.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.875000000000001e-6,"cache_creation_input_token_cost_above_1hr":0.000011000000000000001},"list_pricing":{"input_cost_per_token":5.500000000000001e-6,"output_cost_per_token":0.000027500000000000004,"cache_read_input_token_cost":5.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.875000000000001e-6,"cache_creation_input_token_cost_above_1hr":0.000011000000000000001},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"databricks/databricks-claude-opus-4-6@eu","object":"model","created":1780933486,"owned_by":"databricks","model_name":"databricks-claude-opus-4-6","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Opus 4.6 is Anthropic's most capable hybrid reasoning model with adaptive thinking capabilities. This model introduces a new max effort level for the most demanding tasks, with high effort set as the default for optimal performance. Claude Opus 4.6 excels at complex reasoning, deep analysis, code generation, research, and sophisticated multi-step workflows. It features a 1 million token context window, making it ideal for enterprise applications that require both extensive analysis and comprehensive outputs. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-6,"output_cost_per_token":0.000025,"input_dbu_cost_per_token":0.000071429,"output_dbu_cost_per_token":0.00035714,"cache_read_input_token_cost":5e-7,"cache_creation_input_token_cost":6.25e-6,"cache_creation_input_token_cost_above_1hr":0.00001},"list_pricing":{"input_cost_per_token":5e-6,"output_cost_per_token":0.000025,"input_dbu_cost_per_token":0.000071429,"output_dbu_cost_per_token":0.00035714,"cache_read_input_token_cost":5e-7,"cache_creation_input_token_cost":6.25e-6,"cache_creation_input_token_cost_above_1hr":0.00001},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"databricks/databricks-claude-opus-4-6","object":"model","created":1780933486,"owned_by":"databricks","model_name":"databricks-claude-opus-4-6","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Claude Opus 4.6 is Anthropic's most capable hybrid reasoning model with adaptive thinking capabilities. This model introduces a new max effort level for the most demanding tasks, with high effort set as the default for optimal performance. Claude Opus 4.6 excels at complex reasoning, deep analysis, code generation, research, and sophisticated multi-step workflows. It features a 1 million token context window, making it ideal for enterprise applications that require both extensive analysis and comprehensive outputs. This endpoint is hosted by Databricks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-6,"output_cost_per_token":0.000025,"input_dbu_cost_per_token":0.000071429,"output_dbu_cost_per_token":0.00035714,"cache_read_input_token_cost":5e-7,"cache_creation_input_token_cost":6.25e-6,"cache_creation_input_token_cost_above_1hr":0.00001},"list_pricing":{"input_cost_per_token":5e-6,"output_cost_per_token":0.000025,"input_dbu_cost_per_token":0.000071429,"output_dbu_cost_per_token":0.00035714,"cache_read_input_token_cost":5e-7,"cache_creation_input_token_cost":6.25e-6,"cache_creation_input_token_cost_above_1hr":0.00001},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"anthropic/claude-opus-4-6","object":"model","created":1770219050,"owned_by":"anthropic","model_name":"claude-opus-4-6","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-6,"output_cost_per_token":0.000025,"provider_specific_entry":{"us":1.1},"cache_read_input_token_cost":5e-7,"input_cost_per_token_batches":2.5e-6,"output_cost_per_token_batches":0.0000125,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.25e-6,"cache_read_input_token_cost_batches":2.5e-7,"cache_creation_input_token_cost_above_1hr":0.00001},"list_pricing":{"input_cost_per_token":5e-6,"output_cost_per_token":0.000025,"provider_specific_entry":{"us":1.1},"cache_read_input_token_cost":5e-7,"input_cost_per_token_batches":2.5e-6,"output_cost_per_token_batches":0.0000125,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.25e-6,"cache_read_input_token_cost_batches":2.5e-7,"cache_creation_input_token_cost_above_1hr":0.00001},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null},{"id":"vertex/claude-opus-4-6@eu","object":"model","created":1770219050,"owned_by":"vertex","model_name":"claude-opus-4-6","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5.500000000000001e-6,"output_cost_per_token":0.000027500000000000004,"cache_read_input_token_cost":5.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.875000000000001e-6,"cache_creation_input_token_cost_above_1hr":0.000011000000000000001},"list_pricing":{"input_cost_per_token":5.500000000000001e-6,"output_cost_per_token":0.000027500000000000004,"cache_read_input_token_cost":5.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.875000000000001e-6,"cache_creation_input_token_cost_above_1hr":0.000011000000000000001},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"vertex/claude-opus-4-6","object":"model","created":1770219050,"owned_by":"vertex","model_name":"claude-opus-4-6","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-6,"output_cost_per_token":0.000025,"cache_read_input_token_cost":5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.25e-6,"cache_creation_input_token_cost_above_1hr":0.00001},"list_pricing":{"input_cost_per_token":5e-6,"output_cost_per_token":0.000025,"cache_read_input_token_cost":5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.25e-6,"cache_creation_input_token_cost_above_1hr":0.00001},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"vertex/claude-opus-4-6@us","object":"model","created":1770219050,"owned_by":"vertex","model_name":"claude-opus-4-6","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5.500000000000001e-6,"output_cost_per_token":0.000027500000000000004,"cache_read_input_token_cost":5.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.875000000000001e-6,"cache_creation_input_token_cost_above_1hr":0.000011000000000000001},"list_pricing":{"input_cost_per_token":5.500000000000001e-6,"output_cost_per_token":0.000027500000000000004,"cache_read_input_token_cost":5.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.875000000000001e-6,"cache_creation_input_token_cost_above_1hr":0.000011000000000000001},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":9},{"id":"claude-sonnet-4-5-20250929","object":"model","created":1781775085,"owned_by":"anthropic","mode":"chat","context_length":1000000,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"cache_read_input_token_cost":3e-7,"input_cost_per_token_batches":1.5e-6,"output_cost_per_token_batches":7.5e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":3.75e-6,"cache_read_input_token_cost_batches":1.5e-7,"input_cost_per_token_above_200k_tokens":6e-6,"output_cost_per_token_above_200k_tokens":0.0000225,"cache_creation_input_token_cost_above_1hr":6e-6,"cache_read_input_token_cost_above_200k_tokens":6e-7,"cache_creation_input_token_cost_above_200k_tokens":7.5e-6,"cache_creation_input_token_cost_above_1hr_above_200k_tokens":0.000012},"pricing_endpoint":"anthropic/claude-sonnet-4-5-20250929","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"amazon/anthropic.claude-sonnet-4-5-20250929-v1:0@eu","object":"model","created":1781775085,"owned_by":"amazon","model_name":"anthropic.claude-sonnet-4-5-20250929-v1:0","context_length":200000,"max_input_tokens":200000,"max_output_tokens":64000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.3e-6,"output_cost_per_token":0.0000165,"cache_read_input_token_cost":3.3e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":4.125e-6,"input_cost_per_token_above_200k_tokens":6.6e-6,"output_cost_per_token_above_200k_tokens":0.000024750000000000002,"cache_creation_input_token_cost_above_1hr":6.6e-6,"cache_read_input_token_cost_above_200k_tokens":6.6e-7,"cache_creation_input_token_cost_above_200k_tokens":8.25e-6,"cache_creation_input_token_cost_above_1hr_above_200k_tokens":0.0000132},"list_pricing":{"input_cost_per_token":3.3e-6,"output_cost_per_token":0.0000165,"cache_read_input_token_cost":3.3e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":4.125e-6,"input_cost_per_token_above_200k_tokens":6.6e-6,"output_cost_per_token_above_200k_tokens":0.000024750000000000002,"cache_creation_input_token_cost_above_1hr":6.6e-6,"cache_read_input_token_cost_above_200k_tokens":6.6e-7,"cache_creation_input_token_cost_above_200k_tokens":8.25e-6,"cache_creation_input_token_cost_above_1hr_above_200k_tokens":0.0000132},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/anthropic.claude-sonnet-4-5-20250929-v1:0","object":"model","created":1781775085,"owned_by":"amazon","model_name":"anthropic.claude-sonnet-4-5-20250929-v1:0","context_length":200000,"max_input_tokens":200000,"max_output_tokens":64000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"cache_read_input_token_cost":3e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":3.75e-6,"input_cost_per_token_above_200k_tokens":6e-6,"output_cost_per_token_above_200k_tokens":0.0000225,"cache_creation_input_token_cost_above_1hr":6e-6,"cache_read_input_token_cost_above_200k_tokens":6e-7,"cache_creation_input_token_cost_above_200k_tokens":7.5e-6,"cache_creation_input_token_cost_above_1hr_above_200k_tokens":0.000012},"list_pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"cache_read_input_token_cost":3e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":3.75e-6,"input_cost_per_token_above_200k_tokens":6e-6,"output_cost_per_token_above_200k_tokens":0.0000225,"cache_creation_input_token_cost_above_1hr":6e-6,"cache_read_input_token_cost_above_200k_tokens":6e-7,"cache_creation_input_token_cost_above_200k_tokens":7.5e-6,"cache_creation_input_token_cost_above_1hr_above_200k_tokens":0.000012},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/anthropic.claude-sonnet-4-5-20250929-v1:0@us","object":"model","created":1781775085,"owned_by":"amazon","model_name":"anthropic.claude-sonnet-4-5-20250929-v1:0","context_length":200000,"max_input_tokens":200000,"max_output_tokens":64000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.3e-6,"output_cost_per_token":0.0000165,"cache_read_input_token_cost":3.3e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":4.125e-6,"input_cost_per_token_above_200k_tokens":6.6e-6,"output_cost_per_token_above_200k_tokens":0.000024750000000000002,"cache_creation_input_token_cost_above_1hr":6.6e-6,"cache_read_input_token_cost_above_200k_tokens":6.6e-7,"cache_creation_input_token_cost_above_200k_tokens":8.25e-6,"cache_creation_input_token_cost_above_1hr_above_200k_tokens":0.0000132},"list_pricing":{"input_cost_per_token":3.3e-6,"output_cost_per_token":0.0000165,"cache_read_input_token_cost":3.3e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":4.125e-6,"input_cost_per_token_above_200k_tokens":6.6e-6,"output_cost_per_token_above_200k_tokens":0.000024750000000000002,"cache_creation_input_token_cost_above_1hr":6.6e-6,"cache_read_input_token_cost_above_200k_tokens":6.6e-7,"cache_creation_input_token_cost_above_200k_tokens":8.25e-6,"cache_creation_input_token_cost_above_1hr_above_200k_tokens":0.0000132},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"anthropic/claude-sonnet-4-5-20250929","object":"model","created":1759161676,"owned_by":"anthropic","model_name":"claude-sonnet-4-5-20250929","context_length":1000000,"max_input_tokens":200000,"max_output_tokens":64000,"quantization":null,"retirement_date":null,"description":"Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"cache_read_input_token_cost":3e-7,"input_cost_per_token_batches":1.5e-6,"output_cost_per_token_batches":7.5e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":3.75e-6,"cache_read_input_token_cost_batches":1.5e-7,"input_cost_per_token_above_200k_tokens":6e-6,"output_cost_per_token_above_200k_tokens":0.0000225,"cache_creation_input_token_cost_above_1hr":6e-6,"cache_read_input_token_cost_above_200k_tokens":6e-7,"cache_creation_input_token_cost_above_200k_tokens":7.5e-6,"cache_creation_input_token_cost_above_1hr_above_200k_tokens":0.000012},"list_pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"cache_read_input_token_cost":3e-7,"input_cost_per_token_batches":1.5e-6,"output_cost_per_token_batches":7.5e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":3.75e-6,"cache_read_input_token_cost_batches":1.5e-7,"input_cost_per_token_above_200k_tokens":6e-6,"output_cost_per_token_above_200k_tokens":0.0000225,"cache_creation_input_token_cost_above_1hr":6e-6,"cache_read_input_token_cost_above_200k_tokens":6e-7,"cache_creation_input_token_cost_above_200k_tokens":7.5e-6,"cache_creation_input_token_cost_above_1hr_above_200k_tokens":0.000012},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":4},{"id":"deepseek-r1","object":"model","created":1781775085,"owned_by":"deepseek","mode":"chat","context_length":163840,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":7e-7,"output_cost_per_token":2.4e-6},"pricing_endpoint":"deepinfra/deepseek-ai/DeepSeek-R1","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"amazon/deepseek.r1-v1:0","object":"model","created":1781775085,"owned_by":"amazon","model_name":"deepseek.r1-v1:0","context_length":128000,"max_input_tokens":128000,"max_output_tokens":8192,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.35e-6,"output_cost_per_token":5.4e-6},"list_pricing":{"input_cost_per_token":1.35e-6,"output_cost_per_token":5.4e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"deepinfra/deepseek-ai/DeepSeek-R1","object":"model","created":1780377273,"owned_by":"deepinfra","model_name":"deepseek-ai/DeepSeek-R1","context_length":163840,"max_input_tokens":163840,"max_output_tokens":163840,"quantization":null,"retirement_date":null,"description":"","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":7e-7,"output_cost_per_token":2.4e-6},"list_pricing":{"input_cost_per_token":7e-7,"output_cost_per_token":2.4e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"llama-3.1-70b-instruct","object":"model","created":1781775085,"owned_by":"meta","mode":"chat","context_length":131072,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4e-7,"output_cost_per_token":4e-7},"pricing_endpoint":"deepinfra/meta-llama/Meta-Llama-3.1-70B-Instruct","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"amazon/meta.llama3-1-70b-instruct-v1:0","object":"model","created":1781775085,"owned_by":"amazon","model_name":"meta.llama3-1-70b-instruct-v1:0","context_length":128000,"max_input_tokens":128000,"max_output_tokens":4096,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":7.2e-7,"output_cost_per_token":7.2e-7},"list_pricing":{"input_cost_per_token":7.2e-7,"output_cost_per_token":7.2e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"deepinfra/meta-llama/Meta-Llama-3.1-70B-Instruct","object":"model","created":1767692616,"owned_by":"deepinfra","model_name":"meta-llama/Meta-Llama-3.1-70B-Instruct","context_length":131072,"max_input_tokens":131072,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4e-7,"output_cost_per_token":4e-7},"list_pricing":{"input_cost_per_token":4e-7,"output_cost_per_token":4e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"llama-3.1-8b-instruct","object":"model","created":1781775085,"owned_by":"meta","mode":"chat","context_length":131072,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-8,"output_cost_per_token":5.0000000000000004e-8},"pricing_endpoint":"deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct","regions":[{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"amazon/meta.llama3-1-8b-instruct-v1:0","object":"model","created":1781775085,"owned_by":"amazon","model_name":"meta.llama3-1-8b-instruct-v1:0","context_length":128000,"max_input_tokens":128000,"max_output_tokens":4096,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.2e-7,"output_cost_per_token":2.2e-7},"list_pricing":{"input_cost_per_token":2.2e-7,"output_cost_per_token":2.2e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"databricks/databricks-meta-llama-3-1-8b-instruct","object":"model","created":1769507058,"owned_by":"databricks","model_name":"databricks-meta-llama-3-1-8b-instruct","context_length":128000,"max_input_tokens":128000,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"Llama 3.1 is a state-of-the-art 8B parameter dense language model trained and released by Meta. The model supports a context length of 128K tokens. The model is optimized for multilingual dialogue use cases and aligned with human preferences for helpfulness and safety. It is not intended for use in languages other than English. Meta Llama 3.1 is licensed under the Meta Llama 3.1 Community License, Copyright © Meta Platforms, Inc. All Rights Reserved. Customers are responsible for ensuring compliance with applicable model licenses.","source":"https://www.databricks.com/product/pricing/foundation-model-serving","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":4.5e-7,"input_dbu_cost_per_token":2.1429999999999996e-6,"output_dbu_cost_per_token":6.429000000000001e-6,"cache_read_input_token_cost":1.5e-8,"cache_creation_input_token_cost":1.5e-7},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":4.5e-7,"input_dbu_cost_per_token":2.1429999999999996e-6,"output_dbu_cost_per_token":6.429000000000001e-6,"cache_read_input_token_cost":1.5e-8,"cache_creation_input_token_cost":1.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct","object":"model","created":1767692616,"owned_by":"deepinfra","model_name":"meta-llama/Meta-Llama-3.1-8B-Instruct","context_length":131072,"max_input_tokens":null,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-8,"output_cost_per_token":5.0000000000000004e-8},"list_pricing":{"input_cost_per_token":2e-8,"output_cost_per_token":5.0000000000000004e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":3},{"id":"palmyra-x4","object":"model","created":1781775085,"owned_by":"writer","mode":"chat","context_length":128000,"capabilities":{"input_modalities":["text","file"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.5e-6,"output_cost_per_token":0.00001},"pricing_endpoint":"amazon/writer.palmyra-x4-v1:0","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"amazon/writer.palmyra-x4-v1:0","object":"model","created":1781775085,"owned_by":"amazon","model_name":"writer.palmyra-x4-v1:0","context_length":128000,"max_input_tokens":128000,"max_output_tokens":8192,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","file"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.5e-6,"output_cost_per_token":0.00001},"list_pricing":{"input_cost_per_token":2.5e-6,"output_cost_per_token":0.00001},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"palmyra-x5","object":"model","created":1781775085,"owned_by":"writer","mode":"chat","context_length":128000,"capabilities":{"input_modalities":["text","file"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6e-7,"output_cost_per_token":6e-6},"pricing_endpoint":"amazon/writer.palmyra-x5-v1:0","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"amazon/writer.palmyra-x5-v1:0","object":"model","created":1781775085,"owned_by":"amazon","model_name":"writer.palmyra-x5-v1:0","context_length":128000,"max_input_tokens":128000,"max_output_tokens":8192,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","file"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6e-7,"output_cost_per_token":6e-6},"list_pricing":{"input_cost_per_token":6e-7,"output_cost_per_token":6e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"pixtral-large-2502","object":"model","created":1781775085,"owned_by":"mistral","mode":"chat","context_length":128000,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":6e-6},"pricing_endpoint":"amazon/mistral.pixtral-large-2502-v1:0","regions":[{"code":"eu","name":"Europe"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"amazon/mistral.pixtral-large-2502-v1:0","object":"model","created":1781775085,"owned_by":"amazon","model_name":"mistral.pixtral-large-2502-v1:0","context_length":128000,"max_input_tokens":128000,"max_output_tokens":16384,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":6e-6},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":6e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/mistral.pixtral-large-2502-v1:0@us","object":"model","created":1781775085,"owned_by":"amazon","model_name":"mistral.pixtral-large-2502-v1:0","context_length":128000,"max_input_tokens":128000,"max_output_tokens":16384,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":6e-6},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":6e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"gemini-3.1-flash-image","object":"model","created":1781754065,"owned_by":"google","mode":"chat","context_length":131072,"capabilities":{"input_modalities":["image","text"],"output_modalities":["image","text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":3e-6,"output_cost_per_image_token":0.00006,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014}},"pricing_endpoint":"google/gemini-3.1-flash-image","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"vertex/gemini-3.1-flash-image","object":"model","created":1781754065,"owned_by":"vertex","model_name":"gemini-3.1-flash-image","context_length":131072,"max_input_tokens":null,"max_output_tokens":32768,"quantization":null,"retirement_date":null,"description":"Gemini 3.1 Flash Image, a.k.a. \"Nano Banana 2,\" is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed.","source":null,"capabilities":{"input_modalities":["image","text"],"output_modalities":["image","text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":3e-6,"output_cost_per_image_token":0.00006,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014}},"list_pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":3e-6,"output_cost_per_image_token":0.00006,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014}},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"google/gemini-3.1-flash-image","object":"model","created":1772119558,"owned_by":"google","model_name":"gemini-3.1-flash-image","context_length":65536,"max_input_tokens":65536,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"Gemini 3.1 Flash Image, a.k.a. \"Nano Banana 2,\" is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed.","source":null,"capabilities":{"input_modalities":["image","text"],"output_modalities":["image","text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":3e-6,"output_cost_per_image_token":0.00006,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014}},"list_pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":3e-6,"output_cost_per_image_token":0.00006,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014}},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":2},{"id":"gemini-3-pro-image","object":"model","created":1781754054,"owned_by":"google","mode":"chat","context_length":65536,"capabilities":{"input_modalities":["image","text"],"output_modalities":["image","text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.000012,"input_cost_per_audio_token":2e-6,"input_cost_per_image_token":2e-6,"cache_read_input_token_cost":2e-7,"output_cost_per_image_token":0.00012,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"cache_creation_input_token_cost":3.75e-7,"output_cost_per_reasoning_token":0.000012,"cache_read_input_audio_token_cost":2e-7},"pricing_endpoint":"google/gemini-3-pro-image","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"vertex/gemini-3-pro-image","object":"model","created":1781754054,"owned_by":"vertex","model_name":"gemini-3-pro-image","context_length":65536,"max_input_tokens":null,"max_output_tokens":32768,"quantization":null,"retirement_date":null,"description":"Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro.","source":null,"capabilities":{"input_modalities":["image","text"],"output_modalities":["image","text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.000012,"input_cost_per_audio_token":2e-6,"input_cost_per_image_token":2e-6,"cache_read_input_token_cost":2e-7,"output_cost_per_image_token":0.00012,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"cache_creation_input_token_cost":3.75e-7,"output_cost_per_reasoning_token":0.000012,"cache_read_input_audio_token_cost":2e-7},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.000012,"input_cost_per_audio_token":2e-6,"input_cost_per_image_token":2e-6,"cache_read_input_token_cost":2e-7,"output_cost_per_image_token":0.00012,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"cache_creation_input_token_cost":3.75e-7,"output_cost_per_reasoning_token":0.000012,"cache_read_input_audio_token_cost":2e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"google/gemini-3-pro-image","object":"model","created":1763653797,"owned_by":"google","model_name":"gemini-3-pro-image","context_length":65536,"max_input_tokens":131072,"max_output_tokens":32768,"quantization":null,"retirement_date":null,"description":"Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro.","source":null,"capabilities":{"input_modalities":["image","text"],"output_modalities":["image","text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.000012,"input_cost_per_audio_token":2e-6,"input_cost_per_image_token":2e-6,"cache_read_input_token_cost":2e-7,"output_cost_per_image_token":0.00012,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"cache_creation_input_token_cost":3.75e-7,"output_cost_per_reasoning_token":0.000012,"cache_read_input_audio_token_cost":2e-7},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.000012,"input_cost_per_audio_token":2e-6,"input_cost_per_image_token":2e-6,"cache_read_input_token_cost":2e-7,"output_cost_per_image_token":0.00012,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"cache_creation_input_token_cost":3.75e-7,"output_cost_per_reasoning_token":0.000012,"cache_read_input_audio_token_cost":2e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":2},{"id":"codestral-latest","object":"model","created":1780673223,"owned_by":"mistral","mode":"chat","context_length":256000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":9e-7,"cache_read_input_token_cost":3e-8,"input_cost_per_token_batches":1.5e-7,"output_cost_per_token_batches":4.5e-7,"cache_read_input_token_cost_batches":1.5e-8},"pricing_endpoint":"mistral/codestral-latest","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"mistral/codestral-latest@eu","object":"model","created":1780673223,"owned_by":"mistral","model_name":"codestral-latest","context_length":256000,"max_input_tokens":128000,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.3e-7,"output_cost_per_token":9.9e-7,"cache_read_input_token_cost":3.3e-8,"input_cost_per_token_batches":1.65e-7,"output_cost_per_token_batches":4.95e-7,"cache_read_input_token_cost_batches":1.65e-8},"list_pricing":{"input_cost_per_token":3.3e-7,"output_cost_per_token":9.9e-7,"cache_read_input_token_cost":3.3e-8,"input_cost_per_token_batches":1.65e-7,"output_cost_per_token_batches":4.95e-7,"cache_read_input_token_cost_batches":1.65e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"mistral/codestral-latest","object":"model","created":1780673223,"owned_by":"mistral","model_name":"codestral-latest","context_length":256000,"max_input_tokens":128000,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":9e-7,"cache_read_input_token_cost":3e-8,"input_cost_per_token_batches":1.5e-7,"output_cost_per_token_batches":4.5e-7,"cache_read_input_token_cost_batches":1.5e-8},"list_pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":9e-7,"cache_read_input_token_cost":3e-8,"input_cost_per_token_batches":1.5e-7,"output_cost_per_token_batches":4.5e-7,"cache_read_input_token_cost_batches":1.5e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"mistral-tiny-latest","object":"model","created":1780673223,"owned_by":"mistral","mode":"chat","context_length":131072,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.5e-7,"output_cost_per_token":2.5e-7},"pricing_endpoint":"mistral/mistral-tiny-latest","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"mistral/mistral-tiny-latest@eu","object":"model","created":1780673223,"owned_by":"mistral","model_name":"mistral-tiny-latest","context_length":131072,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":"2026-07-31","description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.75e-7,"output_cost_per_token":2.75e-7},"list_pricing":{"input_cost_per_token":2.75e-7,"output_cost_per_token":2.75e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"mistral/mistral-tiny-latest","object":"model","created":1780673223,"owned_by":"mistral","model_name":"mistral-tiny-latest","context_length":131072,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":"2026-07-31","description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.5e-7,"output_cost_per_token":2.5e-7},"list_pricing":{"input_cost_per_token":2.5e-7,"output_cost_per_token":2.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"grok-4.20-0309-non-reasoning","object":"model","created":1780673222,"owned_by":"xai","mode":"chat","context_length":1000000,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":2.5e-6,"input_cost_per_image_token":1.25e-6,"cache_read_input_token_cost":2e-7,"input_cost_per_token_above_200k_tokens":2.5e-6,"output_cost_per_token_above_200k_tokens":5e-6,"cache_read_input_token_cost_above_200k_tokens":4e-7},"pricing_endpoint":"xai/grok-4.20-0309-non-reasoning","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"xai/grok-4.20-0309-non-reasoning","object":"model","created":1780673222,"owned_by":"xai","model_name":"grok-4.20-0309-non-reasoning","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":2.5e-6,"input_cost_per_image_token":1.25e-6,"cache_read_input_token_cost":2e-7,"input_cost_per_token_above_200k_tokens":2.5e-6,"output_cost_per_token_above_200k_tokens":5e-6,"cache_read_input_token_cost_above_200k_tokens":4e-7},"list_pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":2.5e-6,"input_cost_per_image_token":1.25e-6,"cache_read_input_token_cost":2e-7,"input_cost_per_token_above_200k_tokens":2.5e-6,"output_cost_per_token_above_200k_tokens":5e-6,"cache_read_input_token_cost_above_200k_tokens":4e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"qwen2-1.5b-instruct","object":"model","created":1780673222,"owned_by":"qwen","mode":"chat","context_length":32768,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.0000000000000001e-7,"output_cost_per_token":1.0000000000000001e-7},"pricing_endpoint":"together_ai/arize-ai/qwen-2-1.5b-instruct","regions":[{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"together_ai/arize-ai/qwen-2-1.5b-instruct","object":"model","created":1780673222,"owned_by":"together_ai","model_name":"arize-ai/qwen-2-1.5b-instruct","context_length":32768,"max_input_tokens":32768,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.0000000000000001e-7,"output_cost_per_token":1.0000000000000001e-7},"list_pricing":{"input_cost_per_token":1.0000000000000001e-7,"output_cost_per_token":1.0000000000000001e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":1},{"id":"qwen3.7-plus","object":"model","created":1780491783,"owned_by":"qwen","mode":"chat","context_length":1000000,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"tiered_pricing":[{"range":[0,256000],"input_cost_per_token":2.6000000000000005e-7,"output_cost_per_token":1.0400000000000002e-6,"cache_read_input_token_cost":5.2e-8,"cache_creation_input_token_cost":3.25e-7},{"range":[256000,1000000],"input_cost_per_token":7.799999999999999e-7,"output_cost_per_token":3.1199999999999998e-6,"cache_read_input_token_cost":1.56e-7,"cache_creation_input_token_cost":9.75e-7}],"input_cost_per_token":2.6000000000000005e-7,"output_cost_per_token":1.0400000000000002e-6,"cache_read_input_token_cost":5.2e-8,"cache_creation_input_token_cost":3.25e-7},"pricing_endpoint":"qwen/qwen3.7-plus","regions":[{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"qwen/qwen3.7-plus","object":"model","created":1780491783,"owned_by":"qwen","model_name":"qwen3.7-plus","context_length":1000000,"max_input_tokens":991808,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"Among the Qwen3.7 series, the cost-effective Plus model builds on its robust text capabilities while delivering a comprehensive upgrade to its vision‑language abilities, all while preserving its full‑stack agent‑level intelligence for coding, tool use, and productivity workflows. Its key distinguishing feature is multi‑modal interactive hybrid agent capabilities, enabling it to perceive real‑world scenes, read screens and interact with GUIs, generate code based on visual references, and perform end‑to‑end navigation within mobile apps.","source":null,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"tiered_pricing":[{"range":[0,256000],"input_cost_per_token":2.6000000000000005e-7,"output_cost_per_token":1.0400000000000002e-6,"cache_read_input_token_cost":5.2e-8,"cache_creation_input_token_cost":3.25e-7},{"range":[256000,1000000],"input_cost_per_token":7.799999999999999e-7,"output_cost_per_token":3.1199999999999998e-6,"cache_read_input_token_cost":1.56e-7,"cache_creation_input_token_cost":9.75e-7}],"input_cost_per_token":2.6000000000000005e-7,"output_cost_per_token":1.0400000000000002e-6,"cache_read_input_token_cost":5.2e-8,"cache_creation_input_token_cost":3.25e-7},"list_pricing":{"tiered_pricing":[{"range":[0,256000],"input_cost_per_token":4.0000000000000003e-7,"output_cost_per_token":1.6000000000000001e-6,"cache_read_input_token_cost":8e-8,"cache_creation_input_token_cost":5e-7},{"range":[256000,1000000],"input_cost_per_token":1.2e-6,"output_cost_per_token":4.8e-6,"cache_read_input_token_cost":2.4e-7,"cache_creation_input_token_cost":1.5e-6}],"input_cost_per_token":4.0000000000000003e-7,"output_cost_per_token":1.6000000000000001e-6,"cache_read_input_token_cost":8e-8,"cache_creation_input_token_cost":5e-7},"discount":0.35,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":1},{"id":"qwen3.7-plus-2026-05-26","object":"model","created":1780491783,"owned_by":"qwen","mode":"chat","context_length":1000000,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"tiered_pricing":[{"range":[0,256000],"input_cost_per_token":2.6000000000000005e-7,"output_cost_per_token":1.0400000000000002e-6,"cache_read_input_token_cost":5.2e-8,"cache_creation_input_token_cost":3.25e-7},{"range":[256000,1000000],"input_cost_per_token":7.799999999999999e-7,"output_cost_per_token":3.1199999999999998e-6,"cache_read_input_token_cost":1.56e-7,"cache_creation_input_token_cost":9.75e-7}],"input_cost_per_token":2.6000000000000005e-7,"output_cost_per_token":1.0400000000000002e-6,"cache_read_input_token_cost":5.2e-8,"cache_creation_input_token_cost":3.25e-7},"pricing_endpoint":"qwen/qwen3.7-plus-2026-05-26","regions":[{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"qwen/qwen3.7-plus-2026-05-26","object":"model","created":1780491783,"owned_by":"qwen","model_name":"qwen3.7-plus-2026-05-26","context_length":1000000,"max_input_tokens":991808,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"Among the Qwen3.7 series, the cost-effective Plus model builds on its robust text capabilities while delivering a comprehensive upgrade to its vision‑language abilities, all while preserving its full‑stack agent‑level intelligence for coding, tool use, and productivity workflows. Its key distinguishing feature is multi‑modal interactive hybrid agent capabilities, enabling it to perceive real‑world scenes, read screens and interact with GUIs, generate code based on visual references, and perform end‑to‑end navigation within mobile apps.This version is a snapshot as of May 26, 2026.","source":null,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"tiered_pricing":[{"range":[0,256000],"input_cost_per_token":2.6000000000000005e-7,"output_cost_per_token":1.0400000000000002e-6,"cache_read_input_token_cost":5.2e-8,"cache_creation_input_token_cost":3.25e-7},{"range":[256000,1000000],"input_cost_per_token":7.799999999999999e-7,"output_cost_per_token":3.1199999999999998e-6,"cache_read_input_token_cost":1.56e-7,"cache_creation_input_token_cost":9.75e-7}],"input_cost_per_token":2.6000000000000005e-7,"output_cost_per_token":1.0400000000000002e-6,"cache_read_input_token_cost":5.2e-8,"cache_creation_input_token_cost":3.25e-7},"list_pricing":{"tiered_pricing":[{"range":[0,256000],"input_cost_per_token":4.0000000000000003e-7,"output_cost_per_token":1.6000000000000001e-6,"cache_read_input_token_cost":8e-8,"cache_creation_input_token_cost":5e-7},{"range":[256000,1000000],"input_cost_per_token":1.2e-6,"output_cost_per_token":4.8e-6,"cache_read_input_token_cost":2.4e-7,"cache_creation_input_token_cost":1.5e-6}],"input_cost_per_token":4.0000000000000003e-7,"output_cost_per_token":1.6000000000000001e-6,"cache_read_input_token_cost":8e-8,"cache_creation_input_token_cost":5e-7},"discount":0.35,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":1},{"id":"deepseek-r1-turbo","object":"model","created":1780377273,"owned_by":"deepseek","mode":"chat","context_length":40960,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":3e-6},"pricing_endpoint":"deepinfra/deepseek-ai/DeepSeek-R1-Turbo","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"deepinfra/deepseek-ai/DeepSeek-R1-Turbo","object":"model","created":1780377273,"owned_by":"deepinfra","model_name":"deepseek-ai/DeepSeek-R1-Turbo","context_length":40960,"max_input_tokens":40960,"max_output_tokens":40960,"quantization":null,"retirement_date":null,"description":"","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":3e-6},"list_pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":3e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"glm-4.5","object":"model","created":1780377273,"owned_by":"zai","mode":"chat","context_length":131072,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4e-7,"output_cost_per_token":1.6e-6},"pricing_endpoint":"deepinfra/zai-org/GLM-4.5","regions":[{"code":"ap","name":"Asia"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"deepinfra/zai-org/GLM-4.5","object":"model","created":1780377273,"owned_by":"deepinfra","model_name":"zai-org/GLM-4.5","context_length":131072,"max_input_tokens":131072,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4e-7,"output_cost_per_token":1.6e-6},"list_pricing":{"input_cost_per_token":4e-7,"output_cost_per_token":1.6e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"zai/glm-4.5","object":"model","created":1753471347,"owned_by":"zai","model_name":"glm-4.5","context_length":131072,"max_input_tokens":128000,"max_output_tokens":98304,"quantization":"fp8","retirement_date":"2026-12-31","description":"GLM-4.5 is our latest flagship foundation model, purpose-built for agent-based applications. It leverages a Mixture-of-Experts (MoE) architecture and supports a context length of up to 128k tokens.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6e-7,"output_cost_per_token":2.2e-6,"cache_read_input_token_cost":1.1e-7},"list_pricing":{"input_cost_per_token":6e-7,"output_cost_per_token":2.2e-6,"cache_read_input_token_cost":1.1e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"ap","name":"Asia"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"kimi-k2-instruct","object":"model","created":1780377273,"owned_by":"moonshot","mode":"chat","context_length":131072,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":2e-6},"pricing_endpoint":"deepinfra/moonshotai/Kimi-K2-Instruct","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"deepinfra/moonshotai/Kimi-K2-Instruct","object":"model","created":1780377273,"owned_by":"deepinfra","model_name":"moonshotai/Kimi-K2-Instruct","context_length":131072,"max_input_tokens":131072,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":2e-6},"list_pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":2e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"llama-3.2-3b-instruct","object":"model","created":1780377273,"owned_by":"meta","mode":"chat","context_length":131072,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-8,"output_cost_per_token":2e-8},"pricing_endpoint":"deepinfra/meta-llama/Llama-3.2-3B-Instruct","regions":[{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"deepinfra/meta-llama/Llama-3.2-3B-Instruct","object":"model","created":1780377273,"owned_by":"deepinfra","model_name":"meta-llama/Llama-3.2-3B-Instruct","context_length":131072,"max_input_tokens":131072,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-8,"output_cost_per_token":2e-8},"list_pricing":{"input_cost_per_token":2e-8,"output_cost_per_token":2e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"cloudflare/@cf/meta/llama-3.2-3b-instruct","object":"model","created":1727222400,"owned_by":"cloudflare","model_name":"@cf/meta/llama-3.2-3b-instruct","context_length":80000,"max_input_tokens":80000,"max_output_tokens":null,"quantization":null,"retirement_date":"2026-11-20","description":"Llama 3.2 3B is a 3-billion-parameter multilingual large language model, optimized for advanced natural language processing tasks like dialogue generation, reasoning, and summarization.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5.09e-8,"output_cost_per_token":3.35e-7},"list_pricing":{"input_cost_per_token":5.09e-8,"output_cost_per_token":3.35e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"olmocr-7b-0725-fp8","object":"model","created":1780377273,"owned_by":"allenai","mode":"chat","context_length":16384,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.7e-7,"output_cost_per_token":1.5e-6},"pricing_endpoint":"deepinfra/allenai/olmOCR-7B-0725-FP8","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"deepinfra/allenai/olmOCR-7B-0725-FP8","object":"model","created":1780377273,"owned_by":"deepinfra","model_name":"allenai/olmOCR-7B-0725-FP8","context_length":16384,"max_input_tokens":16384,"max_output_tokens":16384,"quantization":null,"retirement_date":null,"description":"","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.7e-7,"output_cost_per_token":1.5e-6},"list_pricing":{"input_cost_per_token":2.7e-7,"output_cost_per_token":1.5e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"qwen2.5-7b-instruct","object":"model","created":1780377273,"owned_by":"qwen","mode":"chat","context_length":32768,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4e-8,"output_cost_per_token":1e-7},"pricing_endpoint":"deepinfra/Qwen/Qwen2.5-7B-Instruct","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"deepinfra/Qwen/Qwen2.5-7B-Instruct","object":"model","created":1780377273,"owned_by":"deepinfra","model_name":"Qwen/Qwen2.5-7B-Instruct","context_length":32768,"max_input_tokens":32768,"max_output_tokens":32768,"quantization":null,"retirement_date":null,"description":"","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4e-8,"output_cost_per_token":1e-7},"list_pricing":{"input_cost_per_token":4e-8,"output_cost_per_token":1e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"qwen3-235b-a22b","object":"model","created":1780377273,"owned_by":"qwen","mode":"chat","context_length":40960,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.8e-7,"output_cost_per_token":5.4e-7},"pricing_endpoint":"deepinfra/Qwen/Qwen3-235B-A22B","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"deepinfra/Qwen/Qwen3-235B-A22B","object":"model","created":1780377273,"owned_by":"deepinfra","model_name":"Qwen/Qwen3-235B-A22B","context_length":40960,"max_input_tokens":40960,"max_output_tokens":40960,"quantization":null,"retirement_date":null,"description":"","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.8e-7,"output_cost_per_token":5.4e-7},"list_pricing":{"input_cost_per_token":1.8e-7,"output_cost_per_token":5.4e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"wizardlm-2-8x22b","object":"model","created":1780377273,"owned_by":"microsoft","mode":"chat","context_length":65536,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4.8e-7,"output_cost_per_token":4.8e-7},"pricing_endpoint":"deepinfra/microsoft/WizardLM-2-8x22B","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"deepinfra/microsoft/WizardLM-2-8x22B","object":"model","created":1780377273,"owned_by":"deepinfra","model_name":"microsoft/WizardLM-2-8x22B","context_length":65536,"max_input_tokens":65536,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4.8e-7,"output_cost_per_token":4.8e-7},"list_pricing":{"input_cost_per_token":4.8e-7,"output_cost_per_token":4.8e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"step-3.7-flash","object":"model","created":1779985069,"owned_by":"stepfun","mode":"chat","context_length":262144,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":1.15e-6,"cache_read_input_token_cost":4e-8},"pricing_endpoint":"deepinfra/stepfun-ai/Step-3.7-Flash","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"deepinfra/stepfun-ai/Step-3.7-Flash","object":"model","created":1779985069,"owned_by":"deepinfra","model_name":"stepfun-ai/Step-3.7-Flash","context_length":262144,"max_input_tokens":null,"max_output_tokens":32768,"quantization":null,"retirement_date":null,"description":"Step 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Experts model. It pairs a 196B-parameter language backbone with a vision encoder for native image and video understanding, activating roughly 11B parameters...","source":null,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":1.15e-6,"cache_read_input_token_cost":4e-8},"list_pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":1.15e-6,"cache_read_input_token_cost":4e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"qwen3.7-max-2026-05-17","object":"model","created":1779376861,"owned_by":"qwen","mode":"chat","context_length":1000000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.6250000000000001e-6,"output_cost_per_token":4.875e-6},"pricing_endpoint":"qwen/qwen3.7-max-2026-05-17","regions":[{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"qwen/qwen3.7-max-2026-05-17","object":"model","created":1779376861,"owned_by":"qwen","model_name":"qwen3.7-max-2026-05-17","context_length":1000000,"max_input_tokens":991808,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"The early version of the Max model in the Qwen3.7 series supports only the reasoning mode and makes its plain-text capabilities available for experimentation. Qwen3.7 is a next‑generation flagship model designed for the agent‑centric era, with major improvements in coding and agent‑level capabilities. This release is a snapshot as of May 17, 2026.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.6250000000000001e-6,"output_cost_per_token":4.875e-6},"list_pricing":{"input_cost_per_token":2.5e-6,"output_cost_per_token":7.5e-6},"discount":0.35,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":1},{"id":"qwen3.7-max-2026-05-20","object":"model","created":1779376861,"owned_by":"qwen","mode":"chat","context_length":1000000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.6250000000000001e-6,"output_cost_per_token":4.875e-6,"cache_creation_input_token_cost":2.0312500000000002e-6},"pricing_endpoint":"qwen/qwen3.7-max-2026-05-20","regions":[{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"qwen/qwen3.7-max-2026-05-20","object":"model","created":1779376861,"owned_by":"qwen","model_name":"qwen3.7-max-2026-05-20","context_length":1000000,"max_input_tokens":991808,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"The Max model, the largest and most capable in the Qwen3.7 series, currently offers a pure‑text‑only interface for public experimentation. Qwen3.7 is a next‑generation flagship model designed for the agent‑centric era, with its core strengths lying in the breadth and depth of its agent‑level capabilities: it excels at programming, office and productivity tasks, and long‑term autonomous execution.This version is a snapshot as of May 20, 2026.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.6250000000000001e-6,"output_cost_per_token":4.875e-6,"cache_creation_input_token_cost":2.0312500000000002e-6},"list_pricing":{"input_cost_per_token":2.5e-6,"output_cost_per_token":7.5e-6,"cache_creation_input_token_cost":3.125e-6},"discount":0.35,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":1},{"id":"qwen3.7-max-2026-06-08","object":"model","created":1779376861,"owned_by":"qwen","mode":"chat","context_length":1000000,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.6250000000000001e-6,"output_cost_per_token":4.875e-6,"cache_read_input_token_cost":3.25e-7,"cache_creation_input_token_cost":2.0312500000000002e-6},"pricing_endpoint":"qwen/qwen3.7-max-2026-06-08","regions":[{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"qwen/qwen3.7-max-2026-06-08","object":"model","created":1779376861,"owned_by":"qwen","model_name":"qwen3.7-max-2026-06-08","context_length":1000000,"max_input_tokens":991808,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"The Max model, the largest and most capable in the Qwen3.7 series, has added visual‑modal understanding compared to the May 20 snapshot, enabling it to perceive real‑world scenes and supporting multimodal interactive hybrid agent capabilities. This version is based on a snapshot taken on June 8, 2026.","source":null,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.6250000000000001e-6,"output_cost_per_token":4.875e-6,"cache_read_input_token_cost":3.25e-7,"cache_creation_input_token_cost":2.0312500000000002e-6},"list_pricing":{"input_cost_per_token":2.5e-6,"output_cost_per_token":7.5e-6,"cache_read_input_token_cost":5e-7,"cache_creation_input_token_cost":3.125e-6},"discount":0.35,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":1},{"id":"qwen3.7-max-preview","object":"model","created":1779376861,"owned_by":"qwen","mode":"chat","context_length":1000000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.6250000000000001e-6,"output_cost_per_token":4.875e-6},"pricing_endpoint":"qwen/qwen3.7-max-preview","regions":[{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"qwen/qwen3.7-max-preview","object":"model","created":1779376861,"owned_by":"qwen","model_name":"qwen3.7-max-preview","context_length":1000000,"max_input_tokens":991808,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"The Max model, the largest and most capable variant in the Qwen3.7 series, is available as a preview and supports only thinking mode, offering a pure text‑only interface for experimentation. It is primarily optimized for general‑purpose conversational use cases, such as knowledge‑based question answering, instruction following, and creative writing.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.6250000000000001e-6,"output_cost_per_token":4.875e-6},"list_pricing":{"input_cost_per_token":2.5e-6,"output_cost_per_token":7.5e-6},"discount":0.35,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":1},{"id":"grok-build-0.1","object":"model","created":1779298123,"owned_by":"xai","mode":"chat","context_length":256000,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":2e-6,"input_cost_per_image_token":1e-6,"cache_read_input_token_cost":2e-7,"search_context_cost_per_query":{"search_context_size_low":0.005,"search_context_size_high":0.005,"search_context_size_medium":0.005},"input_cost_per_token_above_200k_tokens":2e-6,"output_cost_per_token_above_200k_tokens":4e-6,"cache_read_input_token_cost_above_200k_tokens":4e-7},"pricing_endpoint":"xai/grok-build-0.1","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"xai/grok-build-0.1","object":"model","created":1779298123,"owned_by":"xai","model_name":"grok-build-0.1","context_length":256000,"max_input_tokens":256000,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"Grok Build 0.1 is SpaceXAI’s fast coding model trained specifically for agentic software engineering workflows.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":2e-6,"input_cost_per_image_token":1e-6,"cache_read_input_token_cost":2e-7,"search_context_cost_per_query":{"search_context_size_low":0.005,"search_context_size_high":0.005,"search_context_size_medium":0.005},"input_cost_per_token_above_200k_tokens":2e-6,"output_cost_per_token_above_200k_tokens":4e-6,"cache_read_input_token_cost_above_200k_tokens":4e-7},"list_pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":2e-6,"input_cost_per_image_token":1e-6,"cache_read_input_token_cost":2e-7,"search_context_cost_per_query":{"search_context_size_low":0.005,"search_context_size_high":0.005,"search_context_size_medium":0.005},"input_cost_per_token_above_200k_tokens":2e-6,"output_cost_per_token_above_200k_tokens":4e-6,"cache_read_input_token_cost_above_200k_tokens":4e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"grok-4.3-latest","object":"model","created":1778172174,"owned_by":"xai","mode":"chat","context_length":1000000,"capabilities":{"input_modalities":["image","text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":2.5e-6,"cache_read_input_token_cost":2e-7,"input_cost_per_token_above_200k_tokens":2.5e-6,"output_cost_per_token_above_200k_tokens":5e-6,"cache_read_input_token_cost_above_200k_tokens":4e-7},"pricing_endpoint":"xai/grok-4.3-latest","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"xai/grok-4.3-latest","object":"model","created":1778172174,"owned_by":"xai","model_name":"grok-4.3-latest","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":1000000,"quantization":null,"retirement_date":null,"description":"","source":"https://docs.x.ai/docs/models","capabilities":{"input_modalities":["image","text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":2.5e-6,"cache_read_input_token_cost":2e-7,"input_cost_per_token_above_200k_tokens":2.5e-6,"output_cost_per_token_above_200k_tokens":5e-6,"cache_read_input_token_cost_above_200k_tokens":4e-7},"list_pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":2.5e-6,"cache_read_input_token_cost":2e-7,"input_cost_per_token_above_200k_tokens":2.5e-6,"output_cost_per_token_above_200k_tokens":5e-6,"cache_read_input_token_cost_above_200k_tokens":4e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"gemini-3.1-flash-lite-preview","object":"model","created":1778168828,"owned_by":"google","mode":"chat","context_length":1048576,"capabilities":{"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2.5e-7,"output_cost_per_token":1.5e-6,"input_cost_per_token_flex":1.25e-7,"input_cost_per_audio_token":5e-7,"input_cost_per_image_token":2.5e-7,"output_cost_per_token_flex":7.5e-7,"cache_read_input_token_cost":2.5e-8,"input_cost_per_token_priority":4.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":2.7e-6,"cache_creation_input_token_cost":8.33333333333333e-8,"output_cost_per_reasoning_token":1.5e-6,"cache_read_input_token_cost_flex":1.25e-8,"cache_read_input_audio_token_cost":5e-8,"cache_read_input_token_cost_priority":4.5e-8,"google_maps_grounding_cost_per_query":0.014},"pricing_endpoint":"google/gemini-3.1-flash-lite-preview","regions":[{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"google/gemini-3.1-flash-lite-preview","object":"model","created":1778168828,"owned_by":"google","model_name":"gemini-3.1-flash-lite-preview","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"Gemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads.","source":"https://ai.google.dev/gemini-api/docs/models","capabilities":{"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2.5e-7,"output_cost_per_token":1.5e-6,"input_cost_per_token_flex":1.25e-7,"input_cost_per_audio_token":5e-7,"input_cost_per_image_token":2.5e-7,"output_cost_per_token_flex":7.5e-7,"cache_read_input_token_cost":2.5e-8,"input_cost_per_token_priority":4.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":2.7e-6,"cache_creation_input_token_cost":8.33333333333333e-8,"output_cost_per_reasoning_token":1.5e-6,"cache_read_input_token_cost_flex":1.25e-8,"cache_read_input_audio_token_cost":5e-8,"cache_read_input_token_cost_priority":4.5e-8,"google_maps_grounding_cost_per_query":0.014},"list_pricing":{"input_cost_per_token":2.5e-7,"output_cost_per_token":1.5e-6,"input_cost_per_token_flex":1.25e-7,"input_cost_per_audio_token":5e-7,"input_cost_per_image_token":2.5e-7,"output_cost_per_token_flex":7.5e-7,"cache_read_input_token_cost":2.5e-8,"input_cost_per_token_priority":4.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":2.7e-6,"cache_creation_input_token_cost":8.33333333333333e-8,"output_cost_per_reasoning_token":1.5e-6,"cache_read_input_token_cost_flex":1.25e-8,"cache_read_input_audio_token_cost":5e-8,"cache_read_input_token_cost_priority":4.5e-8,"google_maps_grounding_cost_per_query":0.014},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":1},{"id":"grok-4.3","object":"model","created":1777591821,"owned_by":"xai","mode":"chat","context_length":1000000,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":2.5e-6,"input_cost_per_image_token":1.25e-6,"cache_read_input_token_cost":2e-7,"search_context_cost_per_query":{"search_context_size_low":0.005,"search_context_size_high":0.005,"search_context_size_medium":0.005},"input_cost_per_token_above_200k_tokens":2.5e-6,"output_cost_per_token_above_200k_tokens":5e-6,"cache_read_input_token_cost_above_200k_tokens":4e-7},"pricing_endpoint":"xai/grok-4.3","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"xai/grok-4.3","object":"model","created":1777591821,"owned_by":"xai","model_name":"grok-4.3","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"Grok 4.3 is a reasoning model from SpaceXAI.","source":"https://docs.x.ai/docs/models","capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":2.5e-6,"input_cost_per_image_token":1.25e-6,"cache_read_input_token_cost":2e-7,"search_context_cost_per_query":{"search_context_size_low":0.005,"search_context_size_high":0.005,"search_context_size_medium":0.005},"input_cost_per_token_above_200k_tokens":2.5e-6,"output_cost_per_token_above_200k_tokens":5e-6,"cache_read_input_token_cost_above_200k_tokens":4e-7},"list_pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":2.5e-6,"input_cost_per_image_token":1.25e-6,"cache_read_input_token_cost":2e-7,"search_context_cost_per_query":{"search_context_size_low":0.005,"search_context_size_high":0.005,"search_context_size_medium":0.005},"input_cost_per_token_above_200k_tokens":2.5e-6,"output_cost_per_token_above_200k_tokens":5e-6,"cache_read_input_token_cost_above_200k_tokens":4e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"codestral-2405","object":"model","created":1777389105,"owned_by":"mistral","mode":"chat","context_length":32000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":true,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":3e-6},"pricing_endpoint":"mistral/codestral-2405","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"mistral/codestral-2405@eu","object":"model","created":1777389105,"owned_by":"mistral","model_name":"codestral-2405","context_length":32000,"max_input_tokens":32000,"max_output_tokens":8191,"quantization":null,"retirement_date":null,"description":"","source":"https://docs.mistral.ai/capabilities/code_generation/","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":true,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.1e-6,"output_cost_per_token":3.3e-6},"list_pricing":{"input_cost_per_token":1.1e-6,"output_cost_per_token":3.3e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"mistral/codestral-2405","object":"model","created":1777389105,"owned_by":"mistral","model_name":"codestral-2405","context_length":32000,"max_input_tokens":32000,"max_output_tokens":8191,"quantization":null,"retirement_date":null,"description":"","source":"https://docs.mistral.ai/capabilities/code_generation/","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":true,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":3e-6},"list_pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":3e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"mistral-large-2402","object":"model","created":1777389105,"owned_by":"mistral","mode":"chat","context_length":32000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4e-6,"output_cost_per_token":0.000012},"pricing_endpoint":"mistral/mistral-large-2402","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"mistral/mistral-large-2402@eu","object":"model","created":1777389105,"owned_by":"mistral","model_name":"mistral-large-2402","context_length":32000,"max_input_tokens":32000,"max_output_tokens":8191,"quantization":null,"retirement_date":null,"description":"","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4.4e-6,"output_cost_per_token":0.0000132},"list_pricing":{"input_cost_per_token":4.4e-6,"output_cost_per_token":0.0000132},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"mistral/mistral-large-2402","object":"model","created":1777389105,"owned_by":"mistral","model_name":"mistral-large-2402","context_length":32000,"max_input_tokens":32000,"max_output_tokens":8191,"quantization":null,"retirement_date":null,"description":"","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4e-6,"output_cost_per_token":0.000012},"list_pricing":{"input_cost_per_token":4e-6,"output_cost_per_token":0.000012},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/mistral.mistral-large-2402-v1:0","object":"model","created":1772632546,"owned_by":"amazon","model_name":"mistral.mistral-large-2402-v1:0","context_length":32000,"max_input_tokens":32000,"max_output_tokens":4096,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5.2e-6,"output_cost_per_token":0.0000156},"list_pricing":{"input_cost_per_token":5.2e-6,"output_cost_per_token":0.0000156},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/mistral.mistral-large-2402-v1:0@us","object":"model","created":1772632546,"owned_by":"amazon","model_name":"mistral.mistral-large-2402-v1:0","context_length":32000,"max_input_tokens":32000,"max_output_tokens":4096,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5.2e-6,"output_cost_per_token":0.0000156},"list_pricing":{"input_cost_per_token":5.2e-6,"output_cost_per_token":0.0000156},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":4},{"id":"mistral-medium-2312","object":"model","created":1777389105,"owned_by":"mistral","mode":"chat","context_length":32000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":true,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.7e-6,"output_cost_per_token":8.1e-6},"pricing_endpoint":"mistral/mistral-medium-2312","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"mistral/mistral-medium-2312@eu","object":"model","created":1777389105,"owned_by":"mistral","model_name":"mistral-medium-2312","context_length":32000,"max_input_tokens":32000,"max_output_tokens":8191,"quantization":null,"retirement_date":null,"description":"","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":true,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.9700000000000004e-6,"output_cost_per_token":8.910000000000001e-6},"list_pricing":{"input_cost_per_token":2.9700000000000004e-6,"output_cost_per_token":8.910000000000001e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"mistral/mistral-medium-2312","object":"model","created":1777389105,"owned_by":"mistral","model_name":"mistral-medium-2312","context_length":32000,"max_input_tokens":32000,"max_output_tokens":8191,"quantization":null,"retirement_date":null,"description":"","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":true,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.7e-6,"output_cost_per_token":8.1e-6},"list_pricing":{"input_cost_per_token":2.7e-6,"output_cost_per_token":8.1e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"mistral-small","object":"model","created":1777389105,"owned_by":"mistral","mode":"chat","context_length":32000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":3e-7},"pricing_endpoint":"mistral/mistral-small","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"mistral/mistral-small@eu","object":"model","created":1777389105,"owned_by":"mistral","model_name":"mistral-small","context_length":32000,"max_input_tokens":32000,"max_output_tokens":8191,"quantization":null,"retirement_date":null,"description":"","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.1e-7,"output_cost_per_token":3.3e-7},"list_pricing":{"input_cost_per_token":1.1e-7,"output_cost_per_token":3.3e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"mistral/mistral-small","object":"model","created":1777389105,"owned_by":"mistral","model_name":"mistral-small","context_length":32000,"max_input_tokens":32000,"max_output_tokens":8191,"quantization":null,"retirement_date":null,"description":"","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":3e-7},"list_pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":3e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"mistral-tiny","object":"model","created":1777389105,"owned_by":"mistral","mode":"chat","context_length":32000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":true,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.5e-7,"output_cost_per_token":2.5e-7},"pricing_endpoint":"mistral/mistral-tiny","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"mistral/mistral-tiny@eu","object":"model","created":1777389105,"owned_by":"mistral","model_name":"mistral-tiny","context_length":32000,"max_input_tokens":32000,"max_output_tokens":8191,"quantization":null,"retirement_date":null,"description":"","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":true,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.75e-7,"output_cost_per_token":2.75e-7},"list_pricing":{"input_cost_per_token":2.75e-7,"output_cost_per_token":2.75e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"mistral/mistral-tiny","object":"model","created":1777389105,"owned_by":"mistral","model_name":"mistral-tiny","context_length":32000,"max_input_tokens":32000,"max_output_tokens":8191,"quantization":null,"retirement_date":null,"description":"","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":true,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.5e-7,"output_cost_per_token":2.5e-7},"list_pricing":{"input_cost_per_token":2.5e-7,"output_cost_per_token":2.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"open-mistral-7b","object":"model","created":1777389105,"owned_by":"mistral","mode":"chat","context_length":32000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":true,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.5e-7,"output_cost_per_token":2.5e-7},"pricing_endpoint":"mistral/open-mistral-7b","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"mistral/open-mistral-7b@eu","object":"model","created":1777389105,"owned_by":"mistral","model_name":"open-mistral-7b","context_length":32000,"max_input_tokens":32000,"max_output_tokens":8191,"quantization":null,"retirement_date":null,"description":"","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":true,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.75e-7,"output_cost_per_token":2.75e-7},"list_pricing":{"input_cost_per_token":2.75e-7,"output_cost_per_token":2.75e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"mistral/open-mistral-7b","object":"model","created":1777389105,"owned_by":"mistral","model_name":"open-mistral-7b","context_length":32000,"max_input_tokens":32000,"max_output_tokens":8191,"quantization":null,"retirement_date":null,"description":"","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":true,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.5e-7,"output_cost_per_token":2.5e-7},"list_pricing":{"input_cost_per_token":2.5e-7,"output_cost_per_token":2.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"open-mixtral-8x22b","object":"model","created":1777389105,"owned_by":"mistral","mode":"chat","context_length":65336,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":6e-6},"pricing_endpoint":"mistral/open-mixtral-8x22b","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"mistral/open-mixtral-8x22b@eu","object":"model","created":1777389105,"owned_by":"mistral","model_name":"open-mixtral-8x22b","context_length":65336,"max_input_tokens":65336,"max_output_tokens":8191,"quantization":null,"retirement_date":null,"description":"","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.2e-6,"output_cost_per_token":6.6e-6},"list_pricing":{"input_cost_per_token":2.2e-6,"output_cost_per_token":6.6e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"mistral/open-mixtral-8x22b","object":"model","created":1777389105,"owned_by":"mistral","model_name":"open-mixtral-8x22b","context_length":65336,"max_input_tokens":65336,"max_output_tokens":8191,"quantization":null,"retirement_date":null,"description":"","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":6e-6},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":6e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"open-mixtral-8x7b","object":"model","created":1777389105,"owned_by":"mistral","mode":"chat","context_length":32000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":7e-7,"output_cost_per_token":7e-7},"pricing_endpoint":"mistral/open-mixtral-8x7b","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"mistral/open-mixtral-8x7b@eu","object":"model","created":1777389105,"owned_by":"mistral","model_name":"open-mixtral-8x7b","context_length":32000,"max_input_tokens":32000,"max_output_tokens":8191,"quantization":null,"retirement_date":null,"description":"","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":7.7e-7,"output_cost_per_token":7.7e-7},"list_pricing":{"input_cost_per_token":7.7e-7,"output_cost_per_token":7.7e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"mistral/open-mixtral-8x7b","object":"model","created":1777389105,"owned_by":"mistral","model_name":"open-mixtral-8x7b","context_length":32000,"max_input_tokens":32000,"max_output_tokens":8191,"quantization":null,"retirement_date":null,"description":"","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":7e-7,"output_cost_per_token":7e-7},"list_pricing":{"input_cost_per_token":7e-7,"output_cost_per_token":7e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"pixtral-12b-2409","object":"model","created":1777389105,"owned_by":"mistral","mode":"chat","context_length":128000,"capabilities":{"input_modalities":["image","text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":1.5e-7},"pricing_endpoint":"mistral/pixtral-12b-2409","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"mistral/pixtral-12b-2409@eu","object":"model","created":1777389105,"owned_by":"mistral","model_name":"pixtral-12b-2409","context_length":128000,"max_input_tokens":128000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"","source":null,"capabilities":{"input_modalities":["image","text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.65e-7,"output_cost_per_token":1.65e-7},"list_pricing":{"input_cost_per_token":1.65e-7,"output_cost_per_token":1.65e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"mistral/pixtral-12b-2409","object":"model","created":1777389105,"owned_by":"mistral","model_name":"pixtral-12b-2409","context_length":128000,"max_input_tokens":128000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"","source":null,"capabilities":{"input_modalities":["image","text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":1.5e-7},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":1.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"scaleway/pixtral-12b-2409","object":"model","created":1730385501,"owned_by":"scaleway","model_name":"pixtral-12b-2409","context_length":128000,"max_input_tokens":null,"max_output_tokens":4096,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.24499898413796e-7,"output_cost_per_token":2.24499898413796e-7},"list_pricing":{"input_cost_per_token":2.24499898413796e-7,"output_cost_per_token":2.24499898413796e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":3},{"id":"qwen3.5-plus","object":"model","created":1777261368,"owned_by":"qwen","mode":"chat","context_length":1000000,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"tiered_pricing":[{"range":[0,256000],"input_cost_per_token":2.6000000000000005e-7,"output_cost_per_token":1.5599999999999999e-6,"cache_creation_input_token_cost":3.25e-7},{"range":[256000,1000000],"input_cost_per_token":3.25e-7,"output_cost_per_token":1.95e-6,"cache_creation_input_token_cost":4.0625000000000003e-7}],"input_cost_per_token":2.6000000000000005e-7,"output_cost_per_token":1.5599999999999999e-6,"cache_creation_input_token_cost":3.25e-7},"pricing_endpoint":"qwen/qwen3.5-plus","regions":[{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"qwen/qwen3.5-plus","object":"model","created":1777261368,"owned_by":"qwen","model_name":"qwen3.5-plus","context_length":1000000,"max_input_tokens":991808,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"The Qwen3.5 native vision-language series Plus models are built on a hybrid architecture that integrates linear attention mechanisms with sparse mixture-of-experts models, achieving higher inference efficiency. In a variety of task evaluations, the 3.5 series consistently demonstrates performance on par with state-of-the-art leading models. Compared to the 3 series, these models show a leap forward in both pure-text and multimodal capabilities.","source":null,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"tiered_pricing":[{"range":[0,256000],"input_cost_per_token":2.6000000000000005e-7,"output_cost_per_token":1.5599999999999999e-6,"cache_creation_input_token_cost":3.25e-7},{"range":[256000,1000000],"input_cost_per_token":3.25e-7,"output_cost_per_token":1.95e-6,"cache_creation_input_token_cost":4.0625000000000003e-7}],"input_cost_per_token":2.6000000000000005e-7,"output_cost_per_token":1.5599999999999999e-6,"cache_creation_input_token_cost":3.25e-7},"list_pricing":{"tiered_pricing":[{"range":[0,256000],"input_cost_per_token":4.0000000000000003e-7,"output_cost_per_token":2.4e-6,"cache_creation_input_token_cost":5e-7},{"range":[256000,1000000],"input_cost_per_token":5e-7,"output_cost_per_token":3e-6,"cache_creation_input_token_cost":6.25e-7}],"input_cost_per_token":4.0000000000000003e-7,"output_cost_per_token":2.4e-6,"cache_creation_input_token_cost":5e-7},"discount":0.35,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":1},{"id":"qwen3.5-plus-2026-02-15","object":"model","created":1777261368,"owned_by":"qwen","mode":"chat","context_length":1000000,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"tiered_pricing":[{"range":[0,256000],"input_cost_per_token":2.6000000000000005e-7,"output_cost_per_token":1.5599999999999999e-6},{"range":[256000,1000000],"input_cost_per_token":3.25e-7,"output_cost_per_token":1.95e-6}],"input_cost_per_token":2.6000000000000005e-7,"output_cost_per_token":1.5599999999999999e-6},"pricing_endpoint":"qwen/qwen3.5-plus-2026-02-15","regions":[{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"qwen/qwen3.5-plus-2026-02-15","object":"model","created":1777261368,"owned_by":"qwen","model_name":"qwen3.5-plus-2026-02-15","context_length":1000000,"max_input_tokens":991808,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"The Qwen3.5 native vision-language series Plus models are built on a hybrid architecture that integrates linear attention mechanisms with sparse mixture-of-experts models, achieving higher inference efficiency. In a variety of task evaluations, the 3.5 series consistently demonstrates performance on par with state-of-the-art leading models. Compared to the 3 series, these models show a leap forward in both pure-text and multimodal capabilities.This version is a snapshot as of February 15, 2026.","source":null,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"tiered_pricing":[{"range":[0,256000],"input_cost_per_token":2.6000000000000005e-7,"output_cost_per_token":1.5599999999999999e-6},{"range":[256000,1000000],"input_cost_per_token":3.25e-7,"output_cost_per_token":1.95e-6}],"input_cost_per_token":2.6000000000000005e-7,"output_cost_per_token":1.5599999999999999e-6},"list_pricing":{"tiered_pricing":[{"range":[0,256000],"input_cost_per_token":4.0000000000000003e-7,"output_cost_per_token":2.4e-6},{"range":[256000,1000000],"input_cost_per_token":5e-7,"output_cost_per_token":3e-6}],"input_cost_per_token":4.0000000000000003e-7,"output_cost_per_token":2.4e-6},"discount":0.35,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":1},{"id":"qwen3.5-plus-2026-04-20","object":"model","created":1777261368,"owned_by":"qwen","mode":"chat","context_length":1000000,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"tiered_pricing":[{"range":[0,256000],"input_cost_per_token":2.6000000000000005e-7,"output_cost_per_token":1.5599999999999999e-6,"cache_creation_input_token_cost":3.25e-7},{"range":[256000,1000000],"input_cost_per_token":3.25e-7,"output_cost_per_token":1.95e-6,"cache_creation_input_token_cost":4.0625000000000003e-7}],"input_cost_per_token":2.6000000000000005e-7,"output_cost_per_token":1.5599999999999999e-6,"cache_creation_input_token_cost":3.25e-7},"pricing_endpoint":"qwen/qwen3.5-plus-2026-04-20","regions":[{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"qwen/qwen3.5-plus-2026-04-20","object":"model","created":1777261368,"owned_by":"qwen","model_name":"qwen3.5-plus-2026-04-20","context_length":1000000,"max_input_tokens":991808,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"The Qwen3.5 native vision-language series Plus model has seen a substantial improvement in agentic coding capabilities compared to the February 15th snapshot. Inference speed has also been significantly enhanced, while its knowledge retention, reasoning ability, and long-context processing remain at a high level, making it well-suited for complex agent-based tasks. It is ideal for applications such as coding agents, production workflows, and high-throughput scenarios. This version is based on a snapshot taken on April 20, 2026.","source":null,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"tiered_pricing":[{"range":[0,256000],"input_cost_per_token":2.6000000000000005e-7,"output_cost_per_token":1.5599999999999999e-6,"cache_creation_input_token_cost":3.25e-7},{"range":[256000,1000000],"input_cost_per_token":3.25e-7,"output_cost_per_token":1.95e-6,"cache_creation_input_token_cost":4.0625000000000003e-7}],"input_cost_per_token":2.6000000000000005e-7,"output_cost_per_token":1.5599999999999999e-6,"cache_creation_input_token_cost":3.25e-7},"list_pricing":{"tiered_pricing":[{"range":[0,256000],"input_cost_per_token":4.0000000000000003e-7,"output_cost_per_token":2.4e-6,"cache_creation_input_token_cost":5e-7},{"range":[256000,1000000],"input_cost_per_token":5e-7,"output_cost_per_token":3e-6,"cache_creation_input_token_cost":6.25e-7}],"input_cost_per_token":4.0000000000000003e-7,"output_cost_per_token":2.4e-6,"cache_creation_input_token_cost":5e-7},"discount":0.35,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":1},{"id":"qwen3.6-flash","object":"model","created":1777261362,"owned_by":"qwen","mode":"chat","context_length":1000000,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"tiered_pricing":[{"range":[0,256000],"input_cost_per_token":1.625e-7,"output_cost_per_token":9.75e-7,"cache_creation_input_token_cost":2.0312500000000001e-7},{"range":[256000,1000000],"input_cost_per_token":6.5e-7,"output_cost_per_token":2.6e-6,"cache_creation_input_token_cost":8.125000000000001e-7}],"input_cost_per_token":1.625e-7,"output_cost_per_token":9.75e-7,"cache_creation_input_token_cost":2.0312500000000001e-7},"pricing_endpoint":"qwen/qwen3.6-flash","regions":[{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"qwen/qwen3.6-flash","object":"model","created":1777261362,"owned_by":"qwen","model_name":"qwen3.6-flash","context_length":1000000,"max_input_tokens":991808,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"The Qwen3.6 native vision-language Flash model series delivers a significant performance boost over the 3.5-Flash version. This model particularly excels in agentic coding capabilities, substantially outperforming its predecessor on multiple code-agent benchmarks, as well as in mathematical and code reasoning. In terms of vision, it features markedly improved spatial intelligence, with especially notable enhancements in object localization and object detection.","source":null,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"tiered_pricing":[{"range":[0,256000],"input_cost_per_token":1.625e-7,"output_cost_per_token":9.75e-7,"cache_creation_input_token_cost":2.0312500000000001e-7},{"range":[256000,1000000],"input_cost_per_token":6.5e-7,"output_cost_per_token":2.6e-6,"cache_creation_input_token_cost":8.125000000000001e-7}],"input_cost_per_token":1.625e-7,"output_cost_per_token":9.75e-7,"cache_creation_input_token_cost":2.0312500000000001e-7},"list_pricing":{"tiered_pricing":[{"range":[0,256000],"input_cost_per_token":2.5e-7,"output_cost_per_token":1.5e-6,"cache_creation_input_token_cost":3.125e-7},{"range":[256000,1000000],"input_cost_per_token":1e-6,"output_cost_per_token":4e-6,"cache_creation_input_token_cost":1.25e-6}],"input_cost_per_token":2.5e-7,"output_cost_per_token":1.5e-6,"cache_creation_input_token_cost":3.125e-7},"discount":0.35,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":1},{"id":"qwen3.6-flash-2026-04-16","object":"model","created":1777261362,"owned_by":"qwen","mode":"chat","context_length":1000000,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"tiered_pricing":[{"range":[0,256000],"input_cost_per_token":1.625e-7,"output_cost_per_token":9.75e-7},{"range":[256000,1000000],"input_cost_per_token":6.5e-7,"output_cost_per_token":2.6e-6}],"input_cost_per_token":1.625e-7,"output_cost_per_token":9.75e-7},"pricing_endpoint":"qwen/qwen3.6-flash-2026-04-16","regions":[{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"qwen/qwen3.6-flash-2026-04-16","object":"model","created":1777261362,"owned_by":"qwen","model_name":"qwen3.6-flash-2026-04-16","context_length":1000000,"max_input_tokens":991808,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"The Qwen3.6 native vision-language Flash model series delivers a significant performance boost over the 3.5-Flash version. This model particularly excels in agentic coding capabilities, substantially outperforming its predecessor on multiple code-agent benchmarks, as well as in mathematical and code reasoning. In terms of vision, it features markedly improved spatial intelligence, with especially notable enhancements in object localization and object detection.This release is based on a snapshot taken on April 16, 2026.","source":null,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"tiered_pricing":[{"range":[0,256000],"input_cost_per_token":1.625e-7,"output_cost_per_token":9.75e-7},{"range":[256000,1000000],"input_cost_per_token":6.5e-7,"output_cost_per_token":2.6e-6}],"input_cost_per_token":1.625e-7,"output_cost_per_token":9.75e-7},"list_pricing":{"tiered_pricing":[{"range":[0,256000],"input_cost_per_token":2.5e-7,"output_cost_per_token":1.5e-6},{"range":[256000,1000000],"input_cost_per_token":1e-6,"output_cost_per_token":4e-6}],"input_cost_per_token":2.5e-7,"output_cost_per_token":1.5e-6},"discount":0.35,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":1},{"id":"gpt-5.5-pro-2026-04-23","object":"model","created":1777051896,"owned_by":"openai","mode":"chat","context_length":1050000,"capabilities":{"input_modalities":["file","image","text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":0.00003,"output_cost_per_token":0.00018,"input_cost_per_token_flex":0.000015,"output_cost_per_token_flex":0.00009,"input_cost_per_token_batches":0.000015,"output_cost_per_token_batches":0.00009,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"input_cost_per_token_above_272k_tokens":0.00006,"output_cost_per_token_above_272k_tokens":0.00027},"pricing_endpoint":"openai/gpt-5.5-pro-2026-04-23","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"openai/gpt-5.5-pro-2026-04-23","object":"model","created":1777051896,"owned_by":"openai","model_name":"gpt-5.5-pro-2026-04-23","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5.5 Pro is OpenAI’s high-capability model optimized for deep reasoning and accuracy on complex, high-stakes workloads.","source":null,"capabilities":{"input_modalities":["file","image","text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":0.00003,"output_cost_per_token":0.00018,"input_cost_per_token_flex":0.000015,"output_cost_per_token_flex":0.00009,"input_cost_per_token_batches":0.000015,"output_cost_per_token_batches":0.00009,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"input_cost_per_token_above_272k_tokens":0.00006,"output_cost_per_token_above_272k_tokens":0.00027},"list_pricing":{"input_cost_per_token":0.00003,"output_cost_per_token":0.00018,"input_cost_per_token_flex":0.000015,"output_cost_per_token_flex":0.00009,"input_cost_per_token_batches":0.000015,"output_cost_per_token_batches":0.00009,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"input_cost_per_token_above_272k_tokens":0.00006,"output_cost_per_token_above_272k_tokens":0.00027},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":1},{"id":"gpt-5.5-2026-04-23","object":"model","created":1777051893,"owned_by":"openai","mode":"chat","context_length":1050000,"capabilities":{"input_modalities":["file","image","text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":5e-6,"output_cost_per_token":0.00003,"input_cost_per_token_flex":2.5e-6,"output_cost_per_token_flex":0.000015,"cache_read_input_token_cost":5e-7,"input_cost_per_token_batches":2.5e-6,"input_cost_per_token_priority":0.0000125,"output_cost_per_token_batches":0.000015,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"output_cost_per_token_priority":0.000075,"cache_read_input_token_cost_flex":2.5e-7,"cache_read_input_token_cost_batches":2.5e-7,"cache_read_input_token_cost_priority":1.25e-6,"input_cost_per_token_above_272k_tokens":0.00001,"output_cost_per_token_above_272k_tokens":0.000045,"input_cost_per_token_above_272k_tokens_flex":5e-6,"output_cost_per_token_above_272k_tokens_flex":0.0000225,"cache_read_input_token_cost_above_272k_tokens":1e-6,"cache_read_input_token_cost_above_272k_tokens_flex":5e-7},"pricing_endpoint":"openai/gpt-5.5-2026-04-23","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"openai/gpt-5.5-2026-04-23","object":"model","created":1777051893,"owned_by":"openai","model_name":"gpt-5.5-2026-04-23","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks.","source":null,"capabilities":{"input_modalities":["file","image","text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":5e-6,"output_cost_per_token":0.00003,"input_cost_per_token_flex":2.5e-6,"output_cost_per_token_flex":0.000015,"cache_read_input_token_cost":5e-7,"input_cost_per_token_batches":2.5e-6,"input_cost_per_token_priority":0.0000125,"output_cost_per_token_batches":0.000015,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"output_cost_per_token_priority":0.000075,"cache_read_input_token_cost_flex":2.5e-7,"cache_read_input_token_cost_batches":2.5e-7,"cache_read_input_token_cost_priority":1.25e-6,"input_cost_per_token_above_272k_tokens":0.00001,"output_cost_per_token_above_272k_tokens":0.000045,"input_cost_per_token_above_272k_tokens_flex":5e-6,"output_cost_per_token_above_272k_tokens_flex":0.0000225,"cache_read_input_token_cost_above_272k_tokens":1e-6,"cache_read_input_token_cost_above_272k_tokens_flex":5e-7},"list_pricing":{"input_cost_per_token":5e-6,"output_cost_per_token":0.00003,"input_cost_per_token_flex":2.5e-6,"output_cost_per_token_flex":0.000015,"cache_read_input_token_cost":5e-7,"input_cost_per_token_batches":2.5e-6,"input_cost_per_token_priority":0.0000125,"output_cost_per_token_batches":0.000015,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"output_cost_per_token_priority":0.000075,"cache_read_input_token_cost_flex":2.5e-7,"cache_read_input_token_cost_batches":2.5e-7,"cache_read_input_token_cost_priority":1.25e-6,"input_cost_per_token_above_272k_tokens":0.00001,"output_cost_per_token_above_272k_tokens":0.000045,"input_cost_per_token_above_272k_tokens_flex":5e-6,"output_cost_per_token_above_272k_tokens_flex":0.0000225,"cache_read_input_token_cost_above_272k_tokens":1e-6,"cache_read_input_token_cost_above_272k_tokens_flex":5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":1},{"id":"mimo-v2.5","object":"model","created":1776874269,"owned_by":"xiaomi","mode":"chat","context_length":262144,"capabilities":{"input_modalities":["text","image","audio","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.4e-7,"output_cost_per_token":2.8e-7,"cache_read_input_token_cost":2.8e-9},"pricing_endpoint":"deepinfra/XiaomiMiMo/MiMo-V2.5","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"deepinfra/XiaomiMiMo/MiMo-V2.5","object":"model","created":1776874269,"owned_by":"deepinfra","model_name":"XiaomiMiMo/MiMo-V2.5","context_length":262144,"max_input_tokens":null,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni in multimodal perception across image and video understanding...","source":null,"capabilities":{"input_modalities":["text","image","audio","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.4e-7,"output_cost_per_token":2.8e-7,"cache_read_input_token_cost":2.8e-9},"list_pricing":{"input_cost_per_token":1.4e-7,"output_cost_per_token":2.8e-7,"cache_read_input_token_cost":2.8e-9},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"grok-4.20-0309-reasoning","object":"model","created":1776575593,"owned_by":"xai","mode":"chat","context_length":1000000,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":2.5e-6,"input_cost_per_image_token":1.25e-6,"cache_read_input_token_cost":2e-7,"input_cost_per_token_above_200k_tokens":2.5e-6,"output_cost_per_token_above_200k_tokens":5e-6,"cache_read_input_token_cost_above_200k_tokens":4e-7},"pricing_endpoint":"xai/grok-4.20-0309-reasoning","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"xai/grok-4.20-0309-reasoning","object":"model","created":1776575593,"owned_by":"xai","model_name":"grok-4.20-0309-reasoning","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":"https://docs.x.ai/docs/models","capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":2.5e-6,"input_cost_per_image_token":1.25e-6,"cache_read_input_token_cost":2e-7,"input_cost_per_token_above_200k_tokens":2.5e-6,"output_cost_per_token_above_200k_tokens":5e-6,"cache_read_input_token_cost_above_200k_tokens":4e-7},"list_pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":2.5e-6,"input_cost_per_image_token":1.25e-6,"cache_read_input_token_cost":2e-7,"input_cost_per_token_above_200k_tokens":2.5e-6,"output_cost_per_token_above_200k_tokens":5e-6,"cache_read_input_token_cost_above_200k_tokens":4e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"nemotron-super-3-120b","object":"model","created":1775193119,"owned_by":"nvidia","mode":"chat","context_length":256000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.3e-7,"output_cost_per_token":1.01e-6,"input_cost_per_token_flex":1.15e-7,"output_cost_per_token_flex":5.05e-7,"input_cost_per_token_priority":4.025e-7,"output_cost_per_token_priority":1.7675e-6},"pricing_endpoint":"amazon/nvidia.nemotron-super-3-120b","regions":[{"code":"eu","name":"Europe"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"amazon/nvidia.nemotron-super-3-120b","object":"model","created":1775193119,"owned_by":"amazon","model_name":"nvidia.nemotron-super-3-120b","context_length":256000,"max_input_tokens":256000,"max_output_tokens":32000,"quantization":null,"retirement_date":null,"description":null,"source":"https://aws.amazon.com/bedrock/pricing/","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.3e-7,"output_cost_per_token":1.01e-6,"input_cost_per_token_flex":1.15e-7,"output_cost_per_token_flex":5.05e-7,"input_cost_per_token_priority":4.025e-7,"output_cost_per_token_priority":1.7675e-6},"list_pricing":{"input_cost_per_token":2.3e-7,"output_cost_per_token":1.01e-6,"input_cost_per_token_flex":1.15e-7,"output_cost_per_token_flex":5.05e-7,"input_cost_per_token_priority":4.025e-7,"output_cost_per_token_priority":1.7675e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/nvidia.nemotron-super-3-120b@us","object":"model","created":1775193119,"owned_by":"amazon","model_name":"nvidia.nemotron-super-3-120b","context_length":256000,"max_input_tokens":256000,"max_output_tokens":32000,"quantization":null,"retirement_date":null,"description":null,"source":"https://aws.amazon.com/bedrock/pricing/","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.3e-7,"output_cost_per_token":1.01e-6,"input_cost_per_token_flex":1.15e-7,"output_cost_per_token_flex":5.05e-7,"input_cost_per_token_priority":4.025e-7,"output_cost_per_token_priority":1.7675e-6},"list_pricing":{"input_cost_per_token":2.3e-7,"output_cost_per_token":1.01e-6,"input_cost_per_token_flex":1.15e-7,"output_cost_per_token_flex":5.05e-7,"input_cost_per_token_priority":4.025e-7,"output_cost_per_token_priority":1.7675e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"qwen3.6-plus","object":"model","created":1775133557,"owned_by":"qwen","mode":"chat","context_length":1000000,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"tiered_pricing":[{"range":[0,256000],"input_cost_per_token":3.25e-7,"output_cost_per_token":1.95e-6,"cache_creation_input_token_cost":4.0625000000000003e-7},{"range":[256000,1000000],"input_cost_per_token":1.3e-6,"output_cost_per_token":3.9e-6,"cache_creation_input_token_cost":1.6250000000000001e-6}],"input_cost_per_token":3.25e-7,"output_cost_per_token":1.95e-6,"cache_creation_input_token_cost":4.0625000000000003e-7},"pricing_endpoint":"qwen/qwen3.6-plus","regions":[{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"qwen/qwen3.6-plus","object":"model","created":1775133557,"owned_by":"qwen","model_name":"qwen3.6-plus","context_length":1000000,"max_input_tokens":991808,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"The Qwen3.6 native vision-language Plus series models demonstrate exceptional performance on par with the current state-of-the-art models, with a significant improvement in overall results compared to the 3.5 series. The models have been markedly enhanced in code-related capabilities such as agentic coding, front-end programming, and Vibe coding, as well as in multi-modal general object recognition, OCR, and object localization.","source":null,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"tiered_pricing":[{"range":[0,256000],"input_cost_per_token":3.25e-7,"output_cost_per_token":1.95e-6,"cache_creation_input_token_cost":4.0625000000000003e-7},{"range":[256000,1000000],"input_cost_per_token":1.3e-6,"output_cost_per_token":3.9e-6,"cache_creation_input_token_cost":1.6250000000000001e-6}],"input_cost_per_token":3.25e-7,"output_cost_per_token":1.95e-6,"cache_creation_input_token_cost":4.0625000000000003e-7},"list_pricing":{"tiered_pricing":[{"range":[0,256000],"input_cost_per_token":5e-7,"output_cost_per_token":3e-6,"cache_creation_input_token_cost":6.25e-7},{"range":[256000,1000000],"input_cost_per_token":2e-6,"output_cost_per_token":6e-6,"cache_creation_input_token_cost":2.5e-6}],"input_cost_per_token":5e-7,"output_cost_per_token":3e-6,"cache_creation_input_token_cost":6.25e-7},"discount":0.35,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":1},{"id":"qwen3.6-plus-2026-04-02","object":"model","created":1775133557,"owned_by":"qwen","mode":"chat","context_length":1000000,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"tiered_pricing":[{"range":[0,256000],"input_cost_per_token":3.25e-7,"output_cost_per_token":1.95e-6},{"range":[256000,1000000],"input_cost_per_token":1.3e-6,"output_cost_per_token":3.9e-6}],"input_cost_per_token":3.25e-7,"output_cost_per_token":1.95e-6},"pricing_endpoint":"qwen/qwen3.6-plus-2026-04-02","regions":[{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"qwen/qwen3.6-plus-2026-04-02","object":"model","created":1775133557,"owned_by":"qwen","model_name":"qwen3.6-plus-2026-04-02","context_length":1000000,"max_input_tokens":991808,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"The Qwen3.6 native vision-language Plus series models demonstrate exceptional performance on par with the current state-of-the-art models, with a significant improvement in overall results compared to the 3.5 series. The models have been markedly enhanced in code-related capabilities such as agentic coding, front-end programming, and Vibe coding, as well as in multi-modal general object recognition, OCR, and object localization.This version is a snapshot as of April 2, 2026.","source":null,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"tiered_pricing":[{"range":[0,256000],"input_cost_per_token":3.25e-7,"output_cost_per_token":1.95e-6},{"range":[256000,1000000],"input_cost_per_token":1.3e-6,"output_cost_per_token":3.9e-6}],"input_cost_per_token":3.25e-7,"output_cost_per_token":1.95e-6},"list_pricing":{"tiered_pricing":[{"range":[0,256000],"input_cost_per_token":5e-7,"output_cost_per_token":3e-6},{"range":[256000,1000000],"input_cost_per_token":2e-6,"output_cost_per_token":6e-6}],"input_cost_per_token":5e-7,"output_cost_per_token":3e-6},"discount":0.35,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":1},{"id":"grok-4.20-multi-agent","object":"model","created":1774979158,"owned_by":"xai","mode":"chat","context_length":2000000,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":2.5e-6,"input_cost_per_image_token":1.25e-6,"cache_read_input_token_cost":2e-7,"search_context_cost_per_query":{"search_context_size_low":0.005,"search_context_size_high":0.005,"search_context_size_medium":0.005},"input_cost_per_token_above_200k_tokens":2.5e-6,"output_cost_per_token_above_200k_tokens":5e-6,"cache_read_input_token_cost_above_200k_tokens":4e-7},"pricing_endpoint":"xai/grok-4.20-multi-agent","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"xai/grok-4.20-multi-agent","object":"model","created":1774979158,"owned_by":"xai","model_name":"grok-4.20-multi-agent","context_length":2000000,"max_input_tokens":1000000,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"Grok 4.20 Multi-Agent is a variant of SpaceXAI’s Grok 4.20 designed for collaborative, agent-based workflows.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":2.5e-6,"input_cost_per_image_token":1.25e-6,"cache_read_input_token_cost":2e-7,"search_context_cost_per_query":{"search_context_size_low":0.005,"search_context_size_high":0.005,"search_context_size_medium":0.005},"input_cost_per_token_above_200k_tokens":2.5e-6,"output_cost_per_token_above_200k_tokens":5e-6,"cache_read_input_token_cost_above_200k_tokens":4e-7},"list_pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":2.5e-6,"input_cost_per_image_token":1.25e-6,"cache_read_input_token_cost":2e-7,"search_context_cost_per_query":{"search_context_size_low":0.005,"search_context_size_high":0.005,"search_context_size_medium":0.005},"input_cost_per_token_above_200k_tokens":2.5e-6,"output_cost_per_token_above_200k_tokens":5e-6,"cache_read_input_token_cost_above_200k_tokens":4e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"grok-4.20","object":"model","created":1774979019,"owned_by":"xai","mode":"chat","context_length":2000000,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":2.5e-6,"input_cost_per_image_token":1.25e-6,"cache_read_input_token_cost":2e-7,"search_context_cost_per_query":{"search_context_size_low":0.005,"search_context_size_high":0.005,"search_context_size_medium":0.005},"input_cost_per_token_above_200k_tokens":2.5e-6,"output_cost_per_token_above_200k_tokens":5e-6,"cache_read_input_token_cost_above_200k_tokens":4e-7},"pricing_endpoint":"xai/grok-4.20","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"xai/grok-4.20","object":"model","created":1774979019,"owned_by":"xai","model_name":"grok-4.20","context_length":2000000,"max_input_tokens":1000000,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"Grok 4.20 is a reasoning model from SpaceXAI with industry-leading speed and agentic tool calling capabilities.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":2.5e-6,"input_cost_per_image_token":1.25e-6,"cache_read_input_token_cost":2e-7,"search_context_cost_per_query":{"search_context_size_low":0.005,"search_context_size_high":0.005,"search_context_size_medium":0.005},"input_cost_per_token_above_200k_tokens":2.5e-6,"output_cost_per_token_above_200k_tokens":5e-6,"cache_read_input_token_cost_above_200k_tokens":4e-7},"list_pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":2.5e-6,"input_cost_per_image_token":1.25e-6,"cache_read_input_token_cost":2e-7,"search_context_cost_per_query":{"search_context_size_low":0.005,"search_context_size_high":0.005,"search_context_size_medium":0.005},"input_cost_per_token_above_200k_tokens":2.5e-6,"output_cost_per_token_above_200k_tokens":5e-6,"cache_read_input_token_cost_above_200k_tokens":4e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"grok-4.20-beta-0309-non-reasoning","object":"model","created":1773897105,"owned_by":"xai","mode":"chat","context_length":2000000,"capabilities":{"input_modalities":["image","text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":6e-6,"cache_read_input_token_cost":2e-7},"pricing_endpoint":"xai/grok-4.20-beta-0309-non-reasoning","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"xai/grok-4.20-beta-0309-non-reasoning","object":"model","created":1773897105,"owned_by":"xai","model_name":"grok-4.20-beta-0309-non-reasoning","context_length":2000000,"max_input_tokens":2000000,"max_output_tokens":2000000,"quantization":null,"retirement_date":null,"description":"","source":"https://docs.x.ai/docs/models","capabilities":{"input_modalities":["image","text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":6e-6,"cache_read_input_token_cost":2e-7},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":6e-6,"cache_read_input_token_cost":2e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"grok-4.20-beta-0309-reasoning","object":"model","created":1773897105,"owned_by":"xai","mode":"chat","context_length":2000000,"capabilities":{"input_modalities":["image","text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":6e-6,"cache_read_input_token_cost":2e-7},"pricing_endpoint":"xai/grok-4.20-beta-0309-reasoning","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"xai/grok-4.20-beta-0309-reasoning","object":"model","created":1773897105,"owned_by":"xai","model_name":"grok-4.20-beta-0309-reasoning","context_length":2000000,"max_input_tokens":2000000,"max_output_tokens":2000000,"quantization":null,"retirement_date":null,"description":"","source":"https://docs.x.ai/docs/models","capabilities":{"input_modalities":["image","text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":6e-6,"cache_read_input_token_cost":2e-7},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":6e-6,"cache_read_input_token_cost":2e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"gpt-5.4-nano-2026-03-17","object":"model","created":1773748187,"owned_by":"openai","mode":"chat","context_length":400000,"capabilities":{"input_modalities":["file","image","text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":1.25e-6,"input_cost_per_token_flex":1e-7,"output_cost_per_token_flex":6.25e-7,"cache_read_input_token_cost":2e-8,"input_cost_per_token_batches":1e-7,"output_cost_per_token_batches":6.25e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_read_input_token_cost_flex":1e-8,"cache_read_input_token_cost_batches":1e-8},"pricing_endpoint":"openai/gpt-5.4-nano-2026-03-17","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"openai/gpt-5.4-nano-2026-03-17","object":"model","created":1773748187,"owned_by":"openai","model_name":"gpt-5.4-nano-2026-03-17","context_length":400000,"max_input_tokens":272000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks.","source":null,"capabilities":{"input_modalities":["file","image","text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":1.25e-6,"input_cost_per_token_flex":1e-7,"output_cost_per_token_flex":6.25e-7,"cache_read_input_token_cost":2e-8,"input_cost_per_token_batches":1e-7,"output_cost_per_token_batches":6.25e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_read_input_token_cost_flex":1e-8,"cache_read_input_token_cost_batches":1e-8},"list_pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":1.25e-6,"input_cost_per_token_flex":1e-7,"output_cost_per_token_flex":6.25e-7,"cache_read_input_token_cost":2e-8,"input_cost_per_token_batches":1e-7,"output_cost_per_token_batches":6.25e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_read_input_token_cost_flex":1e-8,"cache_read_input_token_cost_batches":1e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":1},{"id":"gpt-5.4-mini-2026-03-17","object":"model","created":1773748178,"owned_by":"openai","mode":"chat","context_length":400000,"capabilities":{"input_modalities":["file","image","text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":7.5e-7,"output_cost_per_token":4.5e-6,"input_cost_per_token_flex":3.75e-7,"output_cost_per_token_flex":2.25e-6,"cache_read_input_token_cost":7.5e-8,"input_cost_per_token_batches":3.75e-7,"input_cost_per_token_priority":1.5e-6,"output_cost_per_token_batches":2.25e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"output_cost_per_token_priority":9e-6,"cache_read_input_token_cost_flex":3.75e-8,"cache_read_input_token_cost_batches":3.75e-8,"cache_read_input_token_cost_priority":1.5e-7},"pricing_endpoint":"openai/gpt-5.4-mini-2026-03-17","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"openai/gpt-5.4-mini-2026-03-17","object":"model","created":1773748178,"owned_by":"openai","model_name":"gpt-5.4-mini-2026-03-17","context_length":400000,"max_input_tokens":272000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads.","source":null,"capabilities":{"input_modalities":["file","image","text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":7.5e-7,"output_cost_per_token":4.5e-6,"input_cost_per_token_flex":3.75e-7,"output_cost_per_token_flex":2.25e-6,"cache_read_input_token_cost":7.5e-8,"input_cost_per_token_batches":3.75e-7,"input_cost_per_token_priority":1.5e-6,"output_cost_per_token_batches":2.25e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"output_cost_per_token_priority":9e-6,"cache_read_input_token_cost_flex":3.75e-8,"cache_read_input_token_cost_batches":3.75e-8,"cache_read_input_token_cost_priority":1.5e-7},"list_pricing":{"input_cost_per_token":7.5e-7,"output_cost_per_token":4.5e-6,"input_cost_per_token_flex":3.75e-7,"output_cost_per_token_flex":2.25e-6,"cache_read_input_token_cost":7.5e-8,"input_cost_per_token_batches":3.75e-7,"input_cost_per_token_priority":1.5e-6,"output_cost_per_token_batches":2.25e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"output_cost_per_token_priority":9e-6,"cache_read_input_token_cost_flex":3.75e-8,"cache_read_input_token_cost_batches":3.75e-8,"cache_read_input_token_cost_priority":1.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":1},{"id":"mistral-small-2603","object":"model","created":1773695685,"owned_by":"mistral","mode":"chat","context_length":262144,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":1.5e-8,"input_cost_per_token_batches":7.5e-8,"output_cost_per_token_batches":3e-7,"cache_read_input_token_cost_batches":7.5e-9},"pricing_endpoint":"mistral/mistral-small-2603","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"mistral/mistral-small-2603@eu","object":"model","created":1773695685,"owned_by":"mistral","model_name":"mistral-small-2603","context_length":262144,"max_input_tokens":262144,"max_output_tokens":209715,"quantization":null,"retirement_date":null,"description":"Mistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into a single system.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.65e-7,"output_cost_per_token":6.6e-7,"cache_read_input_token_cost":1.65e-8,"input_cost_per_token_batches":8.25e-8,"output_cost_per_token_batches":3.3e-7,"cache_read_input_token_cost_batches":8.25e-9},"list_pricing":{"input_cost_per_token":1.65e-7,"output_cost_per_token":6.6e-7,"cache_read_input_token_cost":1.65e-8,"input_cost_per_token_batches":8.25e-8,"output_cost_per_token_batches":3.3e-7,"cache_read_input_token_cost_batches":8.25e-9},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"mistral/mistral-small-2603","object":"model","created":1773695685,"owned_by":"mistral","model_name":"mistral-small-2603","context_length":262144,"max_input_tokens":262144,"max_output_tokens":209715,"quantization":null,"retirement_date":null,"description":"Mistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into a single system.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":1.5e-8,"input_cost_per_token_batches":7.5e-8,"output_cost_per_token_batches":3e-7,"cache_read_input_token_cost_batches":7.5e-9},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":1.5e-8,"input_cost_per_token_batches":7.5e-8,"output_cost_per_token_batches":3e-7,"cache_read_input_token_cost_batches":7.5e-9},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"seed-2-0-lite-260428","object":"model","created":1773157231,"owned_by":"bytedance","mode":"chat","context_length":262144,"capabilities":{"input_modalities":["text","image","video","audio"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.5e-7,"output_cost_per_token":2e-6,"input_cost_per_token_above_128k_tokens":5e-7,"output_cost_per_token_above_128k_tokens":4e-6},"pricing_endpoint":"bytedance/seed-2-0-lite-260428","regions":[{"code":"ap","name":"Asia"}],"alias_of":null,"endpoints":[{"id":"bytedance/seed-2-0-lite-260428","object":"model","created":1773157231,"owned_by":"bytedance","model_name":"seed-2-0-lite-260428","context_length":262144,"max_input_tokens":229376,"max_output_tokens":131072,"quantization":"fp8","retirement_date":null,"description":"Seed-2.0-Lite is a versatile, cost‑efficient enterprise workhorse that delivers strong multimodal and agent capabilities while offering noticeably lower latency, making it a practical default choice for most production workloads across...","source":null,"capabilities":{"input_modalities":["text","image","video","audio"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.5e-7,"output_cost_per_token":2e-6,"input_cost_per_token_above_128k_tokens":5e-7,"output_cost_per_token_above_128k_tokens":4e-6},"list_pricing":{"input_cost_per_token":2.5e-7,"output_cost_per_token":2e-6,"input_cost_per_token_above_128k_tokens":5e-7,"output_cost_per_token_above_128k_tokens":4e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"ap","name":"Asia"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":1},{"id":"gpt-5.4-pro-2026-03-05","object":"model","created":1772734366,"owned_by":"openai","mode":"chat","context_length":1050000,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":0.00003,"output_cost_per_token":0.00018,"input_cost_per_token_flex":0.000015,"output_cost_per_token_flex":0.00009,"input_cost_per_token_batches":0.000015,"output_cost_per_token_batches":0.00009,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"input_cost_per_token_above_272k_tokens":0.00006,"output_cost_per_token_above_272k_tokens":0.00027,"input_cost_per_token_above_272k_tokens_flex":0.00003,"output_cost_per_token_above_272k_tokens_flex":0.000135},"pricing_endpoint":"openai/gpt-5.4-pro-2026-03-05","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"openai/gpt-5.4-pro-2026-03-05","object":"model","created":1772734366,"owned_by":"openai","model_name":"gpt-5.4-pro-2026-03-05","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5.4 Pro is OpenAI's most advanced model, building on GPT-5.4's unified architecture with enhanced reasoning capabilities for complex, high-stakes tasks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":0.00003,"output_cost_per_token":0.00018,"input_cost_per_token_flex":0.000015,"output_cost_per_token_flex":0.00009,"input_cost_per_token_batches":0.000015,"output_cost_per_token_batches":0.00009,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"input_cost_per_token_above_272k_tokens":0.00006,"output_cost_per_token_above_272k_tokens":0.00027,"input_cost_per_token_above_272k_tokens_flex":0.00003,"output_cost_per_token_above_272k_tokens_flex":0.000135},"list_pricing":{"input_cost_per_token":0.00003,"output_cost_per_token":0.00018,"input_cost_per_token_flex":0.000015,"output_cost_per_token_flex":0.00009,"input_cost_per_token_batches":0.000015,"output_cost_per_token_batches":0.00009,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"input_cost_per_token_above_272k_tokens":0.00006,"output_cost_per_token_above_272k_tokens":0.00027,"input_cost_per_token_above_272k_tokens_flex":0.00003,"output_cost_per_token_above_272k_tokens_flex":0.000135},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":1},{"id":"gpt-5.4-2026-03-05","object":"model","created":1772734352,"owned_by":"openai","mode":"chat","context_length":1050000,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2.5e-6,"output_cost_per_token":0.000015,"input_cost_per_token_flex":1.25e-6,"output_cost_per_token_flex":7.5e-6,"cache_read_input_token_cost":2.5e-7,"input_cost_per_token_batches":1.25e-6,"input_cost_per_token_priority":5e-6,"output_cost_per_token_batches":7.5e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"output_cost_per_token_priority":0.00003,"cache_read_input_token_cost_flex":1.3e-7,"cache_read_input_token_cost_batches":1.3e-7,"cache_read_input_token_cost_priority":5e-7,"input_cost_per_token_above_272k_tokens":5e-6,"output_cost_per_token_above_272k_tokens":0.0000225,"input_cost_per_token_above_272k_tokens_flex":2.5e-6,"output_cost_per_token_above_272k_tokens_flex":0.00001125,"cache_read_input_token_cost_above_272k_tokens":5e-7,"cache_read_input_token_cost_above_272k_tokens_flex":2.5e-7},"pricing_endpoint":"openai/gpt-5.4-2026-03-05","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"openai/gpt-5.4-2026-03-05","object":"model","created":1772734352,"owned_by":"openai","model_name":"gpt-5.4-2026-03-05","context_length":1050000,"max_input_tokens":922000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2.5e-6,"output_cost_per_token":0.000015,"input_cost_per_token_flex":1.25e-6,"output_cost_per_token_flex":7.5e-6,"cache_read_input_token_cost":2.5e-7,"input_cost_per_token_batches":1.25e-6,"input_cost_per_token_priority":5e-6,"output_cost_per_token_batches":7.5e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"output_cost_per_token_priority":0.00003,"cache_read_input_token_cost_flex":1.3e-7,"cache_read_input_token_cost_batches":1.3e-7,"cache_read_input_token_cost_priority":5e-7,"input_cost_per_token_above_272k_tokens":5e-6,"output_cost_per_token_above_272k_tokens":0.0000225,"input_cost_per_token_above_272k_tokens_flex":2.5e-6,"output_cost_per_token_above_272k_tokens_flex":0.00001125,"cache_read_input_token_cost_above_272k_tokens":5e-7,"cache_read_input_token_cost_above_272k_tokens_flex":2.5e-7},"list_pricing":{"input_cost_per_token":2.5e-6,"output_cost_per_token":0.000015,"input_cost_per_token_flex":1.25e-6,"output_cost_per_token_flex":7.5e-6,"cache_read_input_token_cost":2.5e-7,"input_cost_per_token_batches":1.25e-6,"input_cost_per_token_priority":5e-6,"output_cost_per_token_batches":7.5e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"output_cost_per_token_priority":0.00003,"cache_read_input_token_cost_flex":1.3e-7,"cache_read_input_token_cost_batches":1.3e-7,"cache_read_input_token_cost_priority":5e-7,"input_cost_per_token_above_272k_tokens":5e-6,"output_cost_per_token_above_272k_tokens":0.0000225,"input_cost_per_token_above_272k_tokens_flex":2.5e-6,"output_cost_per_token_above_272k_tokens_flex":0.00001125,"cache_read_input_token_cost_above_272k_tokens":5e-7,"cache_read_input_token_cost_above_272k_tokens_flex":2.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":1},{"id":"devstral-2-123b-instruct-2512","object":"model","created":1772697599,"owned_by":"mistral","mode":"chat","context_length":256000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4e-7,"output_cost_per_token":2e-6,"input_cost_per_token_flex":2e-7,"output_cost_per_token_flex":1e-6,"input_cost_per_token_priority":7e-7,"output_cost_per_token_priority":3.5e-6},"pricing_endpoint":"amazon/mistral.devstral-2-123b","regions":[{"code":"eu","name":"Europe"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"amazon/mistral.devstral-2-123b","object":"model","created":1772697599,"owned_by":"amazon","model_name":"mistral.devstral-2-123b","context_length":256000,"max_input_tokens":256000,"max_output_tokens":32000,"quantization":null,"retirement_date":null,"description":null,"source":"https://aws.amazon.com/bedrock/pricing/","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4e-7,"output_cost_per_token":2e-6,"input_cost_per_token_flex":2e-7,"output_cost_per_token_flex":1e-6,"input_cost_per_token_priority":7e-7,"output_cost_per_token_priority":3.5e-6},"list_pricing":{"input_cost_per_token":4e-7,"output_cost_per_token":2e-6,"input_cost_per_token_flex":2e-7,"output_cost_per_token_flex":1e-6,"input_cost_per_token_priority":7e-7,"output_cost_per_token_priority":3.5e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/mistral.devstral-2-123b@us","object":"model","created":1772697599,"owned_by":"amazon","model_name":"mistral.devstral-2-123b","context_length":256000,"max_input_tokens":256000,"max_output_tokens":32000,"quantization":null,"retirement_date":null,"description":null,"source":"https://aws.amazon.com/bedrock/pricing/","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4e-7,"output_cost_per_token":2e-6,"input_cost_per_token_flex":2e-7,"output_cost_per_token_flex":1e-6,"input_cost_per_token_priority":7e-7,"output_cost_per_token_priority":3.5e-6},"list_pricing":{"input_cost_per_token":4e-7,"output_cost_per_token":2e-6,"input_cost_per_token_flex":2e-7,"output_cost_per_token_flex":1e-6,"input_cost_per_token_priority":7e-7,"output_cost_per_token_priority":3.5e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"scaleway/devstral-2-123b-instruct-2512","object":"model","created":1766496679,"owned_by":"scaleway","model_name":"devstral-2-123b-instruct-2512","context_length":200000,"max_input_tokens":null,"max_output_tokens":16384,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4.593999547491045e-7,"output_cost_per_token":2.296999773745522e-6},"list_pricing":{"input_cost_per_token":4.593999547491045e-7,"output_cost_per_token":2.296999773745522e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":3},{"id":"jamba-1-5-large","object":"model","created":1772632546,"owned_by":"ai21","mode":"chat","context_length":256000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":8e-6},"pricing_endpoint":"amazon/ai21.jamba-1-5-large-v1:0","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"amazon/ai21.jamba-1-5-large-v1:0","object":"model","created":1772632546,"owned_by":"amazon","model_name":"ai21.jamba-1-5-large-v1:0","context_length":256000,"max_input_tokens":256000,"max_output_tokens":4096,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":8e-6},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":8e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"jamba-1-5-mini","object":"model","created":1772632546,"owned_by":"ai21","mode":"chat","context_length":256000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":4e-7},"pricing_endpoint":"amazon/ai21.jamba-1-5-mini-v1:0","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"amazon/ai21.jamba-1-5-mini-v1:0","object":"model","created":1772632546,"owned_by":"amazon","model_name":"ai21.jamba-1-5-mini-v1:0","context_length":256000,"max_input_tokens":256000,"max_output_tokens":4096,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":4e-7},"list_pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":4e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"llama3-70b-instruct","object":"model","created":1772632546,"owned_by":"meta","mode":"chat","context_length":8192,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.18e-6,"output_cost_per_token":4.2e-6},"pricing_endpoint":"amazon/meta.llama3-70b-instruct-v1:0","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"amazon/meta.llama3-70b-instruct-v1:0","object":"model","created":1772632546,"owned_by":"amazon","model_name":"meta.llama3-70b-instruct-v1:0","context_length":8192,"max_input_tokens":8192,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.18e-6,"output_cost_per_token":4.2e-6},"list_pricing":{"input_cost_per_token":3.18e-6,"output_cost_per_token":4.2e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"llama3-8b-instruct","object":"model","created":1772632546,"owned_by":"meta","mode":"chat","context_length":8192,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-8,"output_cost_per_token":6e-8},"pricing_endpoint":"deepinfra/meta-llama/Meta-Llama-3-8B-Instruct","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"amazon/meta.llama3-8b-instruct-v1:0","object":"model","created":1772632546,"owned_by":"amazon","model_name":"meta.llama3-8b-instruct-v1:0","context_length":8192,"max_input_tokens":8192,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.6e-7,"output_cost_per_token":7.2e-7},"list_pricing":{"input_cost_per_token":3.6e-7,"output_cost_per_token":7.2e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"deepinfra/meta-llama/Meta-Llama-3-8B-Instruct","object":"model","created":1767692616,"owned_by":"deepinfra","model_name":"meta-llama/Meta-Llama-3-8B-Instruct","context_length":8192,"max_input_tokens":8192,"max_output_tokens":8192,"quantization":null,"retirement_date":null,"description":"","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-8,"output_cost_per_token":6e-8},"list_pricing":{"input_cost_per_token":3e-8,"output_cost_per_token":6e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"mistral-7b-instruct-v0.2","object":"model","created":1772632546,"owned_by":"mistral","mode":"chat","context_length":32000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":2.6e-7},"pricing_endpoint":"amazon/mistral.mistral-7b-instruct-v0:2","regions":[{"code":"eu","name":"Europe"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"amazon/mistral.mistral-7b-instruct-v0:2","object":"model","created":1772632546,"owned_by":"amazon","model_name":"mistral.mistral-7b-instruct-v0:2","context_length":32000,"max_input_tokens":32000,"max_output_tokens":4096,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":2.6e-7},"list_pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":2.6e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/mistral.mistral-7b-instruct-v0:2@us","object":"model","created":1772632546,"owned_by":"amazon","model_name":"mistral.mistral-7b-instruct-v0:2","context_length":32000,"max_input_tokens":32000,"max_output_tokens":4096,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":2.6e-7},"list_pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":2.6e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"mistral-small-2402","object":"model","created":1772632546,"owned_by":"mistral","mode":"chat","context_length":32000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":3e-6},"pricing_endpoint":"amazon/mistral.mistral-small-2402-v1:0","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"amazon/mistral.mistral-small-2402-v1:0","object":"model","created":1772632546,"owned_by":"amazon","model_name":"mistral.mistral-small-2402-v1:0","context_length":32000,"max_input_tokens":32000,"max_output_tokens":4096,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":3e-6},"list_pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":3e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"mixtral-8x7b-instruct-v0.1","object":"model","created":1772632546,"owned_by":"mistral","mode":"chat","context_length":32768,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4e-7,"output_cost_per_token":4e-7},"pricing_endpoint":"deepinfra/mistralai/Mixtral-8x7B-Instruct-v0.1","regions":[{"code":"eu","name":"Europe"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"amazon/mistral.mixtral-8x7b-instruct-v0:1","object":"model","created":1772632546,"owned_by":"amazon","model_name":"mistral.mixtral-8x7b-instruct-v0:1","context_length":32000,"max_input_tokens":32000,"max_output_tokens":4096,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5.9e-7,"output_cost_per_token":9.1e-7},"list_pricing":{"input_cost_per_token":5.9e-7,"output_cost_per_token":9.1e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/mistral.mixtral-8x7b-instruct-v0:1@us","object":"model","created":1772632546,"owned_by":"amazon","model_name":"mistral.mixtral-8x7b-instruct-v0:1","context_length":32000,"max_input_tokens":32000,"max_output_tokens":4096,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5.9e-7,"output_cost_per_token":9.1e-7},"list_pricing":{"input_cost_per_token":5.9e-7,"output_cost_per_token":9.1e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"deepinfra/mistralai/Mixtral-8x7B-Instruct-v0.1","object":"model","created":1767692616,"owned_by":"deepinfra","model_name":"mistralai/Mixtral-8x7B-Instruct-v0.1","context_length":32768,"max_input_tokens":32768,"max_output_tokens":32768,"quantization":null,"retirement_date":null,"description":"","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4e-7,"output_cost_per_token":4e-7},"list_pricing":{"input_cost_per_token":4e-7,"output_cost_per_token":4e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":3},{"id":"seed-2-0-mini-260428","object":"model","created":1772131107,"owned_by":"bytedance","mode":"chat","context_length":262144,"capabilities":{"input_modalities":["text","image","video","audio"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":4e-7,"input_cost_per_token_above_128k_tokens":2e-7,"output_cost_per_token_above_128k_tokens":8e-7},"pricing_endpoint":"bytedance/seed-2-0-mini-260428","regions":[{"code":"ap","name":"Asia"}],"alias_of":null,"endpoints":[{"id":"bytedance/seed-2-0-mini-260428","object":"model","created":1772131107,"owned_by":"bytedance","model_name":"seed-2-0-mini-260428","context_length":262144,"max_input_tokens":229376,"max_output_tokens":131072,"quantization":"fp8","retirement_date":null,"description":"Seed-2.0-mini targets latency-sensitive, high-concurrency, and cost-sensitive scenarios, emphasizing fast response and flexible inference deployment.","source":null,"capabilities":{"input_modalities":["text","image","video","audio"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":4e-7,"input_cost_per_token_above_128k_tokens":2e-7,"output_cost_per_token_above_128k_tokens":8e-7},"list_pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":4e-7,"input_cost_per_token_above_128k_tokens":2e-7,"output_cost_per_token_above_128k_tokens":8e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"ap","name":"Asia"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":1},{"id":"gemini-3.1-flash-image-preview","object":"model","created":1772119558,"owned_by":"google","mode":"chat","context_length":65536,"capabilities":{"input_modalities":["image","text"],"output_modalities":["image","text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":false,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":3e-6,"output_cost_per_image_token":0.00006,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014}},"pricing_endpoint":"google/gemini-3.1-flash-image-preview","regions":[{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"google/gemini-3.1-flash-image-preview","object":"model","created":1772119558,"owned_by":"google","model_name":"gemini-3.1-flash-image-preview","context_length":65536,"max_input_tokens":65536,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"Gemini 3.1 Flash Image, a.k.a. \"Nano Banana 2,\" is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed.","source":"https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models","capabilities":{"input_modalities":["image","text"],"output_modalities":["image","text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":false,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":3e-6,"output_cost_per_image_token":0.00006,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014}},"list_pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":3e-6,"output_cost_per_image_token":0.00006,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014}},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":1},{"id":"qwen3.5-35b-a3b","object":"model","created":1772053822,"owned_by":"qwen","mode":"chat","context_length":262144,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.4e-7,"output_cost_per_token":1e-6,"cache_read_input_token_cost":5.000000040000001e-8},"pricing_endpoint":"deepinfra/Qwen/Qwen3.5-35B-A3B","regions":[{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"deepinfra/Qwen/Qwen3.5-35B-A3B","object":"model","created":1772053822,"owned_by":"deepinfra","model_name":"Qwen/Qwen3.5-35B-A3B","context_length":262144,"max_input_tokens":262144,"max_output_tokens":81920,"quantization":"fp8","retirement_date":null,"description":"The Qwen3.5 Series 35B-A3B is a native vision-language model designed with a hybrid architecture that integrates linear attention mechanisms and a sparse mixture-of-experts model, achieving higher inference efficiency.","source":null,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.4e-7,"output_cost_per_token":1e-6,"cache_read_input_token_cost":5.000000040000001e-8},"list_pricing":{"input_cost_per_token":1.4e-7,"output_cost_per_token":1e-6,"cache_read_input_token_cost":5.000000040000001e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"qwen/qwen3.5-35b-a3b","object":"model","created":1772053822,"owned_by":"qwen","model_name":"qwen3.5-35b-a3b","context_length":262144,"max_input_tokens":260096,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"The Qwen3.5 Series 35B-A3B is a native vision-language model designed with a hybrid architecture that integrates linear attention mechanisms and a sparse mixture-of-experts model, achieving higher inference efficiency. Its overall performance is comparable to that of the Qwen3.5-27B.","source":null,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.625e-7,"output_cost_per_token":1.3e-6},"list_pricing":{"input_cost_per_token":2.5e-7,"output_cost_per_token":2e-6},"discount":0.35,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":2},{"id":"qwen3.5-27b","object":"model","created":1772053810,"owned_by":"qwen","mode":"chat","context_length":262144,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.9499999999999999e-7,"output_cost_per_token":1.5599999999999999e-6},"pricing_endpoint":"qwen/qwen3.5-27b","regions":[{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"deepinfra/Qwen/Qwen3.5-27B","object":"model","created":1772053810,"owned_by":"deepinfra","model_name":"Qwen/Qwen3.5-27B","context_length":262144,"max_input_tokens":262144,"max_output_tokens":81920,"quantization":"fp8","retirement_date":null,"description":"The Qwen3.5 27B native vision-language Dense model incorporates a linear attention mechanism, delivering fast response times while balancing inference speed and performance.","source":null,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.6e-7,"output_cost_per_token":2.5999999999999997e-6},"list_pricing":{"input_cost_per_token":2.6e-7,"output_cost_per_token":2.5999999999999997e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"qwen/qwen3.5-27b","object":"model","created":1772053810,"owned_by":"qwen","model_name":"qwen3.5-27b","context_length":262144,"max_input_tokens":260096,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"The Qwen3.5 27B native vision-language Dense model incorporates a linear attention mechanism, delivering fast response times while balancing inference speed and performance. Its overall capabilities are comparable to those of the Qwen3.5-122B-A10B.","source":null,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.9499999999999999e-7,"output_cost_per_token":1.5599999999999999e-6},"list_pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":2.4e-6},"discount":0.35,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":2},{"id":"gemini-3.1-pro-preview-customtools","object":"model","created":1772045923,"owned_by":"google","mode":"chat","context_length":1048576,"capabilities":{"input_modalities":["text","audio","image","video","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.000012,"input_cost_per_token_flex":1e-6,"input_cost_per_audio_token":2e-6,"input_cost_per_image_token":2e-6,"output_cost_per_token_flex":6e-6,"cache_read_input_token_cost":2e-7,"input_cost_per_token_priority":3.6e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.0000216,"cache_creation_input_token_cost":3.75e-7,"output_cost_per_reasoning_token":0.000012,"cache_read_input_token_cost_flex":2e-7,"cache_read_input_audio_token_cost":2e-7,"cache_read_input_token_cost_priority":3.6e-7,"google_maps_grounding_cost_per_query":0.014,"input_cost_per_token_above_200k_tokens":4e-6,"output_cost_per_token_above_200k_tokens":0.000018,"input_cost_per_token_above_200k_tokens_flex":2e-6,"input_cost_per_audio_token_above_200k_tokens":4e-6,"output_cost_per_token_above_200k_tokens_flex":9e-6,"cache_read_input_token_cost_above_200k_tokens":4e-7,"input_cost_per_token_above_200k_tokens_priority":7.2e-6,"output_cost_per_token_above_200k_tokens_priority":0.0000324,"cache_read_input_token_cost_above_200k_tokens_flex":4e-7,"cache_read_input_audio_token_cost_above_200k_tokens":4e-7,"cache_read_input_token_cost_above_200k_tokens_priority":7.2e-7},"pricing_endpoint":"google/gemini-3.1-pro-preview-customtools","regions":[{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"google/gemini-3.1-pro-preview-customtools","object":"model","created":1772045923,"owned_by":"google","model_name":"gemini-3.1-pro-preview-customtools","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"Gemini 3.1 Pro Preview Custom Tools is a variant of Gemini 3.1 Pro that improves tool selection behavior by preventing overuse of a general bash tool when more efficient third-party...","source":"https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models","capabilities":{"input_modalities":["text","audio","image","video","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.000012,"input_cost_per_token_flex":1e-6,"input_cost_per_audio_token":2e-6,"input_cost_per_image_token":2e-6,"output_cost_per_token_flex":6e-6,"cache_read_input_token_cost":2e-7,"input_cost_per_token_priority":3.6e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.0000216,"cache_creation_input_token_cost":3.75e-7,"output_cost_per_reasoning_token":0.000012,"cache_read_input_token_cost_flex":2e-7,"cache_read_input_audio_token_cost":2e-7,"cache_read_input_token_cost_priority":3.6e-7,"google_maps_grounding_cost_per_query":0.014,"input_cost_per_token_above_200k_tokens":4e-6,"output_cost_per_token_above_200k_tokens":0.000018,"input_cost_per_token_above_200k_tokens_flex":2e-6,"input_cost_per_audio_token_above_200k_tokens":4e-6,"output_cost_per_token_above_200k_tokens_flex":9e-6,"cache_read_input_token_cost_above_200k_tokens":4e-7,"input_cost_per_token_above_200k_tokens_priority":7.2e-6,"output_cost_per_token_above_200k_tokens_priority":0.0000324,"cache_read_input_token_cost_above_200k_tokens_flex":4e-7,"cache_read_input_audio_token_cost_above_200k_tokens":4e-7,"cache_read_input_token_cost_above_200k_tokens_priority":7.2e-7},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.000012,"input_cost_per_token_flex":1e-6,"input_cost_per_audio_token":2e-6,"input_cost_per_image_token":2e-6,"output_cost_per_token_flex":6e-6,"cache_read_input_token_cost":2e-7,"input_cost_per_token_priority":3.6e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.0000216,"cache_creation_input_token_cost":3.75e-7,"output_cost_per_reasoning_token":0.000012,"cache_read_input_token_cost_flex":2e-7,"cache_read_input_audio_token_cost":2e-7,"cache_read_input_token_cost_priority":3.6e-7,"google_maps_grounding_cost_per_query":0.014,"input_cost_per_token_above_200k_tokens":4e-6,"output_cost_per_token_above_200k_tokens":0.000018,"input_cost_per_token_above_200k_tokens_flex":2e-6,"input_cost_per_audio_token_above_200k_tokens":4e-6,"output_cost_per_token_above_200k_tokens_flex":9e-6,"cache_read_input_token_cost_above_200k_tokens":4e-7,"input_cost_per_token_above_200k_tokens_priority":7.2e-6,"output_cost_per_token_above_200k_tokens_priority":0.0000324,"cache_read_input_token_cost_above_200k_tokens_flex":4e-7,"cache_read_input_audio_token_cost_above_200k_tokens":4e-7,"cache_read_input_token_cost_above_200k_tokens_priority":7.2e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":1},{"id":"devstral-latest","object":"model","created":1771588786,"owned_by":"mistral","mode":"chat","context_length":262144,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4e-7,"output_cost_per_token":2e-6},"pricing_endpoint":"mistral/devstral-latest","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"mistral/devstral-latest@eu","object":"model","created":1771588786,"owned_by":"mistral","model_name":"devstral-latest","context_length":262144,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":"2026-08-31","description":null,"source":"https://mistral.ai/news/devstral-2-vibe-cli","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4.4e-7,"output_cost_per_token":2.2e-6},"list_pricing":{"input_cost_per_token":4.4e-7,"output_cost_per_token":2.2e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"mistral/devstral-latest","object":"model","created":1771588786,"owned_by":"mistral","model_name":"devstral-latest","context_length":262144,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":"2026-08-31","description":null,"source":"https://mistral.ai/news/devstral-2-vibe-cli","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4e-7,"output_cost_per_token":2e-6},"list_pricing":{"input_cost_per_token":4e-7,"output_cost_per_token":2e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"devstral-medium-latest","object":"model","created":1771588786,"owned_by":"mistral","mode":"chat","context_length":262144,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4e-7,"output_cost_per_token":2e-6},"pricing_endpoint":"mistral/devstral-medium-latest","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"mistral/devstral-medium-latest@eu","object":"model","created":1771588786,"owned_by":"mistral","model_name":"devstral-medium-latest","context_length":262144,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":"2026-08-31","description":null,"source":"https://mistral.ai/news/devstral-2-vibe-cli","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4.4e-7,"output_cost_per_token":2.2e-6},"list_pricing":{"input_cost_per_token":4.4e-7,"output_cost_per_token":2.2e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"mistral/devstral-medium-latest","object":"model","created":1771588786,"owned_by":"mistral","model_name":"devstral-medium-latest","context_length":262144,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":"2026-08-31","description":null,"source":"https://mistral.ai/news/devstral-2-vibe-cli","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4e-7,"output_cost_per_token":2e-6},"list_pricing":{"input_cost_per_token":4e-7,"output_cost_per_token":2e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"devstral-small-latest","object":"model","created":1771588786,"owned_by":"mistral","mode":"chat","context_length":256000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":3e-7},"pricing_endpoint":"mistral/devstral-small-latest","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"mistral/devstral-small-latest@eu","object":"model","created":1771588786,"owned_by":"mistral","model_name":"devstral-small-latest","context_length":256000,"max_input_tokens":256000,"max_output_tokens":256000,"quantization":null,"retirement_date":null,"description":"","source":"https://docs.mistral.ai/models/devstral-small-2-25-12","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.1e-7,"output_cost_per_token":3.3e-7},"list_pricing":{"input_cost_per_token":1.1e-7,"output_cost_per_token":3.3e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"mistral/devstral-small-latest","object":"model","created":1771588786,"owned_by":"mistral","model_name":"devstral-small-latest","context_length":256000,"max_input_tokens":256000,"max_output_tokens":256000,"quantization":null,"retirement_date":null,"description":"","source":"https://docs.mistral.ai/models/devstral-small-2-25-12","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":3e-7},"list_pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":3e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"gemini-3.1-pro-preview","object":"model","created":1771509627,"owned_by":"google","mode":"chat","context_length":1048576,"capabilities":{"input_modalities":["audio","file","image","text","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.000012,"input_cost_per_token_flex":1e-6,"input_cost_per_audio_token":2e-6,"input_cost_per_image_token":2e-6,"output_cost_per_token_flex":6e-6,"cache_read_input_token_cost":2e-7,"input_cost_per_token_priority":3.6e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.0000216,"cache_creation_input_token_cost":3.75e-7,"output_cost_per_reasoning_token":0.000012,"cache_read_input_token_cost_flex":2e-7,"cache_read_input_audio_token_cost":2e-7,"cache_read_input_token_cost_priority":3.6e-7,"google_maps_grounding_cost_per_query":0.014,"input_cost_per_token_above_200k_tokens":4e-6,"output_cost_per_token_above_200k_tokens":0.000018,"input_cost_per_token_above_200k_tokens_flex":2e-6,"input_cost_per_audio_token_above_200k_tokens":4e-6,"output_cost_per_token_above_200k_tokens_flex":9e-6,"cache_read_input_token_cost_above_200k_tokens":4e-7,"input_cost_per_token_above_200k_tokens_priority":7.2e-6,"output_cost_per_token_above_200k_tokens_priority":0.0000324,"cache_read_input_token_cost_above_200k_tokens_flex":4e-7,"cache_read_input_audio_token_cost_above_200k_tokens":4e-7,"cache_read_input_token_cost_above_200k_tokens_priority":7.2e-7},"pricing_endpoint":"google/gemini-3.1-pro-preview","regions":[{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"google/gemini-3.1-pro-preview","object":"model","created":1771509627,"owned_by":"google","model_name":"gemini-3.1-pro-preview","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage across complex workflows.","source":"https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models","capabilities":{"input_modalities":["audio","file","image","text","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.000012,"input_cost_per_token_flex":1e-6,"input_cost_per_audio_token":2e-6,"input_cost_per_image_token":2e-6,"output_cost_per_token_flex":6e-6,"cache_read_input_token_cost":2e-7,"input_cost_per_token_priority":3.6e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.0000216,"cache_creation_input_token_cost":3.75e-7,"output_cost_per_reasoning_token":0.000012,"cache_read_input_token_cost_flex":2e-7,"cache_read_input_audio_token_cost":2e-7,"cache_read_input_token_cost_priority":3.6e-7,"google_maps_grounding_cost_per_query":0.014,"input_cost_per_token_above_200k_tokens":4e-6,"output_cost_per_token_above_200k_tokens":0.000018,"input_cost_per_token_above_200k_tokens_flex":2e-6,"input_cost_per_audio_token_above_200k_tokens":4e-6,"output_cost_per_token_above_200k_tokens_flex":9e-6,"cache_read_input_token_cost_above_200k_tokens":4e-7,"input_cost_per_token_above_200k_tokens_priority":7.2e-6,"output_cost_per_token_above_200k_tokens_priority":0.0000324,"cache_read_input_token_cost_above_200k_tokens_flex":4e-7,"cache_read_input_audio_token_cost_above_200k_tokens":4e-7,"cache_read_input_token_cost_above_200k_tokens_priority":7.2e-7},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.000012,"input_cost_per_token_flex":1e-6,"input_cost_per_audio_token":2e-6,"input_cost_per_image_token":2e-6,"output_cost_per_token_flex":6e-6,"cache_read_input_token_cost":2e-7,"input_cost_per_token_priority":3.6e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.0000216,"cache_creation_input_token_cost":3.75e-7,"output_cost_per_reasoning_token":0.000012,"cache_read_input_token_cost_flex":2e-7,"cache_read_input_audio_token_cost":2e-7,"cache_read_input_token_cost_priority":3.6e-7,"google_maps_grounding_cost_per_query":0.014,"input_cost_per_token_above_200k_tokens":4e-6,"output_cost_per_token_above_200k_tokens":0.000018,"input_cost_per_token_above_200k_tokens_flex":2e-6,"input_cost_per_audio_token_above_200k_tokens":4e-6,"output_cost_per_token_above_200k_tokens_flex":9e-6,"cache_read_input_token_cost_above_200k_tokens":4e-7,"input_cost_per_token_above_200k_tokens_priority":7.2e-6,"output_cost_per_token_above_200k_tokens_priority":0.0000324,"cache_read_input_token_cost_above_200k_tokens_flex":4e-7,"cache_read_input_audio_token_cost_above_200k_tokens":4e-7,"cache_read_input_token_cost_above_200k_tokens_priority":7.2e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"vertex/gemini-3.1-pro-preview","object":"model","created":1771509627,"owned_by":"vertex","model_name":"gemini-3.1-pro-preview","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage across complex workflows.","source":null,"capabilities":{"input_modalities":["audio","file","image","text","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_image":0.00012,"output_cost_per_token":0.000012,"input_cost_per_token_flex":1e-6,"input_cost_per_audio_token":2e-6,"input_cost_per_image_token":2e-6,"output_cost_per_token_flex":6e-6,"cache_read_input_token_cost":2e-7,"input_cost_per_token_priority":3.6e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.0000216,"cache_creation_input_token_cost":3.75e-7,"output_cost_per_reasoning_token":0.000012,"cache_read_input_audio_token_cost":2e-7,"cache_read_input_token_cost_priority":3.6e-7,"google_maps_grounding_cost_per_query":0.014,"input_cost_per_token_above_200k_tokens":4e-6,"output_cost_per_token_above_200k_tokens":0.000018,"input_cost_per_token_above_200k_tokens_flex":2e-6,"input_cost_per_audio_token_above_200k_tokens":4e-6,"output_cost_per_token_above_200k_tokens_flex":9e-6,"cache_read_input_token_cost_above_200k_tokens":4e-7,"input_cost_per_token_above_200k_tokens_priority":7.2e-6,"output_cost_per_token_above_200k_tokens_priority":0.0000324,"cache_read_input_audio_token_cost_above_200k_tokens":4e-7,"cache_read_input_token_cost_above_200k_tokens_priority":7.2e-7},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_image":0.00012,"output_cost_per_token":0.000012,"input_cost_per_token_flex":1e-6,"input_cost_per_audio_token":2e-6,"input_cost_per_image_token":2e-6,"output_cost_per_token_flex":6e-6,"cache_read_input_token_cost":2e-7,"input_cost_per_token_priority":3.6e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.0000216,"cache_creation_input_token_cost":3.75e-7,"output_cost_per_reasoning_token":0.000012,"cache_read_input_audio_token_cost":2e-7,"cache_read_input_token_cost_priority":3.6e-7,"google_maps_grounding_cost_per_query":0.014,"input_cost_per_token_above_200k_tokens":4e-6,"output_cost_per_token_above_200k_tokens":0.000018,"input_cost_per_token_above_200k_tokens_flex":2e-6,"input_cost_per_audio_token_above_200k_tokens":4e-6,"output_cost_per_token_above_200k_tokens_flex":9e-6,"cache_read_input_token_cost_above_200k_tokens":4e-7,"input_cost_per_token_above_200k_tokens_priority":7.2e-6,"output_cost_per_token_above_200k_tokens_priority":0.0000324,"cache_read_input_audio_token_cost_above_200k_tokens":4e-7,"cache_read_input_token_cost_above_200k_tokens_priority":7.2e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"glm-4.7","object":"model","created":1770991619,"owned_by":"zai","mode":"chat","context_length":203000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4.0000000000000003e-7,"output_cost_per_token":1.75e-6,"cache_read_input_token_cost":8.000000000000001e-8},"pricing_endpoint":"deepinfra/zai-org/GLM-4.7","regions":[{"code":"ap","name":"Asia"},{"code":"eu","name":"Europe"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"amazon/zai.glm-4.7","object":"model","created":1770991619,"owned_by":"amazon","model_name":"zai.glm-4.7","context_length":203000,"max_input_tokens":203000,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":null,"source":"https://aws.amazon.com/bedrock/pricing/","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6e-7,"output_cost_per_token":2.2e-6,"input_cost_per_token_flex":3e-7,"output_cost_per_token_flex":1.1e-6,"input_cost_per_token_priority":1.05e-6,"output_cost_per_token_priority":3.85e-6},"list_pricing":{"input_cost_per_token":6e-7,"output_cost_per_token":2.2e-6,"input_cost_per_token_flex":3e-7,"output_cost_per_token_flex":1.1e-6,"input_cost_per_token_priority":1.05e-6,"output_cost_per_token_priority":3.85e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/zai.glm-4.7@us","object":"model","created":1770991619,"owned_by":"amazon","model_name":"zai.glm-4.7","context_length":203000,"max_input_tokens":203000,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":null,"source":"https://aws.amazon.com/bedrock/pricing/","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6e-7,"output_cost_per_token":2.2e-6,"input_cost_per_token_flex":3e-7,"output_cost_per_token_flex":1.1e-6,"input_cost_per_token_priority":1.05e-6,"output_cost_per_token_priority":3.85e-6},"list_pricing":{"input_cost_per_token":6e-7,"output_cost_per_token":2.2e-6,"input_cost_per_token_flex":3e-7,"output_cost_per_token_flex":1.1e-6,"input_cost_per_token_priority":1.05e-6,"output_cost_per_token_priority":3.85e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"deepinfra/zai-org/GLM-4.7","object":"model","created":1766378014,"owned_by":"deepinfra","model_name":"zai-org/GLM-4.7","context_length":202752,"max_input_tokens":202752,"max_output_tokens":131072,"quantization":"fp4","retirement_date":"2026-12-31","description":"GLM-4.7 is Z.ai’s latest flagship model, featuring upgrades in two key areas: enhanced programming capabilities and more stable multi-step reasoning/execution.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4.0000000000000003e-7,"output_cost_per_token":1.75e-6,"cache_read_input_token_cost":8.000000000000001e-8},"list_pricing":{"input_cost_per_token":4.0000000000000003e-7,"output_cost_per_token":1.75e-6,"cache_read_input_token_cost":8.000000000000001e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"zai/glm-4.7","object":"model","created":1766378014,"owned_by":"zai","model_name":"glm-4.7","context_length":202752,"max_input_tokens":200000,"max_output_tokens":131072,"quantization":"fp4","retirement_date":"2026-12-31","description":"GLM-4.7 is Z.ai’s latest flagship model, featuring upgrades in two key areas: enhanced programming capabilities and more stable multi-step reasoning/execution.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6e-7,"output_cost_per_token":2.2e-6,"cache_read_input_token_cost":1.1e-7,"cache_creation_input_token_cost":0.0},"list_pricing":{"input_cost_per_token":6e-7,"output_cost_per_token":2.2e-6,"cache_read_input_token_cost":1.1e-7,"cache_creation_input_token_cost":0.0},"discount":null,"discount_ends_at":null,"regions":[{"code":"ap","name":"Asia"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":4},{"id":"gpt-5-search-api","object":"model","created":1770991619,"owned_by":"openai","mode":"chat","context_length":272000,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":0.00001,"cache_read_input_token_cost":1.25e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01}},"pricing_endpoint":"openai/gpt-5-search-api","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"openai/gpt-5-search-api","object":"model","created":1770991619,"owned_by":"openai","model_name":"gpt-5-search-api","context_length":272000,"max_input_tokens":272000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":0.00001,"cache_read_input_token_cost":1.25e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01}},"list_pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":0.00001,"cache_read_input_token_cost":1.25e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01}},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":1},{"id":"gpt-5-search-api-2025-10-14","object":"model","created":1770991619,"owned_by":"openai","mode":"chat","context_length":272000,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":0.00001,"cache_read_input_token_cost":1.25e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01}},"pricing_endpoint":"openai/gpt-5-search-api-2025-10-14","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"openai/gpt-5-search-api-2025-10-14","object":"model","created":1770991619,"owned_by":"openai","model_name":"gpt-5-search-api-2025-10-14","context_length":272000,"max_input_tokens":272000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":0.00001,"cache_read_input_token_cost":1.25e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01}},"list_pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":0.00001,"cache_read_input_token_cost":1.25e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01}},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":1},{"id":"minimax-m2.1","object":"model","created":1770991619,"owned_by":"minimax","mode":"chat","context_length":204800,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1.2e-6,"cache_read_input_token_cost":3e-8},"pricing_endpoint":"minimax/MiniMax-M2.1","regions":[{"code":"ap","name":"Asia"},{"code":"eu","name":"Europe"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"amazon/minimax.minimax-m2.1","object":"model","created":1770991619,"owned_by":"amazon","model_name":"minimax.minimax-m2.1","context_length":196000,"max_input_tokens":196000,"max_output_tokens":8192,"quantization":null,"retirement_date":null,"description":"MiniMax-M2.1 is a lightweight, state-of-the-art large language model optimized for coding, agentic workflows, and modern application development.","source":"https://aws.amazon.com/bedrock/pricing/","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.6e-7,"output_cost_per_token":1.44e-6,"input_cost_per_token_flex":1.8e-7,"output_cost_per_token_flex":7.2e-7,"input_cost_per_token_priority":6.3e-7,"output_cost_per_token_priority":2.52e-6},"list_pricing":{"input_cost_per_token":3.6e-7,"output_cost_per_token":1.44e-6,"input_cost_per_token_flex":1.8e-7,"output_cost_per_token_flex":7.2e-7,"input_cost_per_token_priority":6.3e-7,"output_cost_per_token_priority":2.52e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/minimax.minimax-m2.1@us","object":"model","created":1770991619,"owned_by":"amazon","model_name":"minimax.minimax-m2.1","context_length":196000,"max_input_tokens":196000,"max_output_tokens":8192,"quantization":null,"retirement_date":null,"description":"MiniMax-M2.1 is a lightweight, state-of-the-art large language model optimized for coding, agentic workflows, and modern application development.","source":"https://aws.amazon.com/bedrock/pricing/","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.6e-7,"output_cost_per_token":1.44e-6,"input_cost_per_token_flex":1.8e-7,"output_cost_per_token_flex":7.2e-7,"input_cost_per_token_priority":6.3e-7,"output_cost_per_token_priority":2.52e-6},"list_pricing":{"input_cost_per_token":3.6e-7,"output_cost_per_token":1.44e-6,"input_cost_per_token_flex":1.8e-7,"output_cost_per_token_flex":7.2e-7,"input_cost_per_token_priority":6.3e-7,"output_cost_per_token_priority":2.52e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"minimax/MiniMax-M2.1","object":"model","created":1766454997,"owned_by":"minimax","model_name":"MiniMax-M2.1","context_length":204800,"max_input_tokens":null,"max_output_tokens":196000,"quantization":null,"retirement_date":"2026-11-05","description":"MiniMax-M2.1 is a lightweight, state-of-the-art large language model optimized for coding, agentic workflows, and modern application development.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1.2e-6,"cache_read_input_token_cost":3e-8},"list_pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1.2e-6,"cache_read_input_token_cost":3e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"ap","name":"Asia"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":3},{"id":"nemotron-nano-3-30b","object":"model","created":1770991619,"owned_by":"nvidia","mode":"chat","context_length":256000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6e-8,"output_cost_per_token":2.4e-7,"input_cost_per_token_flex":3e-8,"output_cost_per_token_flex":1.2e-7,"input_cost_per_token_priority":1.1e-7,"output_cost_per_token_priority":4.2e-7},"pricing_endpoint":"amazon/nvidia.nemotron-nano-3-30b","regions":[{"code":"eu","name":"Europe"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"amazon/nvidia.nemotron-nano-3-30b","object":"model","created":1770991619,"owned_by":"amazon","model_name":"nvidia.nemotron-nano-3-30b","context_length":256000,"max_input_tokens":256000,"max_output_tokens":8000,"quantization":null,"retirement_date":null,"description":null,"source":"https://aws.amazon.com/bedrock/pricing/","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6e-8,"output_cost_per_token":2.4e-7,"input_cost_per_token_flex":3e-8,"output_cost_per_token_flex":1.2e-7,"input_cost_per_token_priority":1.1e-7,"output_cost_per_token_priority":4.2e-7},"list_pricing":{"input_cost_per_token":6e-8,"output_cost_per_token":2.4e-7,"input_cost_per_token_flex":3e-8,"output_cost_per_token_flex":1.2e-7,"input_cost_per_token_priority":1.1e-7,"output_cost_per_token_priority":4.2e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/nvidia.nemotron-nano-3-30b@us","object":"model","created":1770991619,"owned_by":"amazon","model_name":"nvidia.nemotron-nano-3-30b","context_length":256000,"max_input_tokens":256000,"max_output_tokens":8000,"quantization":null,"retirement_date":null,"description":null,"source":"https://aws.amazon.com/bedrock/pricing/","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6e-8,"output_cost_per_token":2.4e-7,"input_cost_per_token_flex":3e-8,"output_cost_per_token_flex":1.2e-7,"input_cost_per_token_priority":1.1e-7,"output_cost_per_token_priority":4.2e-7},"list_pricing":{"input_cost_per_token":6e-8,"output_cost_per_token":2.4e-7,"input_cost_per_token_flex":3e-8,"output_cost_per_token_flex":1.2e-7,"input_cost_per_token_priority":1.1e-7,"output_cost_per_token_priority":4.2e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"step-3.5-flash","object":"model","created":1769728337,"owned_by":"stepfun","mode":"chat","context_length":262144,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":9e-8,"output_cost_per_token":3e-7,"cache_read_input_token_cost":1.9999999799999997e-8},"pricing_endpoint":"deepinfra/stepfun-ai/Step-3.5-Flash","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"deepinfra/stepfun-ai/Step-3.5-Flash","object":"model","created":1769728337,"owned_by":"deepinfra","model_name":"stepfun-ai/Step-3.5-Flash","context_length":262144,"max_input_tokens":null,"max_output_tokens":262144,"quantization":null,"retirement_date":null,"description":"Step 3.5 Flash is StepFun's most capable open-source foundation model. Built on a sparse Mixture of Experts (MoE) architecture, it selectively activates only 11B of its 196B parameters per token....","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":9e-8,"output_cost_per_token":3e-7,"cache_read_input_token_cost":1.9999999799999997e-8},"list_pricing":{"input_cost_per_token":9e-8,"output_cost_per_token":3e-7,"cache_read_input_token_cost":1.9999999799999997e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"claude-opus-4.1","object":"model","created":1769507058,"owned_by":"anthropic","mode":"chat","context_length":200000,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":0.000015,"output_cost_per_token":0.000075,"input_dbu_cost_per_token":0.00021429,"output_dbu_cost_per_token":0.0010714,"cache_read_input_token_cost":1.5e-6,"cache_creation_input_token_cost":0.00001875,"cache_creation_input_token_cost_above_1hr":0.00003},"pricing_endpoint":"databricks/databricks-claude-opus-4-1","regions":[{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"databricks/databricks-claude-opus-4-1","object":"model","created":1769507058,"owned_by":"databricks","model_name":"databricks-claude-opus-4-1","context_length":200000,"max_input_tokens":200000,"max_output_tokens":32000,"quantization":null,"retirement_date":null,"description":"Claude Opus 4.1 is a state-of-the-art, hybrid reasoning model built and trained by Anthropic. This general purpose large language model is designed for both complex reasoning and real-world applications at enterprise scale. It supports text and image input, with a 200K token context window and 32K output token capabilities. This model excels at tasks like code generation, research and content creation, and multi-step agents workflows without constant human intervention. This endpoint is hosted by Databricks.","source":"https://www.databricks.com/product/pricing/proprietary-foundation-model-serving","capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":0.000015,"output_cost_per_token":0.000075,"input_dbu_cost_per_token":0.00021429,"output_dbu_cost_per_token":0.0010714,"cache_read_input_token_cost":1.5e-6,"cache_creation_input_token_cost":0.00001875,"cache_creation_input_token_cost_above_1hr":0.00003},"list_pricing":{"input_cost_per_token":0.000015,"output_cost_per_token":0.000075,"input_dbu_cost_per_token":0.00021429,"output_dbu_cost_per_token":0.0010714,"cache_read_input_token_cost":1.5e-6,"cache_creation_input_token_cost":0.00001875,"cache_creation_input_token_cost_above_1hr":0.00003},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":1},{"id":"claude-opus-4.5","object":"model","created":1769507058,"owned_by":"anthropic","mode":"chat","context_length":200000,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"supports_output_config":true},"pricing":{"input_cost_per_token":5e-6,"output_cost_per_token":0.000025,"cache_read_input_token_cost":5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.25e-6,"cache_creation_input_token_cost_above_1hr":0.00001},"pricing_endpoint":"anthropic/claude-opus-4-5","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"databricks/databricks-claude-opus-4-5@eu","object":"model","created":1769507058,"owned_by":"databricks","model_name":"databricks-claude-opus-4-5","context_length":200000,"max_input_tokens":200000,"max_output_tokens":64000,"quantization":null,"retirement_date":null,"description":"Claude Opus 4.5 is a large language model built and trained by Anthropic for production software engineering and sophisticated multi-tool agents. It supports text and image input with a 200K token context window. The model is designed for professional tasks requiring complex reasoning across multiple systems, including code generation, document creation, spreadsheets, presentations, and multi-step agent workflows. It features advanced tool use capabilities including tool search and programmatic tool calling for agents working with large tool libraries. This endpoint is hosted by Databricks.","source":"https://www.databricks.com/product/pricing/proprietary-foundation-model-serving","capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"supports_output_config":true},"pricing":{"input_cost_per_token":5e-6,"output_cost_per_token":0.000025,"input_dbu_cost_per_token":0.000071429,"output_dbu_cost_per_token":0.00035714,"cache_read_input_token_cost":5e-7,"cache_creation_input_token_cost":6.25e-6,"cache_creation_input_token_cost_above_1hr":0.00001},"list_pricing":{"input_cost_per_token":5e-6,"output_cost_per_token":0.000025,"input_dbu_cost_per_token":0.000071429,"output_dbu_cost_per_token":0.00035714,"cache_read_input_token_cost":5e-7,"cache_creation_input_token_cost":6.25e-6,"cache_creation_input_token_cost_above_1hr":0.00001},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"databricks/databricks-claude-opus-4-5","object":"model","created":1769507058,"owned_by":"databricks","model_name":"databricks-claude-opus-4-5","context_length":200000,"max_input_tokens":200000,"max_output_tokens":64000,"quantization":null,"retirement_date":null,"description":"Claude Opus 4.5 is a large language model built and trained by Anthropic for production software engineering and sophisticated multi-tool agents. It supports text and image input with a 200K token context window. The model is designed for professional tasks requiring complex reasoning across multiple systems, including code generation, document creation, spreadsheets, presentations, and multi-step agent workflows. It features advanced tool use capabilities including tool search and programmatic tool calling for agents working with large tool libraries. This endpoint is hosted by Databricks.","source":"https://www.databricks.com/product/pricing/proprietary-foundation-model-serving","capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"supports_output_config":true},"pricing":{"input_cost_per_token":5e-6,"output_cost_per_token":0.000025,"input_dbu_cost_per_token":0.000071429,"output_dbu_cost_per_token":0.00035714,"cache_read_input_token_cost":5e-7,"cache_creation_input_token_cost":6.25e-6,"cache_creation_input_token_cost_above_1hr":0.00001},"list_pricing":{"input_cost_per_token":5e-6,"output_cost_per_token":0.000025,"input_dbu_cost_per_token":0.000071429,"output_dbu_cost_per_token":0.00035714,"cache_read_input_token_cost":5e-7,"cache_creation_input_token_cost":6.25e-6,"cache_creation_input_token_cost_above_1hr":0.00001},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"anthropic/claude-opus-4-5","object":"model","created":1764010580,"owned_by":"anthropic","model_name":"claude-opus-4-5","context_length":200000,"max_input_tokens":200000,"max_output_tokens":64000,"quantization":null,"retirement_date":null,"description":"Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and...","source":null,"capabilities":{"input_modalities":["file","image","text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"supports_output_config":true},"pricing":{"input_cost_per_token":5e-6,"output_cost_per_token":0.000025,"cache_read_input_token_cost":5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.25e-6,"cache_creation_input_token_cost_above_1hr":0.00001},"list_pricing":{"input_cost_per_token":5e-6,"output_cost_per_token":0.000025,"cache_read_input_token_cost":5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.25e-6,"cache_creation_input_token_cost_above_1hr":0.00001},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null},{"id":"vertex/claude-opus-4-5@eu","object":"model","created":1764010580,"owned_by":"vertex","model_name":"claude-opus-4-5","context_length":200000,"max_input_tokens":200000,"max_output_tokens":64000,"quantization":null,"retirement_date":null,"description":"Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use.","source":null,"capabilities":{"input_modalities":["file","image","text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5.500000000000001e-6,"output_cost_per_token":0.000027500000000000004,"cache_read_input_token_cost":5.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.875000000000001e-6,"cache_creation_input_token_cost_above_1hr":0.000011000000000000001},"list_pricing":{"input_cost_per_token":5.500000000000001e-6,"output_cost_per_token":0.000027500000000000004,"cache_read_input_token_cost":5.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.875000000000001e-6,"cache_creation_input_token_cost_above_1hr":0.000011000000000000001},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"vertex/claude-opus-4-5","object":"model","created":1764010580,"owned_by":"vertex","model_name":"claude-opus-4-5","context_length":200000,"max_input_tokens":200000,"max_output_tokens":64000,"quantization":null,"retirement_date":null,"description":"Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use.","source":null,"capabilities":{"input_modalities":["file","image","text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-6,"output_cost_per_token":0.000025,"cache_read_input_token_cost":5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.25e-6,"cache_creation_input_token_cost_above_1hr":0.00001},"list_pricing":{"input_cost_per_token":5e-6,"output_cost_per_token":0.000025,"cache_read_input_token_cost":5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.25e-6,"cache_creation_input_token_cost_above_1hr":0.00001},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"vertex/claude-opus-4-5@us","object":"model","created":1764010580,"owned_by":"vertex","model_name":"claude-opus-4-5","context_length":200000,"max_input_tokens":200000,"max_output_tokens":64000,"quantization":null,"retirement_date":null,"description":"Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use.","source":null,"capabilities":{"input_modalities":["file","image","text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5.500000000000001e-6,"output_cost_per_token":0.000027500000000000004,"cache_read_input_token_cost":5.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.875000000000001e-6,"cache_creation_input_token_cost_above_1hr":0.000011000000000000001},"list_pricing":{"input_cost_per_token":5.500000000000001e-6,"output_cost_per_token":0.000027500000000000004,"cache_read_input_token_cost":5.5e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":6.875000000000001e-6,"cache_creation_input_token_cost_above_1hr":0.000011000000000000001},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":6},{"id":"claude-sonnet-4.5","object":"model","created":1769507058,"owned_by":"anthropic","mode":"chat","context_length":1000000,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"input_dbu_cost_per_token":0.000042857,"output_dbu_cost_per_token":0.00021429,"cache_read_input_token_cost":3e-7,"cache_creation_input_token_cost":3.75e-6,"cache_creation_input_token_cost_above_1hr":6e-6},"pricing_endpoint":"databricks/databricks-claude-sonnet-4-5","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"databricks/databricks-claude-sonnet-4-5@eu","object":"model","created":1769507058,"owned_by":"databricks","model_name":"databricks-claude-sonnet-4-5","context_length":200000,"max_input_tokens":200000,"max_output_tokens":64000,"quantization":null,"retirement_date":null,"description":"Claude Sonnet 4.5 is Anthropic's most advanced hybrid reasoning model. It offers two modes: near-instant responses and extended thinking for deeper reasoning based on the complexity of the task. Claude Sonnet 4.5 specializes in application that require a balance of practical throughput and advanced thinking such as customer-facing agents, production coding workflows, and content generation at scale. This endpoint is hosted by Databricks","source":"https://www.databricks.com/product/pricing/proprietary-foundation-model-serving","capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"input_dbu_cost_per_token":0.000042857,"output_dbu_cost_per_token":0.00021429,"cache_read_input_token_cost":3e-7,"cache_creation_input_token_cost":3.75e-6,"cache_creation_input_token_cost_above_1hr":6e-6},"list_pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"input_dbu_cost_per_token":0.000042857,"output_dbu_cost_per_token":0.00021429,"cache_read_input_token_cost":3e-7,"cache_creation_input_token_cost":3.75e-6,"cache_creation_input_token_cost_above_1hr":6e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"databricks/databricks-claude-sonnet-4-5","object":"model","created":1769507058,"owned_by":"databricks","model_name":"databricks-claude-sonnet-4-5","context_length":200000,"max_input_tokens":200000,"max_output_tokens":64000,"quantization":null,"retirement_date":null,"description":"Claude Sonnet 4.5 is Anthropic's most advanced hybrid reasoning model. It offers two modes: near-instant responses and extended thinking for deeper reasoning based on the complexity of the task. Claude Sonnet 4.5 specializes in application that require a balance of practical throughput and advanced thinking such as customer-facing agents, production coding workflows, and content generation at scale. This endpoint is hosted by Databricks","source":"https://www.databricks.com/product/pricing/proprietary-foundation-model-serving","capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"input_dbu_cost_per_token":0.000042857,"output_dbu_cost_per_token":0.00021429,"cache_read_input_token_cost":3e-7,"cache_creation_input_token_cost":3.75e-6,"cache_creation_input_token_cost_above_1hr":6e-6},"list_pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"input_dbu_cost_per_token":0.000042857,"output_dbu_cost_per_token":0.00021429,"cache_read_input_token_cost":3e-7,"cache_creation_input_token_cost":3.75e-6,"cache_creation_input_token_cost_above_1hr":6e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"vertex/claude-sonnet-4-5@eu","object":"model","created":1759161676,"owned_by":"vertex","model_name":"claude-sonnet-4-5","context_length":1000000,"max_input_tokens":200000,"max_output_tokens":64000,"quantization":null,"retirement_date":null,"description":"Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.3e-6,"output_cost_per_token":0.0000165,"cache_read_input_token_cost":3.3e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":4.125e-6,"input_cost_per_token_above_200k_tokens":6.6e-6,"output_cost_per_token_above_200k_tokens":0.000024750000000000002,"cache_creation_input_token_cost_above_1hr":6.6e-6,"cache_read_input_token_cost_above_200k_tokens":6.6e-7,"cache_creation_input_token_cost_above_200k_tokens":8.25e-6,"cache_creation_input_token_cost_above_1hr_above_200k_tokens":0.0000132},"list_pricing":{"input_cost_per_token":3.3e-6,"output_cost_per_token":0.0000165,"cache_read_input_token_cost":3.3e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":4.125e-6,"input_cost_per_token_above_200k_tokens":6.6e-6,"output_cost_per_token_above_200k_tokens":0.000024750000000000002,"cache_creation_input_token_cost_above_1hr":6.6e-6,"cache_read_input_token_cost_above_200k_tokens":6.6e-7,"cache_creation_input_token_cost_above_200k_tokens":8.25e-6,"cache_creation_input_token_cost_above_1hr_above_200k_tokens":0.0000132},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"vertex/claude-sonnet-4-5","object":"model","created":1759161676,"owned_by":"vertex","model_name":"claude-sonnet-4-5","context_length":1000000,"max_input_tokens":200000,"max_output_tokens":64000,"quantization":null,"retirement_date":null,"description":"Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"cache_read_input_token_cost":3e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":3.75e-6,"input_cost_per_token_above_200k_tokens":6e-6,"output_cost_per_token_above_200k_tokens":0.0000225,"cache_creation_input_token_cost_above_1hr":6e-6,"cache_read_input_token_cost_above_200k_tokens":6e-7,"cache_creation_input_token_cost_above_200k_tokens":7.5e-6,"cache_creation_input_token_cost_above_1hr_above_200k_tokens":0.000012},"list_pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"cache_read_input_token_cost":3e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":3.75e-6,"input_cost_per_token_above_200k_tokens":6e-6,"output_cost_per_token_above_200k_tokens":0.0000225,"cache_creation_input_token_cost_above_1hr":6e-6,"cache_read_input_token_cost_above_200k_tokens":6e-7,"cache_creation_input_token_cost_above_200k_tokens":7.5e-6,"cache_creation_input_token_cost_above_1hr_above_200k_tokens":0.000012},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"vertex/claude-sonnet-4-5@us","object":"model","created":1759161676,"owned_by":"vertex","model_name":"claude-sonnet-4-5","context_length":1000000,"max_input_tokens":200000,"max_output_tokens":64000,"quantization":null,"retirement_date":null,"description":"Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.3e-6,"output_cost_per_token":0.0000165,"cache_read_input_token_cost":3.3e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":4.125e-6,"input_cost_per_token_above_200k_tokens":6.6e-6,"output_cost_per_token_above_200k_tokens":0.000024750000000000002,"cache_creation_input_token_cost_above_1hr":6.6e-6,"cache_read_input_token_cost_above_200k_tokens":6.6e-7,"cache_creation_input_token_cost_above_200k_tokens":8.25e-6,"cache_creation_input_token_cost_above_1hr_above_200k_tokens":0.0000132},"list_pricing":{"input_cost_per_token":3.3e-6,"output_cost_per_token":0.0000165,"cache_read_input_token_cost":3.3e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":4.125e-6,"input_cost_per_token_above_200k_tokens":6.6e-6,"output_cost_per_token_above_200k_tokens":0.000024750000000000002,"cache_creation_input_token_cost_above_1hr":6.6e-6,"cache_read_input_token_cost_above_200k_tokens":6.6e-7,"cache_creation_input_token_cost_above_200k_tokens":8.25e-6,"cache_creation_input_token_cost_above_1hr_above_200k_tokens":0.0000132},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":5},{"id":"gemma-3-12b-it","object":"model","created":1769507058,"owned_by":"google","mode":"chat","context_length":131072,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5.0000000000000004e-8,"output_cost_per_token":1.5e-7},"pricing_endpoint":"deepinfra/google/gemma-3-12b-it","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"databricks/databricks-gemma-3-12b@eu","object":"model","created":1769507058,"owned_by":"databricks","model_name":"databricks-gemma-3-12b","context_length":128000,"max_input_tokens":128000,"max_output_tokens":32000,"quantization":null,"retirement_date":null,"description":"Gemma 3 12B is a state-of-the-art multimodal language model built and trained by Google. The model supports a context length of 128K tokens and can analyze images and text. With support for over 140 languages and optimized for dialogue use cases, Gemma 3 12B is aligned with human preferences for helpfulness and safety. This endpoint is hosted by Databricks.","source":"https://www.databricks.com/product/pricing/foundation-model-serving","capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":5e-7,"input_dbu_cost_per_token":2.1429999999999996e-6,"output_dbu_cost_per_token":7.143e-6,"cache_read_input_token_cost":1.5e-8,"cache_creation_input_token_cost":1.5e-7},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":5e-7,"input_dbu_cost_per_token":2.1429999999999996e-6,"output_dbu_cost_per_token":7.143e-6,"cache_read_input_token_cost":1.5e-8,"cache_creation_input_token_cost":1.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"databricks/databricks-gemma-3-12b","object":"model","created":1769507058,"owned_by":"databricks","model_name":"databricks-gemma-3-12b","context_length":128000,"max_input_tokens":128000,"max_output_tokens":32000,"quantization":null,"retirement_date":null,"description":"Gemma 3 12B is a state-of-the-art multimodal language model built and trained by Google. The model supports a context length of 128K tokens and can analyze images and text. With support for over 140 languages and optimized for dialogue use cases, Gemma 3 12B is aligned with human preferences for helpfulness and safety. This endpoint is hosted by Databricks.","source":"https://www.databricks.com/product/pricing/foundation-model-serving","capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":5e-7,"input_dbu_cost_per_token":2.1429999999999996e-6,"output_dbu_cost_per_token":7.143e-6,"cache_read_input_token_cost":1.5e-8,"cache_creation_input_token_cost":1.5e-7},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":5e-7,"input_dbu_cost_per_token":2.1429999999999996e-6,"output_dbu_cost_per_token":7.143e-6,"cache_read_input_token_cost":1.5e-8,"cache_creation_input_token_cost":1.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"amazon/google.gemma-3-12b-it","object":"model","created":1767692616,"owned_by":"amazon","model_name":"google.gemma-3-12b-it","context_length":128000,"max_input_tokens":128000,"max_output_tokens":8000,"quantization":null,"retirement_date":null,"description":"Gemma 3 introduces multimodality, supporting vision-language input and text outputs.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":9e-8,"output_cost_per_token":2.9e-7,"input_cost_per_token_flex":5e-8,"output_cost_per_token_flex":1.5e-7,"input_cost_per_token_priority":1.6e-7,"output_cost_per_token_priority":5.1e-7},"list_pricing":{"input_cost_per_token":9e-8,"output_cost_per_token":2.9e-7,"input_cost_per_token_flex":5e-8,"output_cost_per_token_flex":1.5e-7,"input_cost_per_token_priority":1.6e-7,"output_cost_per_token_priority":5.1e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/google.gemma-3-12b-it@us","object":"model","created":1767692616,"owned_by":"amazon","model_name":"google.gemma-3-12b-it","context_length":128000,"max_input_tokens":128000,"max_output_tokens":8000,"quantization":null,"retirement_date":null,"description":"Gemma 3 introduces multimodality, supporting vision-language input and text outputs.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":9e-8,"output_cost_per_token":2.9e-7,"input_cost_per_token_flex":5e-8,"output_cost_per_token_flex":1.5e-7,"input_cost_per_token_priority":1.6e-7,"output_cost_per_token_priority":5.1e-7},"list_pricing":{"input_cost_per_token":9e-8,"output_cost_per_token":2.9e-7,"input_cost_per_token_flex":5e-8,"output_cost_per_token_flex":1.5e-7,"input_cost_per_token_priority":1.6e-7,"output_cost_per_token_priority":5.1e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"deepinfra/google/gemma-3-12b-it","object":"model","created":1741902625,"owned_by":"deepinfra","model_name":"google/gemma-3-12b-it","context_length":131072,"max_input_tokens":131072,"max_output_tokens":16384,"quantization":"bf16","retirement_date":null,"description":"Gemma 3 introduces multimodality, supporting vision-language input and text outputs.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5.0000000000000004e-8,"output_cost_per_token":1.5e-7},"list_pricing":{"input_cost_per_token":5.0000000000000004e-8,"output_cost_per_token":1.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":5},{"id":"llama-4-maverick","object":"model","created":1769507058,"owned_by":"meta","mode":"chat","context_length":128000,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":1.5e-6,"input_dbu_cost_per_token":7.143e-6,"output_dbu_cost_per_token":0.000021429,"cache_read_input_token_cost":5e-8,"cache_creation_input_token_cost":5e-7},"pricing_endpoint":"databricks/databricks-llama-4-maverick","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"databricks/databricks-llama-4-maverick@eu","object":"model","created":1769507058,"owned_by":"databricks","model_name":"databricks-llama-4-maverick","context_length":128000,"max_input_tokens":128000,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"Llama 4 Maverick is a state-of-the-art mixture of experts (MoE) language model trained and released by Meta. The model has 17B active parameters, 128 experts, and 400 billion total parameters. The model supports a context length of 128K tokens. The model is optimized for multilingual dialogue use cases, supporting 12 languages, and is aligned with human preferences for helpfulness and safety. It is not intended for use in languages other than English. Llama 4 is licensed under the Meta Llama 4 Community License, Copyright © Meta Platforms, Inc. All Rights Reserved. Customers are responsible for ensuring compliance with applicable model licenses.","source":"https://www.databricks.com/product/pricing/foundation-model-serving","capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":1.5e-6,"input_dbu_cost_per_token":7.143e-6,"output_dbu_cost_per_token":0.000021429,"cache_read_input_token_cost":5e-8,"cache_creation_input_token_cost":5e-7},"list_pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":1.5e-6,"input_dbu_cost_per_token":7.143e-6,"output_dbu_cost_per_token":0.000021429,"cache_read_input_token_cost":5e-8,"cache_creation_input_token_cost":5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"databricks/databricks-llama-4-maverick","object":"model","created":1769507058,"owned_by":"databricks","model_name":"databricks-llama-4-maverick","context_length":128000,"max_input_tokens":128000,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"Llama 4 Maverick is a state-of-the-art mixture of experts (MoE) language model trained and released by Meta. The model has 17B active parameters, 128 experts, and 400 billion total parameters. The model supports a context length of 128K tokens. The model is optimized for multilingual dialogue use cases, supporting 12 languages, and is aligned with human preferences for helpfulness and safety. It is not intended for use in languages other than English. Llama 4 is licensed under the Meta Llama 4 Community License, Copyright © Meta Platforms, Inc. All Rights Reserved. Customers are responsible for ensuring compliance with applicable model licenses.","source":"https://www.databricks.com/product/pricing/foundation-model-serving","capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":1.5e-6,"input_dbu_cost_per_token":7.143e-6,"output_dbu_cost_per_token":0.000021429,"cache_read_input_token_cost":5e-8,"cache_creation_input_token_cost":5e-7},"list_pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":1.5e-6,"input_dbu_cost_per_token":7.143e-6,"output_dbu_cost_per_token":0.000021429,"cache_read_input_token_cost":5e-8,"cache_creation_input_token_cost":5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":2},{"id":"qwen2.5-vl-72b-instruct","object":"model","created":1769507058,"owned_by":"qwen","mode":"chat","context_length":32768,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.01e-6,"output_cost_per_token":1.01e-6},"pricing_endpoint":"ovhcloud/Qwen2.5-VL-72B-Instruct","regions":[{"code":"eu","name":"Europe"}],"alias_of":null,"endpoints":[{"id":"ovhcloud/Qwen2.5-VL-72B-Instruct","object":"model","created":1769507058,"owned_by":"ovhcloud","model_name":"Qwen2.5-VL-72B-Instruct","context_length":32768,"max_input_tokens":32000,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"Qwen2.5-VL is proficient in recognizing common objects such as flowers, birds, fish, and insects. It is also highly capable of analyzing texts, charts, icons, graphics, and layouts within images.","source":"https://endpoints.ai.cloud.ovh.net/models/qwen2-5-vl-72b-instruct","capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.01e-6,"output_cost_per_token":1.01e-6},"list_pricing":{"input_cost_per_token":1.01e-6,"output_cost_per_token":1.01e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"claude-3-7-sonnet-latest","object":"model","created":1767692616,"owned_by":"anthropic","mode":"chat","context_length":200000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.3e-6,"output_cost_per_token":0.0000165,"cache_read_input_token_cost":3.3e-7},"pricing_endpoint":"deepinfra/anthropic/claude-3-7-sonnet-latest","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"deepinfra/anthropic/claude-3-7-sonnet-latest","object":"model","created":1767692616,"owned_by":"deepinfra","model_name":"anthropic/claude-3-7-sonnet-latest","context_length":200000,"max_input_tokens":200000,"max_output_tokens":200000,"quantization":null,"retirement_date":null,"description":"","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.3e-6,"output_cost_per_token":0.0000165,"cache_read_input_token_cost":3.3e-7},"list_pricing":{"input_cost_per_token":3.3e-6,"output_cost_per_token":0.0000165,"cache_read_input_token_cost":3.3e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":1},{"id":"claude-4-opus","object":"model","created":1767692616,"owned_by":"anthropic","mode":"chat","context_length":200000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":0.0000165,"output_cost_per_token":0.0000825},"pricing_endpoint":"deepinfra/anthropic/claude-4-opus","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"deepinfra/anthropic/claude-4-opus","object":"model","created":1767692616,"owned_by":"deepinfra","model_name":"anthropic/claude-4-opus","context_length":200000,"max_input_tokens":200000,"max_output_tokens":200000,"quantization":null,"retirement_date":null,"description":"","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":0.0000165,"output_cost_per_token":0.0000825},"list_pricing":{"input_cost_per_token":0.0000165,"output_cost_per_token":0.0000825},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":1},{"id":"claude-4-sonnet","object":"model","created":1767692616,"owned_by":"anthropic","mode":"chat","context_length":200000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.3e-6,"output_cost_per_token":0.0000165},"pricing_endpoint":"deepinfra/anthropic/claude-4-sonnet","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"deepinfra/anthropic/claude-4-sonnet","object":"model","created":1767692616,"owned_by":"deepinfra","model_name":"anthropic/claude-4-sonnet","context_length":200000,"max_input_tokens":200000,"max_output_tokens":200000,"quantization":null,"retirement_date":null,"description":"","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.3e-6,"output_cost_per_token":0.0000165},"list_pricing":{"input_cost_per_token":3.3e-6,"output_cost_per_token":0.0000165},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":1},{"id":"deepseek-chat","object":"model","created":1767692616,"owned_by":"deepseek","mode":"chat","context_length":131072,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":3e-9,"input_cost_per_token_cache_hit":2.8e-8,"cache_creation_input_token_cost":0.0},"pricing_endpoint":"deepseek/deepseek-chat","regions":[{"code":"ap","name":"Asia"}],"alias_of":null,"endpoints":[{"id":"deepseek/deepseek-chat","object":"model","created":1767692616,"owned_by":"deepseek","model_name":"deepseek-chat","context_length":131072,"max_input_tokens":131072,"max_output_tokens":8192,"quantization":null,"retirement_date":null,"description":"DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions.","source":"https://api-docs.deepseek.com/quick_start/pricing","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":3e-9,"input_cost_per_token_cache_hit":2.8e-8,"cache_creation_input_token_cost":0.0},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":3e-9,"input_cost_per_token_cache_hit":2.8e-8,"cache_creation_input_token_cost":0.0},"discount":null,"discount_ends_at":null,"regions":[{"code":"ap","name":"Asia"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":1},{"id":"deepseek-r1-0528-turbo","object":"model","created":1767692616,"owned_by":"deepseek","mode":"chat","context_length":32768,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":3e-6},"pricing_endpoint":"deepinfra/deepseek-ai/DeepSeek-R1-0528-Turbo","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"deepinfra/deepseek-ai/DeepSeek-R1-0528-Turbo","object":"model","created":1767692616,"owned_by":"deepinfra","model_name":"deepseek-ai/DeepSeek-R1-0528-Turbo","context_length":32768,"max_input_tokens":32768,"max_output_tokens":32768,"quantization":null,"retirement_date":null,"description":"","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":3e-6},"list_pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":3e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"deepseek-reasoner","object":"model","created":1767692616,"owned_by":"deepseek","mode":"chat","context_length":131072,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":false,"supports_native_streaming":true,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":3e-9,"input_cost_per_token_cache_hit":2.8e-8},"pricing_endpoint":"deepseek/deepseek-reasoner","regions":[{"code":"ap","name":"Asia"}],"alias_of":null,"endpoints":[{"id":"deepseek/deepseek-reasoner","object":"model","created":1767692616,"owned_by":"deepseek","model_name":"deepseek-reasoner","context_length":131072,"max_input_tokens":131072,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":null,"source":"https://api-docs.deepseek.com/quick_start/pricing","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":false,"supports_native_streaming":true,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":3e-9,"input_cost_per_token_cache_hit":2.8e-8},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":3e-9,"input_cost_per_token_cache_hit":2.8e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"ap","name":"Asia"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":1},{"id":"deepseek-v3-0324","object":"model","created":1767692616,"owned_by":"deepseek","mode":"chat","context_length":163840,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.4000000000000003e-7,"output_cost_per_token":9.000000000000001e-7,"cache_read_input_token_cost":1.35e-7},"pricing_endpoint":"deepinfra/deepseek-ai/DeepSeek-V3-0324","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"deepinfra/deepseek-ai/DeepSeek-V3-0324","object":"model","created":1767692616,"owned_by":"deepinfra","model_name":"deepseek-ai/DeepSeek-V3-0324","context_length":163840,"max_input_tokens":null,"max_output_tokens":163840,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.4000000000000003e-7,"output_cost_per_token":9.000000000000001e-7,"cache_read_input_token_cost":1.35e-7},"list_pricing":{"input_cost_per_token":2.4000000000000003e-7,"output_cost_per_token":9.000000000000001e-7,"cache_read_input_token_cost":1.35e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"deepseek-v3.1","object":"model","created":1767692616,"owned_by":"deepseek","mode":"chat","context_length":163840,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.5e-7,"output_cost_per_token":9.499999999999999e-7,"cache_read_input_token_cost":1.3e-7},"pricing_endpoint":"deepinfra/deepseek-ai/DeepSeek-V3.1","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"deepinfra/deepseek-ai/DeepSeek-V3.1","object":"model","created":1767692616,"owned_by":"deepinfra","model_name":"deepseek-ai/DeepSeek-V3.1","context_length":163840,"max_input_tokens":163840,"max_output_tokens":null,"quantization":"fp4","retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.5e-7,"output_cost_per_token":9.499999999999999e-7,"cache_read_input_token_cost":1.3e-7},"list_pricing":{"input_cost_per_token":2.5e-7,"output_cost_per_token":9.499999999999999e-7,"cache_read_input_token_cost":1.3e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"gemini-2.5-flash","object":"model","created":1767692616,"owned_by":"google","mode":"chat","context_length":1048576,"capabilities":{"input_modalities":["text","image","audio","file","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":2.5e-6,"input_cost_per_token_flex":1.5e-7,"input_cost_per_audio_token":1e-6,"input_cost_per_image_token":3e-7,"output_cost_per_token_flex":1.25e-6,"cache_read_input_token_cost":3e-8,"input_cost_per_token_priority":5.4e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":4.5e-6,"cache_creation_input_token_cost":8.33333333333333e-8,"input_cost_per_audio_token_flex":5e-7,"output_cost_per_reasoning_token":2.5e-6,"cache_read_input_token_cost_flex":3e-8,"cache_read_input_audio_token_cost":1e-7,"input_cost_per_audio_token_priority":1.8e-6,"cache_read_input_token_cost_priority":5.4e-8,"google_maps_grounding_cost_per_query":0.025,"cache_read_input_audio_token_cost_flex":1e-7,"cache_read_input_audio_token_cost_priority":1.8e-7},"pricing_endpoint":"google/gemini-2.5-flash","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"deepinfra/google/gemini-2.5-flash","object":"model","created":1767692616,"owned_by":"deepinfra","model_name":"google/gemini-2.5-flash","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks.","source":null,"capabilities":{"input_modalities":["text","image","audio"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":2.5e-6},"list_pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":2.5e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null},{"id":"google/gemini-2.5-flash","object":"model","created":1750172488,"owned_by":"google","model_name":"gemini-2.5-flash","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"quantization":null,"retirement_date":"2026-10-20","description":"Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks.","source":"https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview","capabilities":{"input_modalities":["file","image","text","audio","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":2.5e-6,"input_cost_per_token_flex":1.5e-7,"input_cost_per_audio_token":1e-6,"input_cost_per_image_token":3e-7,"output_cost_per_token_flex":1.25e-6,"cache_read_input_token_cost":3e-8,"input_cost_per_token_priority":5.4e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":4.5e-6,"cache_creation_input_token_cost":8.33333333333333e-8,"input_cost_per_audio_token_flex":5e-7,"output_cost_per_reasoning_token":2.5e-6,"cache_read_input_token_cost_flex":3e-8,"cache_read_input_audio_token_cost":1e-7,"input_cost_per_audio_token_priority":1.8e-6,"cache_read_input_token_cost_priority":5.4e-8,"google_maps_grounding_cost_per_query":0.025,"cache_read_input_audio_token_cost_flex":1e-7,"cache_read_input_audio_token_cost_priority":1.8e-7},"list_pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":2.5e-6,"input_cost_per_token_flex":1.5e-7,"input_cost_per_audio_token":1e-6,"input_cost_per_image_token":3e-7,"output_cost_per_token_flex":1.25e-6,"cache_read_input_token_cost":3e-8,"input_cost_per_token_priority":5.4e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":4.5e-6,"cache_creation_input_token_cost":8.33333333333333e-8,"input_cost_per_audio_token_flex":5e-7,"output_cost_per_reasoning_token":2.5e-6,"cache_read_input_token_cost_flex":3e-8,"cache_read_input_audio_token_cost":1e-7,"input_cost_per_audio_token_priority":1.8e-6,"cache_read_input_token_cost_priority":5.4e-8,"google_maps_grounding_cost_per_query":0.025,"cache_read_input_audio_token_cost_flex":1e-7,"cache_read_input_audio_token_cost_priority":1.8e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"vertex/gemini-2.5-flash@eu","object":"model","created":1750172488,"owned_by":"vertex","model_name":"gemini-2.5-flash","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"quantization":null,"retirement_date":"2026-10-20","description":"Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks.","source":null,"capabilities":{"input_modalities":["file","image","text","audio","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":2.5e-6,"input_cost_per_token_flex":1.5e-7,"input_cost_per_audio_token":1e-6,"output_cost_per_token_flex":1.25e-6,"cache_read_input_token_cost":3e-8,"input_cost_per_token_priority":5.4e-7,"search_context_cost_per_query":{"search_context_size_low":0.035,"search_context_size_high":0.035,"search_context_size_medium":0.035},"output_cost_per_token_priority":4.5e-6,"input_cost_per_audio_token_flex":5e-7,"output_cost_per_reasoning_token":2.5e-6,"cache_read_input_token_cost_flex":3e-8,"cache_read_input_audio_token_cost":1e-7,"input_cost_per_audio_token_priority":1.8e-6,"cache_read_input_token_cost_priority":5.4e-8,"google_maps_grounding_cost_per_query":0.025,"cache_read_input_audio_token_cost_priority":1.8e-7,"input_cost_per_audio_token_above_200k_tokens":3e-7,"input_cost_per_audio_token_above_200k_tokens_flex":5e-7,"input_cost_per_audio_token_above_200k_tokens_priority":1.8e-6},"list_pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":2.5e-6,"input_cost_per_token_flex":1.5e-7,"input_cost_per_audio_token":1e-6,"output_cost_per_token_flex":1.25e-6,"cache_read_input_token_cost":3e-8,"input_cost_per_token_priority":5.4e-7,"search_context_cost_per_query":{"search_context_size_low":0.035,"search_context_size_high":0.035,"search_context_size_medium":0.035},"output_cost_per_token_priority":4.5e-6,"input_cost_per_audio_token_flex":5e-7,"output_cost_per_reasoning_token":2.5e-6,"cache_read_input_token_cost_flex":3e-8,"cache_read_input_audio_token_cost":1e-7,"input_cost_per_audio_token_priority":1.8e-6,"cache_read_input_token_cost_priority":5.4e-8,"google_maps_grounding_cost_per_query":0.025,"cache_read_input_audio_token_cost_priority":1.8e-7,"input_cost_per_audio_token_above_200k_tokens":3e-7,"input_cost_per_audio_token_above_200k_tokens_flex":5e-7,"input_cost_per_audio_token_above_200k_tokens_priority":1.8e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"vertex/gemini-2.5-flash","object":"model","created":1750172488,"owned_by":"vertex","model_name":"gemini-2.5-flash","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"quantization":null,"retirement_date":"2026-10-20","description":"Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks.","source":null,"capabilities":{"input_modalities":["file","image","text","audio","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":2.5e-6,"input_cost_per_token_flex":1.5e-7,"input_cost_per_audio_token":1e-6,"output_cost_per_token_flex":1.25e-6,"cache_read_input_token_cost":3e-8,"input_cost_per_token_priority":5.4e-7,"search_context_cost_per_query":{"search_context_size_low":0.035,"search_context_size_high":0.035,"search_context_size_medium":0.035},"output_cost_per_token_priority":4.5e-6,"input_cost_per_audio_token_flex":5e-7,"output_cost_per_reasoning_token":2.5e-6,"cache_read_input_token_cost_flex":3e-8,"cache_read_input_audio_token_cost":1e-7,"input_cost_per_audio_token_priority":1.8e-6,"cache_read_input_token_cost_priority":5.4e-8,"google_maps_grounding_cost_per_query":0.025,"cache_read_input_audio_token_cost_priority":1.8e-7,"input_cost_per_audio_token_above_200k_tokens":3e-7,"input_cost_per_audio_token_above_200k_tokens_flex":5e-7,"input_cost_per_audio_token_above_200k_tokens_priority":1.8e-6},"list_pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":2.5e-6,"input_cost_per_token_flex":1.5e-7,"input_cost_per_audio_token":1e-6,"output_cost_per_token_flex":1.25e-6,"cache_read_input_token_cost":3e-8,"input_cost_per_token_priority":5.4e-7,"search_context_cost_per_query":{"search_context_size_low":0.035,"search_context_size_high":0.035,"search_context_size_medium":0.035},"output_cost_per_token_priority":4.5e-6,"input_cost_per_audio_token_flex":5e-7,"output_cost_per_reasoning_token":2.5e-6,"cache_read_input_token_cost_flex":3e-8,"cache_read_input_audio_token_cost":1e-7,"input_cost_per_audio_token_priority":1.8e-6,"cache_read_input_token_cost_priority":5.4e-8,"google_maps_grounding_cost_per_query":0.025,"cache_read_input_audio_token_cost_priority":1.8e-7,"input_cost_per_audio_token_above_200k_tokens":3e-7,"input_cost_per_audio_token_above_200k_tokens_flex":5e-7,"input_cost_per_audio_token_above_200k_tokens_priority":1.8e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"vertex/gemini-2.5-flash@us","object":"model","created":1750172488,"owned_by":"vertex","model_name":"gemini-2.5-flash","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"quantization":null,"retirement_date":"2026-10-20","description":"Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks.","source":null,"capabilities":{"input_modalities":["file","image","text","audio","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":2.5e-6,"input_cost_per_token_flex":1.5e-7,"input_cost_per_audio_token":1e-6,"output_cost_per_token_flex":1.25e-6,"cache_read_input_token_cost":3e-8,"input_cost_per_token_priority":5.4e-7,"search_context_cost_per_query":{"search_context_size_low":0.035,"search_context_size_high":0.035,"search_context_size_medium":0.035},"output_cost_per_token_priority":4.5e-6,"input_cost_per_audio_token_flex":5e-7,"output_cost_per_reasoning_token":2.5e-6,"cache_read_input_token_cost_flex":3e-8,"cache_read_input_audio_token_cost":1e-7,"input_cost_per_audio_token_priority":1.8e-6,"cache_read_input_token_cost_priority":5.4e-8,"google_maps_grounding_cost_per_query":0.025,"cache_read_input_audio_token_cost_priority":1.8e-7,"input_cost_per_audio_token_above_200k_tokens":3e-7,"input_cost_per_audio_token_above_200k_tokens_flex":5e-7,"input_cost_per_audio_token_above_200k_tokens_priority":1.8e-6},"list_pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":2.5e-6,"input_cost_per_token_flex":1.5e-7,"input_cost_per_audio_token":1e-6,"output_cost_per_token_flex":1.25e-6,"cache_read_input_token_cost":3e-8,"input_cost_per_token_priority":5.4e-7,"search_context_cost_per_query":{"search_context_size_low":0.035,"search_context_size_high":0.035,"search_context_size_medium":0.035},"output_cost_per_token_priority":4.5e-6,"input_cost_per_audio_token_flex":5e-7,"output_cost_per_reasoning_token":2.5e-6,"cache_read_input_token_cost_flex":3e-8,"cache_read_input_audio_token_cost":1e-7,"input_cost_per_audio_token_priority":1.8e-6,"cache_read_input_token_cost_priority":5.4e-8,"google_maps_grounding_cost_per_query":0.025,"cache_read_input_audio_token_cost_priority":1.8e-7,"input_cost_per_audio_token_above_200k_tokens":3e-7,"input_cost_per_audio_token_above_200k_tokens_flex":5e-7,"input_cost_per_audio_token_above_200k_tokens_priority":1.8e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":5},{"id":"gemini-2.5-pro","object":"model","created":1767692616,"owned_by":"google","mode":"chat","context_length":1048576,"capabilities":{"input_modalities":["text","image","audio","file","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":0.00001,"input_cost_per_token_flex":6.25e-7,"input_cost_per_audio_token":1.25e-6,"input_cost_per_image_token":1.25e-6,"output_cost_per_token_flex":5e-6,"cache_read_input_token_cost":1.25e-7,"input_cost_per_token_priority":2.25e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.000018,"cache_creation_input_token_cost":3.75e-7,"output_cost_per_reasoning_token":0.00001,"cache_read_input_token_cost_flex":1.25e-7,"cache_read_input_audio_token_cost":1.25e-7,"cache_read_input_token_cost_priority":2.25e-7,"google_maps_grounding_cost_per_query":0.025,"input_cost_per_token_above_200k_tokens":2.5e-6,"output_cost_per_token_above_200k_tokens":0.000015,"input_cost_per_token_above_200k_tokens_flex":1.25e-6,"input_cost_per_audio_token_above_200k_tokens":2.5e-6,"output_cost_per_token_above_200k_tokens_flex":7.5e-6,"cache_read_input_token_cost_above_200k_tokens":2.5e-7,"input_cost_per_token_above_200k_tokens_priority":4.5e-6,"output_cost_per_token_above_200k_tokens_priority":0.000027,"cache_read_input_token_cost_above_200k_tokens_flex":2.5e-7,"cache_read_input_audio_token_cost_above_200k_tokens":2.5e-7,"cache_read_input_token_cost_above_200k_tokens_priority":4.5e-7},"pricing_endpoint":"google/gemini-2.5-pro","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"deepinfra/google/gemini-2.5-pro","object":"model","created":1767692616,"owned_by":"deepinfra","model_name":"google/gemini-2.5-pro","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks.","source":null,"capabilities":{"input_modalities":["text","image","audio"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":0.00001},"list_pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":0.00001},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null},{"id":"google/gemini-2.5-pro","object":"model","created":1750169544,"owned_by":"google","model_name":"gemini-2.5-pro","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"quantization":null,"retirement_date":"2026-10-20","description":"Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks.","source":"https://cloud.google.com/vertex-ai/generative-ai/pricing","capabilities":{"input_modalities":["text","image","file","audio","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":0.00001,"input_cost_per_token_flex":6.25e-7,"input_cost_per_audio_token":1.25e-6,"input_cost_per_image_token":1.25e-6,"output_cost_per_token_flex":5e-6,"cache_read_input_token_cost":1.25e-7,"input_cost_per_token_priority":2.25e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.000018,"cache_creation_input_token_cost":3.75e-7,"output_cost_per_reasoning_token":0.00001,"cache_read_input_token_cost_flex":1.25e-7,"cache_read_input_audio_token_cost":1.25e-7,"cache_read_input_token_cost_priority":2.25e-7,"google_maps_grounding_cost_per_query":0.025,"input_cost_per_token_above_200k_tokens":2.5e-6,"output_cost_per_token_above_200k_tokens":0.000015,"input_cost_per_token_above_200k_tokens_flex":1.25e-6,"input_cost_per_audio_token_above_200k_tokens":2.5e-6,"output_cost_per_token_above_200k_tokens_flex":7.5e-6,"cache_read_input_token_cost_above_200k_tokens":2.5e-7,"input_cost_per_token_above_200k_tokens_priority":4.5e-6,"output_cost_per_token_above_200k_tokens_priority":0.000027,"cache_read_input_token_cost_above_200k_tokens_flex":2.5e-7,"cache_read_input_audio_token_cost_above_200k_tokens":2.5e-7,"cache_read_input_token_cost_above_200k_tokens_priority":4.5e-7},"list_pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":0.00001,"input_cost_per_token_flex":6.25e-7,"input_cost_per_audio_token":1.25e-6,"input_cost_per_image_token":1.25e-6,"output_cost_per_token_flex":5e-6,"cache_read_input_token_cost":1.25e-7,"input_cost_per_token_priority":2.25e-6,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":0.000018,"cache_creation_input_token_cost":3.75e-7,"output_cost_per_reasoning_token":0.00001,"cache_read_input_token_cost_flex":1.25e-7,"cache_read_input_audio_token_cost":1.25e-7,"cache_read_input_token_cost_priority":2.25e-7,"google_maps_grounding_cost_per_query":0.025,"input_cost_per_token_above_200k_tokens":2.5e-6,"output_cost_per_token_above_200k_tokens":0.000015,"input_cost_per_token_above_200k_tokens_flex":1.25e-6,"input_cost_per_audio_token_above_200k_tokens":2.5e-6,"output_cost_per_token_above_200k_tokens_flex":7.5e-6,"cache_read_input_token_cost_above_200k_tokens":2.5e-7,"input_cost_per_token_above_200k_tokens_priority":4.5e-6,"output_cost_per_token_above_200k_tokens_priority":0.000027,"cache_read_input_token_cost_above_200k_tokens_flex":2.5e-7,"cache_read_input_audio_token_cost_above_200k_tokens":2.5e-7,"cache_read_input_token_cost_above_200k_tokens_priority":4.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"vertex/gemini-2.5-pro@eu","object":"model","created":1750169544,"owned_by":"vertex","model_name":"gemini-2.5-pro","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"quantization":null,"retirement_date":"2026-10-20","description":"Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks.","source":null,"capabilities":{"input_modalities":["text","image","file","audio","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":0.00001,"input_cost_per_token_flex":6.25e-7,"output_cost_per_token_flex":5e-6,"cache_read_input_token_cost":1.25e-7,"input_cost_per_token_priority":2.25e-6,"search_context_cost_per_query":{"search_context_size_low":0.035,"search_context_size_high":0.035,"search_context_size_medium":0.035},"output_cost_per_token_priority":0.000018,"cache_read_input_token_cost_flex":1.25e-7,"cache_read_input_token_cost_priority":2.25e-7,"google_maps_grounding_cost_per_query":0.025,"input_cost_per_token_above_200k_tokens":2.5e-6,"output_cost_per_token_above_200k_tokens":0.000015,"input_cost_per_token_above_200k_tokens_flex":1.25e-6,"output_cost_per_token_above_200k_tokens_flex":7.5e-6,"cache_read_input_token_cost_above_200k_tokens":2.5e-7,"input_cost_per_token_above_200k_tokens_priority":4.5e-6,"output_cost_per_token_above_200k_tokens_priority":0.000027,"cache_read_input_token_cost_above_200k_tokens_priority":4.5e-7},"list_pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":0.00001,"input_cost_per_token_flex":6.25e-7,"output_cost_per_token_flex":5e-6,"cache_read_input_token_cost":1.25e-7,"input_cost_per_token_priority":2.25e-6,"search_context_cost_per_query":{"search_context_size_low":0.035,"search_context_size_high":0.035,"search_context_size_medium":0.035},"output_cost_per_token_priority":0.000018,"cache_read_input_token_cost_flex":1.25e-7,"cache_read_input_token_cost_priority":2.25e-7,"google_maps_grounding_cost_per_query":0.025,"input_cost_per_token_above_200k_tokens":2.5e-6,"output_cost_per_token_above_200k_tokens":0.000015,"input_cost_per_token_above_200k_tokens_flex":1.25e-6,"output_cost_per_token_above_200k_tokens_flex":7.5e-6,"cache_read_input_token_cost_above_200k_tokens":2.5e-7,"input_cost_per_token_above_200k_tokens_priority":4.5e-6,"output_cost_per_token_above_200k_tokens_priority":0.000027,"cache_read_input_token_cost_above_200k_tokens_priority":4.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"vertex/gemini-2.5-pro","object":"model","created":1750169544,"owned_by":"vertex","model_name":"gemini-2.5-pro","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"quantization":null,"retirement_date":"2026-10-20","description":"Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks.","source":null,"capabilities":{"input_modalities":["text","image","file","audio","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":0.00001,"input_cost_per_token_flex":6.25e-7,"output_cost_per_token_flex":5e-6,"cache_read_input_token_cost":1.25e-7,"input_cost_per_token_priority":2.25e-6,"search_context_cost_per_query":{"search_context_size_low":0.035,"search_context_size_high":0.035,"search_context_size_medium":0.035},"output_cost_per_token_priority":0.000018,"cache_read_input_token_cost_flex":1.25e-7,"cache_read_input_token_cost_priority":2.25e-7,"google_maps_grounding_cost_per_query":0.025,"input_cost_per_token_above_200k_tokens":2.5e-6,"output_cost_per_token_above_200k_tokens":0.000015,"input_cost_per_token_above_200k_tokens_flex":1.25e-6,"output_cost_per_token_above_200k_tokens_flex":7.5e-6,"cache_read_input_token_cost_above_200k_tokens":2.5e-7,"input_cost_per_token_above_200k_tokens_priority":4.5e-6,"output_cost_per_token_above_200k_tokens_priority":0.000027,"cache_read_input_token_cost_above_200k_tokens_priority":4.5e-7},"list_pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":0.00001,"input_cost_per_token_flex":6.25e-7,"output_cost_per_token_flex":5e-6,"cache_read_input_token_cost":1.25e-7,"input_cost_per_token_priority":2.25e-6,"search_context_cost_per_query":{"search_context_size_low":0.035,"search_context_size_high":0.035,"search_context_size_medium":0.035},"output_cost_per_token_priority":0.000018,"cache_read_input_token_cost_flex":1.25e-7,"cache_read_input_token_cost_priority":2.25e-7,"google_maps_grounding_cost_per_query":0.025,"input_cost_per_token_above_200k_tokens":2.5e-6,"output_cost_per_token_above_200k_tokens":0.000015,"input_cost_per_token_above_200k_tokens_flex":1.25e-6,"output_cost_per_token_above_200k_tokens_flex":7.5e-6,"cache_read_input_token_cost_above_200k_tokens":2.5e-7,"input_cost_per_token_above_200k_tokens_priority":4.5e-6,"output_cost_per_token_above_200k_tokens_priority":0.000027,"cache_read_input_token_cost_above_200k_tokens_priority":4.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"vertex/gemini-2.5-pro@us","object":"model","created":1750169544,"owned_by":"vertex","model_name":"gemini-2.5-pro","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"quantization":null,"retirement_date":"2026-10-20","description":"Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks.","source":null,"capabilities":{"input_modalities":["text","image","file","audio","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":0.00001,"input_cost_per_token_flex":6.25e-7,"output_cost_per_token_flex":5e-6,"cache_read_input_token_cost":1.25e-7,"input_cost_per_token_priority":2.25e-6,"search_context_cost_per_query":{"search_context_size_low":0.035,"search_context_size_high":0.035,"search_context_size_medium":0.035},"output_cost_per_token_priority":0.000018,"cache_read_input_token_cost_flex":1.25e-7,"cache_read_input_token_cost_priority":2.25e-7,"google_maps_grounding_cost_per_query":0.025,"input_cost_per_token_above_200k_tokens":2.5e-6,"output_cost_per_token_above_200k_tokens":0.000015,"input_cost_per_token_above_200k_tokens_flex":1.25e-6,"output_cost_per_token_above_200k_tokens_flex":7.5e-6,"cache_read_input_token_cost_above_200k_tokens":2.5e-7,"input_cost_per_token_above_200k_tokens_priority":4.5e-6,"output_cost_per_token_above_200k_tokens_priority":0.000027,"cache_read_input_token_cost_above_200k_tokens_priority":4.5e-7},"list_pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":0.00001,"input_cost_per_token_flex":6.25e-7,"output_cost_per_token_flex":5e-6,"cache_read_input_token_cost":1.25e-7,"input_cost_per_token_priority":2.25e-6,"search_context_cost_per_query":{"search_context_size_low":0.035,"search_context_size_high":0.035,"search_context_size_medium":0.035},"output_cost_per_token_priority":0.000018,"cache_read_input_token_cost_flex":1.25e-7,"cache_read_input_token_cost_priority":2.25e-7,"google_maps_grounding_cost_per_query":0.025,"input_cost_per_token_above_200k_tokens":2.5e-6,"output_cost_per_token_above_200k_tokens":0.000015,"input_cost_per_token_above_200k_tokens_flex":1.25e-6,"output_cost_per_token_above_200k_tokens_flex":7.5e-6,"cache_read_input_token_cost_above_200k_tokens":2.5e-7,"input_cost_per_token_above_200k_tokens_priority":4.5e-6,"output_cost_per_token_above_200k_tokens_priority":0.000027,"cache_read_input_token_cost_above_200k_tokens_priority":4.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":5},{"id":"gemma-3-27b-it","object":"model","created":1767692616,"owned_by":"google","mode":"chat","context_length":131072,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":8e-8,"output_cost_per_token":1.6e-7},"pricing_endpoint":"deepinfra/google/gemma-3-27b-it","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"amazon/google.gemma-3-27b-it","object":"model","created":1767692616,"owned_by":"amazon","model_name":"google.gemma-3-27b-it","context_length":128000,"max_input_tokens":128000,"max_output_tokens":8000,"quantization":null,"retirement_date":null,"description":"Gemma 3 introduces multimodality, supporting vision-language input and text outputs.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.3e-7,"output_cost_per_token":3.8e-7,"input_cost_per_token_flex":1.2e-7,"output_cost_per_token_flex":1.9e-7,"input_cost_per_token_priority":4e-7,"output_cost_per_token_priority":6.7e-7},"list_pricing":{"input_cost_per_token":2.3e-7,"output_cost_per_token":3.8e-7,"input_cost_per_token_flex":1.2e-7,"output_cost_per_token_flex":1.9e-7,"input_cost_per_token_priority":4e-7,"output_cost_per_token_priority":6.7e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/google.gemma-3-27b-it@us","object":"model","created":1767692616,"owned_by":"amazon","model_name":"google.gemma-3-27b-it","context_length":128000,"max_input_tokens":128000,"max_output_tokens":8000,"quantization":null,"retirement_date":null,"description":"Gemma 3 introduces multimodality, supporting vision-language input and text outputs.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.3e-7,"output_cost_per_token":3.8e-7,"input_cost_per_token_flex":1.2e-7,"output_cost_per_token_flex":1.9e-7,"input_cost_per_token_priority":4e-7,"output_cost_per_token_priority":6.7e-7},"list_pricing":{"input_cost_per_token":2.3e-7,"output_cost_per_token":3.8e-7,"input_cost_per_token_flex":1.2e-7,"output_cost_per_token_flex":1.9e-7,"input_cost_per_token_priority":4e-7,"output_cost_per_token_priority":6.7e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"deepinfra/google/gemma-3-27b-it","object":"model","created":1741756359,"owned_by":"deepinfra","model_name":"google/gemma-3-27b-it","context_length":131072,"max_input_tokens":131072,"max_output_tokens":16384,"quantization":"fp8","retirement_date":null,"description":"Gemma 3 introduces multimodality, supporting vision-language input and text outputs.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":8e-8,"output_cost_per_token":1.6e-7},"list_pricing":{"input_cost_per_token":8e-8,"output_cost_per_token":1.6e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"nebius/google/gemma-3-27b-it","object":"model","created":1741756359,"owned_by":"nebius","model_name":"google/gemma-3-27b-it","context_length":110000,"max_input_tokens":110000,"max_output_tokens":null,"quantization":"fp8","retirement_date":null,"description":"Gemma 3 introduces multimodality, supporting vision-language input and text outputs.","source":"https://nebius.com/prices-ai-studio","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":3e-7,"cache_read_input_token_cost":1e-7},"list_pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":3e-7,"cache_read_input_token_cost":1e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"scaleway/gemma-3-27b-it","object":"model","created":1730385501,"owned_by":"scaleway","model_name":"gemma-3-27b-it","context_length":40000,"max_input_tokens":null,"max_output_tokens":8192,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.8712497171819026e-7,"output_cost_per_token":5.742499434363805e-7},"list_pricing":{"input_cost_per_token":2.8712497171819026e-7,"output_cost_per_token":5.742499434363805e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":5},{"id":"gemma-3-4b-it","object":"model","created":1767692616,"owned_by":"google","mode":"chat","context_length":131072,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4e-8,"output_cost_per_token":8e-8,"input_cost_per_token_flex":2e-8,"output_cost_per_token_flex":4e-8,"input_cost_per_token_priority":7e-8,"output_cost_per_token_priority":1.4e-7},"pricing_endpoint":"amazon/google.gemma-3-4b-it","regions":[{"code":"eu","name":"Europe"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"amazon/google.gemma-3-4b-it","object":"model","created":1767692616,"owned_by":"amazon","model_name":"google.gemma-3-4b-it","context_length":128000,"max_input_tokens":128000,"max_output_tokens":8000,"quantization":null,"retirement_date":null,"description":"Gemma 3 introduces multimodality, supporting vision-language input and text outputs.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4e-8,"output_cost_per_token":8e-8,"input_cost_per_token_flex":2e-8,"output_cost_per_token_flex":4e-8,"input_cost_per_token_priority":7e-8,"output_cost_per_token_priority":1.4e-7},"list_pricing":{"input_cost_per_token":4e-8,"output_cost_per_token":8e-8,"input_cost_per_token_flex":2e-8,"output_cost_per_token_flex":4e-8,"input_cost_per_token_priority":7e-8,"output_cost_per_token_priority":1.4e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/google.gemma-3-4b-it@us","object":"model","created":1767692616,"owned_by":"amazon","model_name":"google.gemma-3-4b-it","context_length":128000,"max_input_tokens":128000,"max_output_tokens":8000,"quantization":null,"retirement_date":null,"description":"Gemma 3 introduces multimodality, supporting vision-language input and text outputs.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4e-8,"output_cost_per_token":8e-8,"input_cost_per_token_flex":2e-8,"output_cost_per_token_flex":4e-8,"input_cost_per_token_priority":7e-8,"output_cost_per_token_priority":1.4e-7},"list_pricing":{"input_cost_per_token":4e-8,"output_cost_per_token":8e-8,"input_cost_per_token_flex":2e-8,"output_cost_per_token_flex":4e-8,"input_cost_per_token_priority":7e-8,"output_cost_per_token_priority":1.4e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"deepinfra/google/gemma-3-4b-it","object":"model","created":1741905510,"owned_by":"deepinfra","model_name":"google/gemma-3-4b-it","context_length":131072,"max_input_tokens":131072,"max_output_tokens":16384,"quantization":"bf16","retirement_date":null,"description":"Gemma 3 introduces multimodality, supporting vision-language input and text outputs.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5.0000000000000004e-8,"output_cost_per_token":1.0000000000000001e-7},"list_pricing":{"input_cost_per_token":5.0000000000000004e-8,"output_cost_per_token":1.0000000000000001e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":3},{"id":"gpt-3.5-turbo","object":"model","created":1767692616,"owned_by":"openai","mode":"chat","context_length":4097,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":1.5e-6},"pricing_endpoint":"microsoft/gpt-35-turbo","regions":[{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"microsoft/gpt-35-turbo","object":"model","created":1767692616,"owned_by":"microsoft","model_name":"gpt-35-turbo","context_length":4097,"max_input_tokens":4097,"max_output_tokens":4096,"quantization":null,"retirement_date":null,"description":"","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":1.5e-6},"list_pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":1.5e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":1},{"id":"gpt-oss-safeguard-120b","object":"model","created":1767692616,"owned_by":"openai","mode":"chat","context_length":128000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"input_cost_per_token_flex":7e-8,"output_cost_per_token_flex":3e-7,"input_cost_per_token_priority":2.6e-7,"output_cost_per_token_priority":1.05e-6},"pricing_endpoint":"amazon/openai.gpt-oss-safeguard-120b","regions":[{"code":"eu","name":"Europe"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"amazon/openai.gpt-oss-safeguard-120b","object":"model","created":1767692616,"owned_by":"amazon","model_name":"openai.gpt-oss-safeguard-120b","context_length":128000,"max_input_tokens":128000,"max_output_tokens":16000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"input_cost_per_token_flex":7e-8,"output_cost_per_token_flex":3e-7,"input_cost_per_token_priority":2.6e-7,"output_cost_per_token_priority":1.05e-6},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"input_cost_per_token_flex":7e-8,"output_cost_per_token_flex":3e-7,"input_cost_per_token_priority":2.6e-7,"output_cost_per_token_priority":1.05e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/openai.gpt-oss-safeguard-120b@us","object":"model","created":1767692616,"owned_by":"amazon","model_name":"openai.gpt-oss-safeguard-120b","context_length":128000,"max_input_tokens":128000,"max_output_tokens":16000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"input_cost_per_token_flex":7e-8,"output_cost_per_token_flex":3e-7,"input_cost_per_token_priority":2.6e-7,"output_cost_per_token_priority":1.05e-6},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"input_cost_per_token_flex":7e-8,"output_cost_per_token_flex":3e-7,"input_cost_per_token_priority":2.6e-7,"output_cost_per_token_priority":1.05e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"gpt-oss-safeguard-20b","object":"model","created":1767692616,"owned_by":"openai","mode":"chat","context_length":131072,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":7e-8,"output_cost_per_token":2e-7,"input_cost_per_token_flex":3e-8,"output_cost_per_token_flex":1e-7,"input_cost_per_token_priority":1.2e-7,"output_cost_per_token_priority":3.5e-7},"pricing_endpoint":"amazon/openai.gpt-oss-safeguard-20b","regions":[{"code":"eu","name":"Europe"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"amazon/openai.gpt-oss-safeguard-20b","object":"model","created":1767692616,"owned_by":"amazon","model_name":"openai.gpt-oss-safeguard-20b","context_length":128000,"max_input_tokens":128000,"max_output_tokens":16000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":7e-8,"output_cost_per_token":2e-7,"input_cost_per_token_flex":3e-8,"output_cost_per_token_flex":1e-7,"input_cost_per_token_priority":1.2e-7,"output_cost_per_token_priority":3.5e-7},"list_pricing":{"input_cost_per_token":7e-8,"output_cost_per_token":2e-7,"input_cost_per_token_flex":3e-8,"output_cost_per_token_flex":1e-7,"input_cost_per_token_priority":1.2e-7,"output_cost_per_token_priority":3.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/openai.gpt-oss-safeguard-20b@us","object":"model","created":1767692616,"owned_by":"amazon","model_name":"openai.gpt-oss-safeguard-20b","context_length":128000,"max_input_tokens":128000,"max_output_tokens":16000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":7e-8,"output_cost_per_token":2e-7,"input_cost_per_token_flex":3e-8,"output_cost_per_token_flex":1e-7,"input_cost_per_token_priority":1.2e-7,"output_cost_per_token_priority":3.5e-7},"list_pricing":{"input_cost_per_token":7e-8,"output_cost_per_token":2e-7,"input_cost_per_token_flex":3e-8,"output_cost_per_token_flex":1e-7,"input_cost_per_token_priority":1.2e-7,"output_cost_per_token_priority":3.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"groq/openai/gpt-oss-safeguard-20b","object":"model","created":1761752836,"owned_by":"groq","model_name":"openai/gpt-oss-safeguard-20b","context_length":131072,"max_input_tokens":131072,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"gpt-oss-safeguard-20b is a safety reasoning model from OpenAI built upon gpt-oss-20b.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":7.5e-8,"output_cost_per_token":3e-7,"cache_read_input_token_cost":3.75e-8,"search_context_cost_per_query":{"search_context_size_low":0.005,"search_context_size_high":0.005,"search_context_size_medium":0.005}},"list_pricing":{"input_cost_per_token":7.5e-8,"output_cost_per_token":3e-7,"cache_read_input_token_cost":3.75e-8,"search_context_cost_per_query":{"search_context_size_low":0.005,"search_context_size_high":0.005,"search_context_size_medium":0.005}},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":3},{"id":"grok-3-fast-beta","object":"model","created":1767692616,"owned_by":"xai","mode":"chat","context_length":131072,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-6,"output_cost_per_token":0.000025,"cache_read_input_token_cost":1.25e-6},"pricing_endpoint":"xai/grok-3-fast-beta","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"xai/grok-3-fast-beta","object":"model","created":1767692616,"owned_by":"xai","model_name":"grok-3-fast-beta","context_length":131072,"max_input_tokens":131072,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"","source":"https://x.ai/api#pricing","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-6,"output_cost_per_token":0.000025,"cache_read_input_token_cost":1.25e-6},"list_pricing":{"input_cost_per_token":5e-6,"output_cost_per_token":0.000025,"cache_read_input_token_cost":1.25e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"grok-3-fast-latest","object":"model","created":1767692616,"owned_by":"xai","mode":"chat","context_length":131072,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-6,"output_cost_per_token":0.000025,"cache_read_input_token_cost":1.25e-6},"pricing_endpoint":"xai/grok-3-fast-latest","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"xai/grok-3-fast-latest","object":"model","created":1767692616,"owned_by":"xai","model_name":"grok-3-fast-latest","context_length":131072,"max_input_tokens":131072,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"","source":"https://x.ai/api#pricing","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-6,"output_cost_per_token":0.000025,"cache_read_input_token_cost":1.25e-6},"list_pricing":{"input_cost_per_token":5e-6,"output_cost_per_token":0.000025,"cache_read_input_token_cost":1.25e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"grok-3-latest","object":"model","created":1767692616,"owned_by":"xai","mode":"chat","context_length":131072,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"cache_read_input_token_cost":7.5e-7},"pricing_endpoint":"xai/grok-3-latest","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"xai/grok-3-latest","object":"model","created":1767692616,"owned_by":"xai","model_name":"grok-3-latest","context_length":131072,"max_input_tokens":131072,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"","source":"https://x.ai/api#pricing","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"cache_read_input_token_cost":7.5e-7},"list_pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"cache_read_input_token_cost":7.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"grok-3-mini-fast","object":"model","created":1767692616,"owned_by":"xai","mode":"chat","context_length":131072,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6e-7,"output_cost_per_token":4e-6,"cache_read_input_token_cost":1.5e-7},"pricing_endpoint":"xai/grok-3-mini-fast","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"xai/grok-3-mini-fast","object":"model","created":1767692616,"owned_by":"xai","model_name":"grok-3-mini-fast","context_length":131072,"max_input_tokens":131072,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"","source":"https://x.ai/api#pricing","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6e-7,"output_cost_per_token":4e-6,"cache_read_input_token_cost":1.5e-7},"list_pricing":{"input_cost_per_token":6e-7,"output_cost_per_token":4e-6,"cache_read_input_token_cost":1.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"grok-3-mini-fast-beta","object":"model","created":1767692616,"owned_by":"xai","mode":"chat","context_length":131072,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6e-7,"output_cost_per_token":4e-6,"cache_read_input_token_cost":1.5e-7},"pricing_endpoint":"xai/grok-3-mini-fast-beta","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"xai/grok-3-mini-fast-beta","object":"model","created":1767692616,"owned_by":"xai","model_name":"grok-3-mini-fast-beta","context_length":131072,"max_input_tokens":131072,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"","source":"https://x.ai/api#pricing","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6e-7,"output_cost_per_token":4e-6,"cache_read_input_token_cost":1.5e-7},"list_pricing":{"input_cost_per_token":6e-7,"output_cost_per_token":4e-6,"cache_read_input_token_cost":1.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"grok-3-mini-fast-latest","object":"model","created":1767692616,"owned_by":"xai","mode":"chat","context_length":131072,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6e-7,"output_cost_per_token":4e-6,"cache_read_input_token_cost":1.5e-7},"pricing_endpoint":"xai/grok-3-mini-fast-latest","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"xai/grok-3-mini-fast-latest","object":"model","created":1767692616,"owned_by":"xai","model_name":"grok-3-mini-fast-latest","context_length":131072,"max_input_tokens":131072,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"","source":"https://x.ai/api#pricing","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6e-7,"output_cost_per_token":4e-6,"cache_read_input_token_cost":1.5e-7},"list_pricing":{"input_cost_per_token":6e-7,"output_cost_per_token":4e-6,"cache_read_input_token_cost":1.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"grok-3-mini-latest","object":"model","created":1767692616,"owned_by":"xai","mode":"chat","context_length":131072,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":7.5e-8},"pricing_endpoint":"xai/grok-3-mini-latest","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"xai/grok-3-mini-latest","object":"model","created":1767692616,"owned_by":"xai","model_name":"grok-3-mini-latest","context_length":131072,"max_input_tokens":131072,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"","source":"https://x.ai/api#pricing","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":7.5e-8},"list_pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":7.5e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"grok-4-0709","object":"model","created":1767692616,"owned_by":"xai","mode":"chat","context_length":256000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"input_cost_per_token_above_128k_tokens":6e-6,"output_cost_per_token_above_128k_tokens":0.00003},"pricing_endpoint":"xai/grok-4-0709","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"xai/grok-4-0709","object":"model","created":1767692616,"owned_by":"xai","model_name":"grok-4-0709","context_length":256000,"max_input_tokens":256000,"max_output_tokens":256000,"quantization":null,"retirement_date":null,"description":"","source":"https://docs.x.ai/docs/models","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"input_cost_per_token_above_128k_tokens":6e-6,"output_cost_per_token_above_128k_tokens":0.00003},"list_pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"input_cost_per_token_above_128k_tokens":6e-6,"output_cost_per_token_above_128k_tokens":0.00003},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"grok-4-1-fast-non-reasoning","object":"model","created":1767692616,"owned_by":"xai","mode":"chat","context_length":2000000,"capabilities":{"input_modalities":["audio","image","text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":5e-8,"input_cost_per_token_above_128k_tokens":4e-7,"output_cost_per_token_above_128k_tokens":1e-6},"pricing_endpoint":"xai/grok-4-1-fast-non-reasoning","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"xai/grok-4-1-fast-non-reasoning","object":"model","created":1767692616,"owned_by":"xai","model_name":"grok-4-1-fast-non-reasoning","context_length":2000000,"max_input_tokens":2000000,"max_output_tokens":2000000,"quantization":null,"retirement_date":null,"description":"","source":"https://docs.x.ai/docs/models/grok-4-1-fast-non-reasoning","capabilities":{"input_modalities":["audio","image","text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":5e-8,"input_cost_per_token_above_128k_tokens":4e-7,"output_cost_per_token_above_128k_tokens":1e-6},"list_pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":5e-8,"input_cost_per_token_above_128k_tokens":4e-7,"output_cost_per_token_above_128k_tokens":1e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"grok-4-1-fast-non-reasoning-latest","object":"model","created":1767692616,"owned_by":"xai","mode":"chat","context_length":2000000,"capabilities":{"input_modalities":["audio","image","text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":5e-8,"input_cost_per_token_above_128k_tokens":4e-7,"output_cost_per_token_above_128k_tokens":1e-6},"pricing_endpoint":"xai/grok-4-1-fast-non-reasoning-latest","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"xai/grok-4-1-fast-non-reasoning-latest","object":"model","created":1767692616,"owned_by":"xai","model_name":"grok-4-1-fast-non-reasoning-latest","context_length":2000000,"max_input_tokens":2000000,"max_output_tokens":2000000,"quantization":null,"retirement_date":null,"description":"","source":"https://docs.x.ai/docs/models/grok-4-1-fast-non-reasoning","capabilities":{"input_modalities":["audio","image","text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":5e-8,"input_cost_per_token_above_128k_tokens":4e-7,"output_cost_per_token_above_128k_tokens":1e-6},"list_pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":5e-8,"input_cost_per_token_above_128k_tokens":4e-7,"output_cost_per_token_above_128k_tokens":1e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"grok-4-1-fast-reasoning","object":"model","created":1767692616,"owned_by":"xai","mode":"chat","context_length":2000000,"capabilities":{"input_modalities":["audio","image","text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":5e-8,"input_cost_per_token_above_128k_tokens":4e-7,"output_cost_per_token_above_128k_tokens":1e-6},"pricing_endpoint":"xai/grok-4-1-fast-reasoning","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"xai/grok-4-1-fast-reasoning","object":"model","created":1767692616,"owned_by":"xai","model_name":"grok-4-1-fast-reasoning","context_length":2000000,"max_input_tokens":2000000,"max_output_tokens":2000000,"quantization":null,"retirement_date":null,"description":"","source":"https://docs.x.ai/docs/models/grok-4-1-fast-reasoning","capabilities":{"input_modalities":["audio","image","text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":5e-8,"input_cost_per_token_above_128k_tokens":4e-7,"output_cost_per_token_above_128k_tokens":1e-6},"list_pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":5e-8,"input_cost_per_token_above_128k_tokens":4e-7,"output_cost_per_token_above_128k_tokens":1e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"grok-4-1-fast-reasoning-latest","object":"model","created":1767692616,"owned_by":"xai","mode":"chat","context_length":2000000,"capabilities":{"input_modalities":["audio","image","text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":5e-8,"input_cost_per_token_above_128k_tokens":4e-7,"output_cost_per_token_above_128k_tokens":1e-6},"pricing_endpoint":"xai/grok-4-1-fast-reasoning-latest","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"xai/grok-4-1-fast-reasoning-latest","object":"model","created":1767692616,"owned_by":"xai","model_name":"grok-4-1-fast-reasoning-latest","context_length":2000000,"max_input_tokens":2000000,"max_output_tokens":2000000,"quantization":null,"retirement_date":null,"description":"","source":"https://docs.x.ai/docs/models/grok-4-1-fast-reasoning","capabilities":{"input_modalities":["audio","image","text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":5e-8,"input_cost_per_token_above_128k_tokens":4e-7,"output_cost_per_token_above_128k_tokens":1e-6},"list_pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":5e-8,"input_cost_per_token_above_128k_tokens":4e-7,"output_cost_per_token_above_128k_tokens":1e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"grok-4-fast-non-reasoning","object":"model","created":1767692616,"owned_by":"xai","mode":"chat","context_length":2000000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":5e-8,"input_cost_per_token_above_128k_tokens":4e-7,"output_cost_per_token_above_128k_tokens":1e-6},"pricing_endpoint":"xai/grok-4-fast-non-reasoning","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"xai/grok-4-fast-non-reasoning","object":"model","created":1767692616,"owned_by":"xai","model_name":"grok-4-fast-non-reasoning","context_length":2000000,"max_input_tokens":2000000,"max_output_tokens":2000000,"quantization":null,"retirement_date":null,"description":"","source":"https://docs.x.ai/docs/models","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":5e-8,"input_cost_per_token_above_128k_tokens":4e-7,"output_cost_per_token_above_128k_tokens":1e-6},"list_pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":5e-8,"input_cost_per_token_above_128k_tokens":4e-7,"output_cost_per_token_above_128k_tokens":1e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"grok-4-fast-reasoning","object":"model","created":1767692616,"owned_by":"xai","mode":"chat","context_length":2000000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":5e-8,"input_cost_per_token_above_128k_tokens":4e-7,"output_cost_per_token_above_128k_tokens":1e-6},"pricing_endpoint":"xai/grok-4-fast-reasoning","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"xai/grok-4-fast-reasoning","object":"model","created":1767692616,"owned_by":"xai","model_name":"grok-4-fast-reasoning","context_length":2000000,"max_input_tokens":2000000,"max_output_tokens":2000000,"quantization":null,"retirement_date":null,"description":"","source":"https://docs.x.ai/docs/models","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":5e-8,"input_cost_per_token_above_128k_tokens":4e-7,"output_cost_per_token_above_128k_tokens":1e-6},"list_pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":5e-8,"input_cost_per_token_above_128k_tokens":4e-7,"output_cost_per_token_above_128k_tokens":1e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"grok-4-latest","object":"model","created":1767692616,"owned_by":"xai","mode":"chat","context_length":256000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"input_cost_per_token_above_128k_tokens":6e-6,"output_cost_per_token_above_128k_tokens":0.00003},"pricing_endpoint":"xai/grok-4-latest","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"xai/grok-4-latest","object":"model","created":1767692616,"owned_by":"xai","model_name":"grok-4-latest","context_length":256000,"max_input_tokens":256000,"max_output_tokens":256000,"quantization":null,"retirement_date":null,"description":"","source":"https://docs.x.ai/docs/models","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"input_cost_per_token_above_128k_tokens":6e-6,"output_cost_per_token_above_128k_tokens":0.00003},"list_pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"input_cost_per_token_above_128k_tokens":6e-6,"output_cost_per_token_above_128k_tokens":0.00003},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"grok-code-fast","object":"model","created":1767692616,"owned_by":"xai","mode":"chat","context_length":256000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":1.5e-6,"cache_read_input_token_cost":2e-8},"pricing_endpoint":"xai/grok-code-fast","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"xai/grok-code-fast","object":"model","created":1767692616,"owned_by":"xai","model_name":"grok-code-fast","context_length":256000,"max_input_tokens":256000,"max_output_tokens":256000,"quantization":null,"retirement_date":null,"description":"","source":"https://docs.x.ai/docs/models","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":1.5e-6,"cache_read_input_token_cost":2e-8},"list_pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":1.5e-6,"cache_read_input_token_cost":2e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"grok-code-fast-1-0825","object":"model","created":1767692616,"owned_by":"xai","mode":"chat","context_length":256000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":1.5e-6,"cache_read_input_token_cost":2e-8},"pricing_endpoint":"xai/grok-code-fast-1-0825","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"xai/grok-code-fast-1-0825","object":"model","created":1767692616,"owned_by":"xai","model_name":"grok-code-fast-1-0825","context_length":256000,"max_input_tokens":256000,"max_output_tokens":256000,"quantization":null,"retirement_date":null,"description":"","source":"https://docs.x.ai/docs/models","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":1.5e-6,"cache_read_input_token_cost":2e-8},"list_pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":1.5e-6,"cache_read_input_token_cost":2e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"kimi-k2-instruct-0905","object":"model","created":1767692616,"owned_by":"moonshot","mode":"chat","context_length":262144,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":2e-6,"cache_read_input_token_cost":4e-7},"pricing_endpoint":"deepinfra/moonshotai/Kimi-K2-Instruct-0905","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"deepinfra/moonshotai/Kimi-K2-Instruct-0905","object":"model","created":1767692616,"owned_by":"deepinfra","model_name":"moonshotai/Kimi-K2-Instruct-0905","context_length":262144,"max_input_tokens":262144,"max_output_tokens":262144,"quantization":null,"retirement_date":null,"description":"","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":2e-6,"cache_read_input_token_cost":4e-7},"list_pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":2e-6,"cache_read_input_token_cost":4e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"kimi-k2-thinking","object":"model","created":1767692616,"owned_by":"moonshot","mode":"chat","context_length":256000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6e-7,"output_cost_per_token":2.5e-6,"input_cost_per_token_priority":1.05e-6,"output_cost_per_token_priority":4.38e-6},"pricing_endpoint":"amazon/moonshot.kimi-k2-thinking","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"amazon/moonshot.kimi-k2-thinking","object":"model","created":1767692616,"owned_by":"amazon","model_name":"moonshot.kimi-k2-thinking","context_length":256000,"max_input_tokens":256000,"max_output_tokens":16000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6e-7,"output_cost_per_token":2.5e-6,"input_cost_per_token_priority":1.05e-6,"output_cost_per_token_priority":4.38e-6},"list_pricing":{"input_cost_per_token":6e-7,"output_cost_per_token":2.5e-6,"input_cost_per_token_priority":1.05e-6,"output_cost_per_token_priority":4.38e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"l3-8b-lunaris-turbo","object":"model","created":1767692616,"owned_by":"sao10k","mode":"chat","context_length":8192,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4e-8,"output_cost_per_token":5.0000000000000004e-8},"pricing_endpoint":"deepinfra/Sao10K/L3-8B-Lunaris-v1-Turbo","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"deepinfra/Sao10K/L3-8B-Lunaris-v1-Turbo","object":"model","created":1767692616,"owned_by":"deepinfra","model_name":"Sao10K/L3-8B-Lunaris-v1-Turbo","context_length":8192,"max_input_tokens":8192,"max_output_tokens":null,"quantization":"fp8","retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4e-8,"output_cost_per_token":5.0000000000000004e-8},"list_pricing":{"input_cost_per_token":4e-8,"output_cost_per_token":5.0000000000000004e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"l3.1-70b-euryale-v2.2","object":"model","created":1767692616,"owned_by":"sao10k","mode":"chat","context_length":131072,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":8.5e-7,"output_cost_per_token":8.5e-7},"pricing_endpoint":"deepinfra/Sao10K/L3.1-70B-Euryale-v2.2","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"deepinfra/Sao10K/L3.1-70B-Euryale-v2.2","object":"model","created":1767692616,"owned_by":"deepinfra","model_name":"Sao10K/L3.1-70B-Euryale-v2.2","context_length":131072,"max_input_tokens":131072,"max_output_tokens":null,"quantization":"fp8","retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":8.5e-7,"output_cost_per_token":8.5e-7},"list_pricing":{"input_cost_per_token":8.5e-7,"output_cost_per_token":8.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"l3.3-70b-euryale-v2.3","object":"model","created":1767692616,"owned_by":"sao10k","mode":"chat","context_length":131072,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6.5e-7,"output_cost_per_token":7.5e-7},"pricing_endpoint":"deepinfra/Sao10K/L3.3-70B-Euryale-v2.3","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"deepinfra/Sao10K/L3.3-70B-Euryale-v2.3","object":"model","created":1767692616,"owned_by":"deepinfra","model_name":"Sao10K/L3.3-70B-Euryale-v2.3","context_length":131072,"max_input_tokens":131072,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6.5e-7,"output_cost_per_token":7.5e-7},"list_pricing":{"input_cost_per_token":6.5e-7,"output_cost_per_token":7.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"labs-devstral-small-2512","object":"model","created":1767692616,"owned_by":"mistral","mode":"chat","context_length":256000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":3e-7},"pricing_endpoint":"mistral/labs-devstral-small-2512","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"mistral/labs-devstral-small-2512@eu","object":"model","created":1767692616,"owned_by":"mistral","model_name":"labs-devstral-small-2512","context_length":256000,"max_input_tokens":256000,"max_output_tokens":256000,"quantization":null,"retirement_date":null,"description":"","source":"https://docs.mistral.ai/models/devstral-small-2-25-12","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.1e-7,"output_cost_per_token":3.3e-7},"list_pricing":{"input_cost_per_token":1.1e-7,"output_cost_per_token":3.3e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":false,"alias_of":null},{"id":"mistral/labs-devstral-small-2512","object":"model","created":1767692616,"owned_by":"mistral","model_name":"labs-devstral-small-2512","context_length":256000,"max_input_tokens":256000,"max_output_tokens":256000,"quantization":null,"retirement_date":null,"description":"","source":"https://docs.mistral.ai/models/devstral-small-2-25-12","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":3e-7},"list_pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":3e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":2},{"id":"llama-3.1-70b-instruct-turbo","object":"model","created":1767692616,"owned_by":"meta","mode":"chat","context_length":131072,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4.0000000000000003e-7,"output_cost_per_token":4.0000000000000003e-7},"pricing_endpoint":"deepinfra/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"deepinfra/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo","object":"model","created":1767692616,"owned_by":"deepinfra","model_name":"meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo","context_length":131072,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4.0000000000000003e-7,"output_cost_per_token":4.0000000000000003e-7},"list_pricing":{"input_cost_per_token":4.0000000000000003e-7,"output_cost_per_token":4.0000000000000003e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"llama-3.1-8b-instruct-turbo","object":"model","created":1767692616,"owned_by":"meta","mode":"chat","context_length":131072,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-8,"output_cost_per_token":4e-8},"pricing_endpoint":"deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo","object":"model","created":1767692616,"owned_by":"deepinfra","model_name":"meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo","context_length":131072,"max_input_tokens":131072,"max_output_tokens":null,"quantization":"fp8","retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-8,"output_cost_per_token":4e-8},"list_pricing":{"input_cost_per_token":2e-8,"output_cost_per_token":4e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"llama-3.1-nemotron-70b-instruct","object":"model","created":1767692616,"owned_by":"nvidia","mode":"chat","context_length":131072,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6e-7,"output_cost_per_token":6e-7},"pricing_endpoint":"deepinfra/nvidia/Llama-3.1-Nemotron-70B-Instruct","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"deepinfra/nvidia/Llama-3.1-Nemotron-70B-Instruct","object":"model","created":1767692616,"owned_by":"deepinfra","model_name":"nvidia/Llama-3.1-Nemotron-70B-Instruct","context_length":131072,"max_input_tokens":131072,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6e-7,"output_cost_per_token":6e-7},"list_pricing":{"input_cost_per_token":6e-7,"output_cost_per_token":6e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"llama-3.3-70b-instruct-turbo","object":"model","created":1767692616,"owned_by":"meta","mode":"chat","context_length":131072,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.0000000000000001e-7,"output_cost_per_token":3.2e-7},"pricing_endpoint":"deepinfra/meta-llama/Llama-3.3-70B-Instruct-Turbo","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"deepinfra/meta-llama/Llama-3.3-70B-Instruct-Turbo","object":"model","created":1767692616,"owned_by":"deepinfra","model_name":"meta-llama/Llama-3.3-70B-Instruct-Turbo","context_length":131072,"max_input_tokens":131072,"max_output_tokens":null,"quantization":"fp8","retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.0000000000000001e-7,"output_cost_per_token":3.2e-7},"list_pricing":{"input_cost_per_token":1.0000000000000001e-7,"output_cost_per_token":3.2e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"llama-4-maverick-17b-128e-instruct-fp8","object":"model","created":1767692616,"owned_by":"meta","mode":"chat","context_length":1048576,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.0000000000000002e-7,"output_cost_per_token":8.000000000000001e-7},"pricing_endpoint":"deepinfra/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"deepinfra/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8","object":"model","created":1767692616,"owned_by":"deepinfra","model_name":"meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8","context_length":1048576,"max_input_tokens":null,"max_output_tokens":1048576,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.0000000000000002e-7,"output_cost_per_token":8.000000000000001e-7},"list_pricing":{"input_cost_per_token":2.0000000000000002e-7,"output_cost_per_token":8.000000000000001e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"magistral-medium-latest","object":"model","created":1767692616,"owned_by":"mistral","mode":"chat","context_length":262144,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-6,"output_cost_per_token":7.5e-6,"cache_read_input_token_cost":1.5e-7,"input_cost_per_token_batches":7.5e-7,"output_cost_per_token_batches":3.75e-6,"cache_read_input_token_cost_batches":7.5e-8},"pricing_endpoint":"mistral/magistral-medium-latest","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"mistral/magistral-medium-latest@eu","object":"model","created":1767692616,"owned_by":"mistral","model_name":"magistral-medium-latest","context_length":262144,"max_input_tokens":262144,"max_output_tokens":null,"quantization":null,"retirement_date":"2026-07-31","description":null,"source":"https://mistral.ai/news/magistral","capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.65e-6,"output_cost_per_token":8.25e-6,"cache_read_input_token_cost":1.65e-7,"input_cost_per_token_batches":8.25e-7,"output_cost_per_token_batches":4.125e-6,"cache_read_input_token_cost_batches":8.25e-8},"list_pricing":{"input_cost_per_token":1.65e-6,"output_cost_per_token":8.25e-6,"cache_read_input_token_cost":1.65e-7,"input_cost_per_token_batches":8.25e-7,"output_cost_per_token_batches":4.125e-6,"cache_read_input_token_cost_batches":8.25e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"mistral/magistral-medium-latest","object":"model","created":1767692616,"owned_by":"mistral","model_name":"magistral-medium-latest","context_length":262144,"max_input_tokens":262144,"max_output_tokens":null,"quantization":null,"retirement_date":"2026-07-31","description":null,"source":"https://mistral.ai/news/magistral","capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-6,"output_cost_per_token":7.5e-6,"cache_read_input_token_cost":1.5e-7,"input_cost_per_token_batches":7.5e-7,"output_cost_per_token_batches":3.75e-6,"cache_read_input_token_cost_batches":7.5e-8},"list_pricing":{"input_cost_per_token":1.5e-6,"output_cost_per_token":7.5e-6,"cache_read_input_token_cost":1.5e-7,"input_cost_per_token_batches":7.5e-7,"output_cost_per_token_batches":3.75e-6,"cache_read_input_token_cost_batches":7.5e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"magistral-small-2509","object":"model","created":1767692616,"owned_by":"mistral","mode":"chat","context_length":128000,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":1.5e-6,"input_cost_per_token_flex":2.5e-7,"output_cost_per_token_flex":7.5e-7,"input_cost_per_token_priority":8.8e-7,"output_cost_per_token_priority":2.63e-6},"pricing_endpoint":"amazon/mistral.magistral-small-2509","regions":[{"code":"eu","name":"Europe"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"amazon/mistral.magistral-small-2509","object":"model","created":1767692616,"owned_by":"amazon","model_name":"mistral.magistral-small-2509","context_length":128000,"max_input_tokens":128000,"max_output_tokens":40000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":1.5e-6,"input_cost_per_token_flex":2.5e-7,"output_cost_per_token_flex":7.5e-7,"input_cost_per_token_priority":8.8e-7,"output_cost_per_token_priority":2.63e-6},"list_pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":1.5e-6,"input_cost_per_token_flex":2.5e-7,"output_cost_per_token_flex":7.5e-7,"input_cost_per_token_priority":8.8e-7,"output_cost_per_token_priority":2.63e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/mistral.magistral-small-2509@us","object":"model","created":1767692616,"owned_by":"amazon","model_name":"mistral.magistral-small-2509","context_length":128000,"max_input_tokens":128000,"max_output_tokens":40000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":1.5e-6,"input_cost_per_token_flex":2.5e-7,"output_cost_per_token_flex":7.5e-7,"input_cost_per_token_priority":8.8e-7,"output_cost_per_token_priority":2.63e-6},"list_pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":1.5e-6,"input_cost_per_token_flex":2.5e-7,"output_cost_per_token_flex":7.5e-7,"input_cost_per_token_priority":8.8e-7,"output_cost_per_token_priority":2.63e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"magistral-small-latest","object":"model","created":1767692616,"owned_by":"mistral","mode":"chat","context_length":262144,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":1.5e-8,"input_cost_per_token_batches":7.5e-8,"output_cost_per_token_batches":3e-7,"cache_read_input_token_cost_batches":7.5e-9},"pricing_endpoint":"mistral/magistral-small-latest","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"mistral/magistral-small-latest@eu","object":"model","created":1767692616,"owned_by":"mistral","model_name":"magistral-small-latest","context_length":262144,"max_input_tokens":262144,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":"https://mistral.ai/pricing#api-pricing","capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.65e-7,"output_cost_per_token":6.6e-7,"cache_read_input_token_cost":1.65e-8,"input_cost_per_token_batches":8.25e-8,"output_cost_per_token_batches":3.3e-7,"cache_read_input_token_cost_batches":8.25e-9},"list_pricing":{"input_cost_per_token":1.65e-7,"output_cost_per_token":6.6e-7,"cache_read_input_token_cost":1.65e-8,"input_cost_per_token_batches":8.25e-8,"output_cost_per_token_batches":3.3e-7,"cache_read_input_token_cost_batches":8.25e-9},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"mistral/magistral-small-latest","object":"model","created":1767692616,"owned_by":"mistral","model_name":"magistral-small-latest","context_length":262144,"max_input_tokens":262144,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":"https://mistral.ai/pricing#api-pricing","capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":1.5e-8,"input_cost_per_token_batches":7.5e-8,"output_cost_per_token_batches":3e-7,"cache_read_input_token_cost_batches":7.5e-9},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":1.5e-8,"input_cost_per_token_batches":7.5e-8,"output_cost_per_token_batches":3e-7,"cache_read_input_token_cost_batches":7.5e-9},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"minimax-m2","object":"model","created":1767692616,"owned_by":"minimax","mode":"chat","context_length":1000000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1.2e-6},"pricing_endpoint":"minimax/MiniMax-M2","regions":[{"code":"ap","name":"Asia"},{"code":"eu","name":"Europe"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"amazon/minimax.minimax-m2","object":"model","created":1767692616,"owned_by":"amazon","model_name":"minimax.minimax-m2","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":8000,"quantization":null,"retirement_date":null,"description":"MiniMax-M2 is a compact, high-efficiency large language model optimized for end-to-end coding and agentic workflows.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1.2e-6,"input_cost_per_token_flex":1.5e-7,"output_cost_per_token_flex":6e-7,"input_cost_per_token_priority":5.2e-7,"output_cost_per_token_priority":2.1e-6},"list_pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1.2e-6,"input_cost_per_token_flex":1.5e-7,"output_cost_per_token_flex":6e-7,"input_cost_per_token_priority":5.2e-7,"output_cost_per_token_priority":2.1e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/minimax.minimax-m2@us","object":"model","created":1767692616,"owned_by":"amazon","model_name":"minimax.minimax-m2","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":8000,"quantization":null,"retirement_date":null,"description":"MiniMax-M2 is a compact, high-efficiency large language model optimized for end-to-end coding and agentic workflows.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1.2e-6,"input_cost_per_token_flex":1.5e-7,"output_cost_per_token_flex":6e-7,"input_cost_per_token_priority":5.2e-7,"output_cost_per_token_priority":2.1e-6},"list_pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1.2e-6,"input_cost_per_token_flex":1.5e-7,"output_cost_per_token_flex":6e-7,"input_cost_per_token_priority":5.2e-7,"output_cost_per_token_priority":2.1e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"minimax/MiniMax-M2","object":"model","created":1761252093,"owned_by":"minimax","model_name":"MiniMax-M2","context_length":204800,"max_input_tokens":null,"max_output_tokens":131072,"quantization":null,"retirement_date":"2026-11-05","description":"MiniMax-M2 is a compact, high-efficiency large language model optimized for end-to-end coding and agentic workflows.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1.2e-6},"list_pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1.2e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"ap","name":"Asia"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":3},{"id":"ministral-3-14b-instruct","object":"model","created":1767692616,"owned_by":"mistral","mode":"chat","context_length":128000,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":2e-7,"input_cost_per_token_flex":1e-7,"output_cost_per_token_flex":1e-7,"input_cost_per_token_priority":3.5e-7,"output_cost_per_token_priority":3.5e-7},"pricing_endpoint":"amazon/mistral.ministral-3-14b-instruct","regions":[{"code":"eu","name":"Europe"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"amazon/mistral.ministral-3-14b-instruct","object":"model","created":1767692616,"owned_by":"amazon","model_name":"mistral.ministral-3-14b-instruct","context_length":128000,"max_input_tokens":128000,"max_output_tokens":8000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":2e-7,"input_cost_per_token_flex":1e-7,"output_cost_per_token_flex":1e-7,"input_cost_per_token_priority":3.5e-7,"output_cost_per_token_priority":3.5e-7},"list_pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":2e-7,"input_cost_per_token_flex":1e-7,"output_cost_per_token_flex":1e-7,"input_cost_per_token_priority":3.5e-7,"output_cost_per_token_priority":3.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/mistral.ministral-3-14b-instruct@us","object":"model","created":1767692616,"owned_by":"amazon","model_name":"mistral.ministral-3-14b-instruct","context_length":128000,"max_input_tokens":128000,"max_output_tokens":8000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":2e-7,"input_cost_per_token_flex":1e-7,"output_cost_per_token_flex":1e-7,"input_cost_per_token_priority":3.5e-7,"output_cost_per_token_priority":3.5e-7},"list_pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":2e-7,"input_cost_per_token_flex":1e-7,"output_cost_per_token_flex":1e-7,"input_cost_per_token_priority":3.5e-7,"output_cost_per_token_priority":3.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"ministral-3-3b-instruct","object":"model","created":1767692616,"owned_by":"mistral","mode":"chat","context_length":128000,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":1e-7,"input_cost_per_token_flex":5e-8,"output_cost_per_token_flex":5e-8,"input_cost_per_token_priority":1.7e-7,"output_cost_per_token_priority":1.7e-7},"pricing_endpoint":"amazon/mistral.ministral-3-3b-instruct","regions":[{"code":"eu","name":"Europe"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"amazon/mistral.ministral-3-3b-instruct","object":"model","created":1767692616,"owned_by":"amazon","model_name":"mistral.ministral-3-3b-instruct","context_length":128000,"max_input_tokens":128000,"max_output_tokens":8000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":1e-7,"input_cost_per_token_flex":5e-8,"output_cost_per_token_flex":5e-8,"input_cost_per_token_priority":1.7e-7,"output_cost_per_token_priority":1.7e-7},"list_pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":1e-7,"input_cost_per_token_flex":5e-8,"output_cost_per_token_flex":5e-8,"input_cost_per_token_priority":1.7e-7,"output_cost_per_token_priority":1.7e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/mistral.ministral-3-3b-instruct@us","object":"model","created":1767692616,"owned_by":"amazon","model_name":"mistral.ministral-3-3b-instruct","context_length":128000,"max_input_tokens":128000,"max_output_tokens":8000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":1e-7,"input_cost_per_token_flex":5e-8,"output_cost_per_token_flex":5e-8,"input_cost_per_token_priority":1.7e-7,"output_cost_per_token_priority":1.7e-7},"list_pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":1e-7,"input_cost_per_token_flex":5e-8,"output_cost_per_token_flex":5e-8,"input_cost_per_token_priority":1.7e-7,"output_cost_per_token_priority":1.7e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"ministral-3-8b-instruct","object":"model","created":1767692616,"owned_by":"mistral","mode":"chat","context_length":128000,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":1.5e-7,"input_cost_per_token_flex":7e-8,"output_cost_per_token_flex":7e-8,"input_cost_per_token_priority":2.6e-7,"output_cost_per_token_priority":2.6e-7},"pricing_endpoint":"amazon/mistral.ministral-3-8b-instruct","regions":[{"code":"eu","name":"Europe"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"amazon/mistral.ministral-3-8b-instruct","object":"model","created":1767692616,"owned_by":"amazon","model_name":"mistral.ministral-3-8b-instruct","context_length":128000,"max_input_tokens":128000,"max_output_tokens":8000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":1.5e-7,"input_cost_per_token_flex":7e-8,"output_cost_per_token_flex":7e-8,"input_cost_per_token_priority":2.6e-7,"output_cost_per_token_priority":2.6e-7},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":1.5e-7,"input_cost_per_token_flex":7e-8,"output_cost_per_token_flex":7e-8,"input_cost_per_token_priority":2.6e-7,"output_cost_per_token_priority":2.6e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/mistral.ministral-3-8b-instruct@us","object":"model","created":1767692616,"owned_by":"amazon","model_name":"mistral.ministral-3-8b-instruct","context_length":128000,"max_input_tokens":128000,"max_output_tokens":8000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":1.5e-7,"input_cost_per_token_flex":7e-8,"output_cost_per_token_flex":7e-8,"input_cost_per_token_priority":2.6e-7,"output_cost_per_token_priority":2.6e-7},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":1.5e-7,"input_cost_per_token_flex":7e-8,"output_cost_per_token_flex":7e-8,"input_cost_per_token_priority":2.6e-7,"output_cost_per_token_priority":2.6e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"mistral-large-3-675b-instruct","object":"model","created":1767692616,"owned_by":"mistral","mode":"chat","context_length":256000,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":1.5e-6,"input_cost_per_token_flex":2.5e-7,"output_cost_per_token_flex":7.5e-7,"input_cost_per_token_priority":8.8e-7,"output_cost_per_token_priority":2.63e-6},"pricing_endpoint":"amazon/mistral.mistral-large-3-675b-instruct","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"amazon/mistral.mistral-large-3-675b-instruct","object":"model","created":1767692616,"owned_by":"amazon","model_name":"mistral.mistral-large-3-675b-instruct","context_length":256000,"max_input_tokens":256000,"max_output_tokens":32000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":1.5e-6,"input_cost_per_token_flex":2.5e-7,"output_cost_per_token_flex":7.5e-7,"input_cost_per_token_priority":8.8e-7,"output_cost_per_token_priority":2.63e-6},"list_pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":1.5e-6,"input_cost_per_token_flex":2.5e-7,"output_cost_per_token_flex":7.5e-7,"input_cost_per_token_priority":8.8e-7,"output_cost_per_token_priority":2.63e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"mistral-medium","object":"model","created":1767692616,"owned_by":"mistral","mode":"chat","context_length":262144,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-6,"output_cost_per_token":7.5e-6,"cache_read_input_token_cost":1.5e-7,"input_cost_per_token_batches":7.5e-7,"output_cost_per_token_batches":3.75e-6,"cache_read_input_token_cost_batches":7.5e-8},"pricing_endpoint":"mistral/mistral-medium","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"mistral/mistral-medium@eu","object":"model","created":1767692616,"owned_by":"mistral","model_name":"mistral-medium","context_length":262144,"max_input_tokens":262144,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.65e-6,"output_cost_per_token":8.25e-6,"cache_read_input_token_cost":1.65e-7,"input_cost_per_token_batches":8.25e-7,"output_cost_per_token_batches":4.125e-6,"cache_read_input_token_cost_batches":8.25e-8},"list_pricing":{"input_cost_per_token":1.65e-6,"output_cost_per_token":8.25e-6,"cache_read_input_token_cost":1.65e-7,"input_cost_per_token_batches":8.25e-7,"output_cost_per_token_batches":4.125e-6,"cache_read_input_token_cost_batches":8.25e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"mistral/mistral-medium","object":"model","created":1767692616,"owned_by":"mistral","model_name":"mistral-medium","context_length":262144,"max_input_tokens":262144,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-6,"output_cost_per_token":7.5e-6,"cache_read_input_token_cost":1.5e-7,"input_cost_per_token_batches":7.5e-7,"output_cost_per_token_batches":3.75e-6,"cache_read_input_token_cost_batches":7.5e-8},"list_pricing":{"input_cost_per_token":1.5e-6,"output_cost_per_token":7.5e-6,"cache_read_input_token_cost":1.5e-7,"input_cost_per_token_batches":7.5e-7,"output_cost_per_token_batches":3.75e-6,"cache_read_input_token_cost_batches":7.5e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"mistral-medium-2505","object":"model","created":1767692616,"owned_by":"mistral","mode":"chat","context_length":131072,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4e-7,"output_cost_per_token":2e-6},"pricing_endpoint":"mistral/mistral-medium-2505","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"mistral/mistral-medium-2505@eu","object":"model","created":1767692616,"owned_by":"mistral","model_name":"mistral-medium-2505","context_length":131072,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":"2026-08-31","description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4.4e-7,"output_cost_per_token":2.2e-6},"list_pricing":{"input_cost_per_token":4.4e-7,"output_cost_per_token":2.2e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"mistral/mistral-medium-2505","object":"model","created":1767692616,"owned_by":"mistral","model_name":"mistral-medium-2505","context_length":131072,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":"2026-08-31","description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4e-7,"output_cost_per_token":2e-6},"list_pricing":{"input_cost_per_token":4e-7,"output_cost_per_token":2e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"mistral-medium-latest","object":"model","created":1767692616,"owned_by":"mistral","mode":"chat","context_length":262144,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-6,"output_cost_per_token":7.5e-6,"cache_read_input_token_cost":1.5e-7,"input_cost_per_token_batches":7.5e-7,"output_cost_per_token_batches":3.75e-6,"cache_read_input_token_cost_batches":7.5e-8},"pricing_endpoint":"mistral/mistral-medium-latest","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"mistral/mistral-medium-latest@eu","object":"model","created":1767692616,"owned_by":"mistral","model_name":"mistral-medium-latest","context_length":262144,"max_input_tokens":262144,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.65e-6,"output_cost_per_token":8.25e-6,"cache_read_input_token_cost":1.65e-7,"input_cost_per_token_batches":8.25e-7,"output_cost_per_token_batches":4.125e-6,"cache_read_input_token_cost_batches":8.25e-8},"list_pricing":{"input_cost_per_token":1.65e-6,"output_cost_per_token":8.25e-6,"cache_read_input_token_cost":1.65e-7,"input_cost_per_token_batches":8.25e-7,"output_cost_per_token_batches":4.125e-6,"cache_read_input_token_cost_batches":8.25e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"mistral/mistral-medium-latest","object":"model","created":1767692616,"owned_by":"mistral","model_name":"mistral-medium-latest","context_length":262144,"max_input_tokens":262144,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-6,"output_cost_per_token":7.5e-6,"cache_read_input_token_cost":1.5e-7,"input_cost_per_token_batches":7.5e-7,"output_cost_per_token_batches":3.75e-6,"cache_read_input_token_cost_batches":7.5e-8},"list_pricing":{"input_cost_per_token":1.5e-6,"output_cost_per_token":7.5e-6,"cache_read_input_token_cost":1.5e-7,"input_cost_per_token_batches":7.5e-7,"output_cost_per_token_batches":3.75e-6,"cache_read_input_token_cost_batches":7.5e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"mistral-nemo-instruct-2407","object":"model","created":1767692616,"owned_by":"mistral","mode":"chat","context_length":131072,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.9e-8,"output_cost_per_token":3.0000000000000004e-8},"pricing_endpoint":"deepinfra/mistralai/Mistral-Nemo-Instruct-2407","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"deepinfra/mistralai/Mistral-Nemo-Instruct-2407","object":"model","created":1767692616,"owned_by":"deepinfra","model_name":"mistralai/Mistral-Nemo-Instruct-2407","context_length":131072,"max_input_tokens":131072,"max_output_tokens":null,"quantization":"fp8","retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.9e-8,"output_cost_per_token":3.0000000000000004e-8},"list_pricing":{"input_cost_per_token":2.9e-8,"output_cost_per_token":3.0000000000000004e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"mistral-small-latest","object":"model","created":1767692616,"owned_by":"mistral","mode":"chat","context_length":262144,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":1.5e-8,"input_cost_per_token_batches":7.5e-8,"output_cost_per_token_batches":3e-7,"cache_read_input_token_cost_batches":7.5e-9},"pricing_endpoint":"mistral/mistral-small-latest","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"mistral/mistral-small-latest@eu","object":"model","created":1767692616,"owned_by":"mistral","model_name":"mistral-small-latest","context_length":262144,"max_input_tokens":262144,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":"https://mistral.ai/pricing","capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.65e-7,"output_cost_per_token":6.6e-7,"cache_read_input_token_cost":1.65e-8,"input_cost_per_token_batches":8.25e-8,"output_cost_per_token_batches":3.3e-7,"cache_read_input_token_cost_batches":8.25e-9},"list_pricing":{"input_cost_per_token":1.65e-7,"output_cost_per_token":6.6e-7,"cache_read_input_token_cost":1.65e-8,"input_cost_per_token_batches":8.25e-8,"output_cost_per_token_batches":3.3e-7,"cache_read_input_token_cost_batches":8.25e-9},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"mistral/mistral-small-latest","object":"model","created":1767692616,"owned_by":"mistral","model_name":"mistral-small-latest","context_length":262144,"max_input_tokens":262144,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":null,"source":"https://mistral.ai/pricing","capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":1.5e-8,"input_cost_per_token_batches":7.5e-8,"output_cost_per_token_batches":3e-7,"cache_read_input_token_cost_batches":7.5e-9},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":1.5e-8,"input_cost_per_token_batches":7.5e-8,"output_cost_per_token_batches":3e-7,"cache_read_input_token_cost_batches":7.5e-9},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"nemotron-nano-12b-v2","object":"model","created":1767692616,"owned_by":"nvidia","mode":"chat","context_length":128000,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":6e-7,"input_cost_per_token_flex":1e-7,"output_cost_per_token_flex":3e-7,"input_cost_per_token_priority":3.5e-7,"output_cost_per_token_priority":1.05e-6},"pricing_endpoint":"amazon/nvidia.nemotron-nano-12b-v2","regions":[{"code":"eu","name":"Europe"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"amazon/nvidia.nemotron-nano-12b-v2","object":"model","created":1767692616,"owned_by":"amazon","model_name":"nvidia.nemotron-nano-12b-v2","context_length":128000,"max_input_tokens":128000,"max_output_tokens":8000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":6e-7,"input_cost_per_token_flex":1e-7,"output_cost_per_token_flex":3e-7,"input_cost_per_token_priority":3.5e-7,"output_cost_per_token_priority":1.05e-6},"list_pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":6e-7,"input_cost_per_token_flex":1e-7,"output_cost_per_token_flex":3e-7,"input_cost_per_token_priority":3.5e-7,"output_cost_per_token_priority":1.05e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/nvidia.nemotron-nano-12b-v2@us","object":"model","created":1767692616,"owned_by":"amazon","model_name":"nvidia.nemotron-nano-12b-v2","context_length":128000,"max_input_tokens":128000,"max_output_tokens":8000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":6e-7,"input_cost_per_token_flex":1e-7,"output_cost_per_token_flex":3e-7,"input_cost_per_token_priority":3.5e-7,"output_cost_per_token_priority":1.05e-6},"list_pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":6e-7,"input_cost_per_token_flex":1e-7,"output_cost_per_token_flex":3e-7,"input_cost_per_token_priority":3.5e-7,"output_cost_per_token_priority":1.05e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"nemotron-nano-9b-v2","object":"model","created":1767692616,"owned_by":"nvidia","mode":"chat","context_length":131072,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4e-8,"output_cost_per_token":1.6e-7},"pricing_endpoint":"deepinfra/nvidia/NVIDIA-Nemotron-Nano-9B-v2","regions":[{"code":"eu","name":"Europe"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"amazon/nvidia.nemotron-nano-9b-v2","object":"model","created":1767692616,"owned_by":"amazon","model_name":"nvidia.nemotron-nano-9b-v2","context_length":128000,"max_input_tokens":128000,"max_output_tokens":8000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6e-8,"output_cost_per_token":2.3e-7,"input_cost_per_token_flex":3e-8,"output_cost_per_token_flex":1.2e-7,"input_cost_per_token_priority":1.1e-7,"output_cost_per_token_priority":4e-7},"list_pricing":{"input_cost_per_token":6e-8,"output_cost_per_token":2.3e-7,"input_cost_per_token_flex":3e-8,"output_cost_per_token_flex":1.2e-7,"input_cost_per_token_priority":1.1e-7,"output_cost_per_token_priority":4e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/nvidia.nemotron-nano-9b-v2@us","object":"model","created":1767692616,"owned_by":"amazon","model_name":"nvidia.nemotron-nano-9b-v2","context_length":128000,"max_input_tokens":128000,"max_output_tokens":8000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6e-8,"output_cost_per_token":2.3e-7,"input_cost_per_token_flex":3e-8,"output_cost_per_token_flex":1.2e-7,"input_cost_per_token_priority":1.1e-7,"output_cost_per_token_priority":4e-7},"list_pricing":{"input_cost_per_token":6e-8,"output_cost_per_token":2.3e-7,"input_cost_per_token_flex":3e-8,"output_cost_per_token_flex":1.2e-7,"input_cost_per_token_priority":1.1e-7,"output_cost_per_token_priority":4e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"deepinfra/nvidia/NVIDIA-Nemotron-Nano-9B-v2","object":"model","created":1767692616,"owned_by":"deepinfra","model_name":"nvidia/NVIDIA-Nemotron-Nano-9B-v2","context_length":131072,"max_input_tokens":131072,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4e-8,"output_cost_per_token":1.6e-7},"list_pricing":{"input_cost_per_token":4e-8,"output_cost_per_token":1.6e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":3},{"id":"o1-mini","object":"model","created":1767692616,"owned_by":"openai","mode":"chat","context_length":128000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.21e-6,"output_cost_per_token":4.84e-6,"cache_read_input_token_cost":6.05e-7},"pricing_endpoint":"microsoft/o1-mini","regions":[{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"microsoft/o1-mini","object":"model","created":1767692616,"owned_by":"microsoft","model_name":"o1-mini","context_length":128000,"max_input_tokens":128000,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.21e-6,"output_cost_per_token":4.84e-6,"cache_read_input_token_cost":6.05e-7},"list_pricing":{"input_cost_per_token":1.21e-6,"output_cost_per_token":4.84e-6,"cache_read_input_token_cost":6.05e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":1},{"id":"o3-mini","object":"model","created":1767692616,"owned_by":"openai","mode":"chat","context_length":200000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.1e-6,"output_cost_per_token":4.4e-6,"cache_read_input_token_cost":5.5e-7},"pricing_endpoint":"microsoft/o3-mini","regions":[{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"microsoft/o3-mini","object":"model","created":1767692616,"owned_by":"microsoft","model_name":"o3-mini","context_length":200000,"max_input_tokens":200000,"max_output_tokens":100000,"quantization":null,"retirement_date":null,"description":"","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.1e-6,"output_cost_per_token":4.4e-6,"cache_read_input_token_cost":5.5e-7},"list_pricing":{"input_cost_per_token":1.1e-6,"output_cost_per_token":4.4e-6,"cache_read_input_token_cost":5.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":1},{"id":"open-mistral-nemo","object":"model","created":1767692616,"owned_by":"mistral","mode":"chat","context_length":131072,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":3e-7},"pricing_endpoint":"mistral/open-mistral-nemo","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"mistral/open-mistral-nemo@eu","object":"model","created":1767692616,"owned_by":"mistral","model_name":"open-mistral-nemo","context_length":131072,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":"2026-07-31","description":null,"source":"https://mistral.ai/technology/","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.3e-7,"output_cost_per_token":3.3e-7},"list_pricing":{"input_cost_per_token":3.3e-7,"output_cost_per_token":3.3e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"mistral/open-mistral-nemo","object":"model","created":1767692616,"owned_by":"mistral","model_name":"open-mistral-nemo","context_length":131072,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":"2026-07-31","description":null,"source":"https://mistral.ai/technology/","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":3e-7},"list_pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":3e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"open-mistral-nemo-2407","object":"model","created":1767692616,"owned_by":"mistral","mode":"chat","context_length":131072,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":3e-7},"pricing_endpoint":"mistral/open-mistral-nemo-2407","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"mistral/open-mistral-nemo-2407@eu","object":"model","created":1767692616,"owned_by":"mistral","model_name":"open-mistral-nemo-2407","context_length":131072,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":"2026-07-31","description":null,"source":"https://mistral.ai/technology/","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.3e-7,"output_cost_per_token":3.3e-7},"list_pricing":{"input_cost_per_token":3.3e-7,"output_cost_per_token":3.3e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"mistral/open-mistral-nemo-2407","object":"model","created":1767692616,"owned_by":"mistral","model_name":"open-mistral-nemo-2407","context_length":131072,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":"2026-07-31","description":null,"source":"https://mistral.ai/technology/","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":3e-7},"list_pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":3e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"qwen2.5-vl-32b-instruct","object":"model","created":1767692616,"owned_by":"qwen","mode":"chat","context_length":128000,"capabilities":{"input_modalities":["image","text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":6e-7},"pricing_endpoint":"deepinfra/Qwen/Qwen2.5-VL-32B-Instruct","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"deepinfra/Qwen/Qwen2.5-VL-32B-Instruct","object":"model","created":1767692616,"owned_by":"deepinfra","model_name":"Qwen/Qwen2.5-VL-32B-Instruct","context_length":128000,"max_input_tokens":128000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"","source":null,"capabilities":{"input_modalities":["image","text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":6e-7},"list_pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":6e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"qwen3-coder-30b-a3b-instruct","object":"model","created":1767692616,"owned_by":"qwen","mode":"chat","context_length":262144,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"input_cost_per_token_priority":2.625e-7,"output_cost_per_token_priority":1.05e-6},"pricing_endpoint":"amazon/qwen.qwen3-coder-30b-a3b-v1:0","regions":[{"code":"eu","name":"Europe"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"amazon/qwen.qwen3-coder-30b-a3b-v1:0","object":"model","created":1767692616,"owned_by":"amazon","model_name":"qwen.qwen3-coder-30b-a3b-v1:0","context_length":262144,"max_input_tokens":262144,"max_output_tokens":16384,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"input_cost_per_token_priority":2.625e-7,"output_cost_per_token_priority":1.05e-6},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"input_cost_per_token_priority":2.625e-7,"output_cost_per_token_priority":1.05e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/qwen.qwen3-coder-30b-a3b-v1:0@us","object":"model","created":1767692616,"owned_by":"amazon","model_name":"qwen.qwen3-coder-30b-a3b-v1:0","context_length":262144,"max_input_tokens":262144,"max_output_tokens":16384,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"input_cost_per_token_priority":2.625e-7,"output_cost_per_token_priority":1.05e-6},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"input_cost_per_token_priority":2.625e-7,"output_cost_per_token_priority":1.05e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"scaleway/qwen3-coder-30b-a3b-instruct","object":"model","created":1755006551,"owned_by":"scaleway","model_name":"qwen3-coder-30b-a3b-instruct","context_length":128000,"max_input_tokens":null,"max_output_tokens":32768,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.24499898413796e-7,"output_cost_per_token":8.97999593655184e-7},"list_pricing":{"input_cost_per_token":2.24499898413796e-7,"output_cost_per_token":8.97999593655184e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":3},{"id":"qwen3-coder-480b-a35b-instruct","object":"model","created":1767692616,"owned_by":"qwen","mode":"chat","context_length":262144,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4e-7,"output_cost_per_token":1.6e-6},"pricing_endpoint":"deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct","object":"model","created":1767692616,"owned_by":"deepinfra","model_name":"Qwen/Qwen3-Coder-480B-A35B-Instruct","context_length":262144,"max_input_tokens":262144,"max_output_tokens":262144,"quantization":null,"retirement_date":null,"description":"","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4e-7,"output_cost_per_token":1.6e-6},"list_pricing":{"input_cost_per_token":4e-7,"output_cost_per_token":1.6e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"qwen3-coder-480b-a35b-instruct-turbo","object":"model","created":1767692616,"owned_by":"qwen","mode":"chat","context_length":262144,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1e-6,"cache_read_input_token_cost":9.999999899999999e-8},"pricing_endpoint":"deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo","object":"model","created":1767692616,"owned_by":"deepinfra","model_name":"Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo","context_length":262144,"max_input_tokens":262144,"max_output_tokens":null,"quantization":"fp4","retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1e-6,"cache_read_input_token_cost":9.999999899999999e-8},"list_pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":1e-6,"cache_read_input_token_cost":9.999999899999999e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"qwen3-next-80b-a3b","object":"model","created":1767692616,"owned_by":"qwen","mode":"chat","context_length":256000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":1.2e-6,"input_cost_per_token_flex":7e-8,"output_cost_per_token_flex":6e-7,"input_cost_per_token_priority":2.6e-7,"output_cost_per_token_priority":2.1e-6},"pricing_endpoint":"amazon/qwen.qwen3-next-80b-a3b","regions":[{"code":"eu","name":"Europe"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"amazon/qwen.qwen3-next-80b-a3b","object":"model","created":1767692616,"owned_by":"amazon","model_name":"qwen.qwen3-next-80b-a3b","context_length":256000,"max_input_tokens":256000,"max_output_tokens":8000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":1.2e-6,"input_cost_per_token_flex":7e-8,"output_cost_per_token_flex":6e-7,"input_cost_per_token_priority":2.6e-7,"output_cost_per_token_priority":2.1e-6},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":1.2e-6,"input_cost_per_token_flex":7e-8,"output_cost_per_token_flex":6e-7,"input_cost_per_token_priority":2.6e-7,"output_cost_per_token_priority":2.1e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/qwen.qwen3-next-80b-a3b@us","object":"model","created":1767692616,"owned_by":"amazon","model_name":"qwen.qwen3-next-80b-a3b","context_length":256000,"max_input_tokens":256000,"max_output_tokens":8000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":1.2e-6,"input_cost_per_token_flex":7e-8,"output_cost_per_token_flex":6e-7,"input_cost_per_token_priority":2.6e-7,"output_cost_per_token_priority":2.1e-6},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":1.2e-6,"input_cost_per_token_flex":7e-8,"output_cost_per_token_flex":6e-7,"input_cost_per_token_priority":2.6e-7,"output_cost_per_token_priority":2.1e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"qwen3-vl-235b-a22b","object":"model","created":1767692616,"owned_by":"qwen","mode":"chat","context_length":256000,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5.3e-7,"output_cost_per_token":2.66e-6,"input_cost_per_token_priority":9.3e-7,"output_cost_per_token_priority":4.66e-6},"pricing_endpoint":"amazon/qwen.qwen3-vl-235b-a22b","regions":[{"code":"eu","name":"Europe"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"amazon/qwen.qwen3-vl-235b-a22b","object":"model","created":1767692616,"owned_by":"amazon","model_name":"qwen.qwen3-vl-235b-a22b","context_length":256000,"max_input_tokens":256000,"max_output_tokens":8000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5.3e-7,"output_cost_per_token":2.66e-6,"input_cost_per_token_priority":9.3e-7,"output_cost_per_token_priority":4.66e-6},"list_pricing":{"input_cost_per_token":5.3e-7,"output_cost_per_token":2.66e-6,"input_cost_per_token_priority":9.3e-7,"output_cost_per_token_priority":4.66e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/qwen.qwen3-vl-235b-a22b@us","object":"model","created":1767692616,"owned_by":"amazon","model_name":"qwen.qwen3-vl-235b-a22b","context_length":256000,"max_input_tokens":256000,"max_output_tokens":8000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5.3e-7,"output_cost_per_token":2.66e-6,"input_cost_per_token_priority":9.3e-7,"output_cost_per_token_priority":4.66e-6},"list_pricing":{"input_cost_per_token":5.3e-7,"output_cost_per_token":2.66e-6,"input_cost_per_token_priority":9.3e-7,"output_cost_per_token_priority":4.66e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"voxtral-mini-3b-2507","object":"model","created":1767692616,"owned_by":"mistral","mode":"chat","context_length":32768,"capabilities":{"input_modalities":["text","audio"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4e-8,"output_cost_per_token":4e-8,"input_cost_per_token_flex":2e-8,"output_cost_per_token_flex":2e-8,"input_cost_per_token_priority":7e-8,"output_cost_per_token_priority":7e-8},"pricing_endpoint":"amazon/mistral.voxtral-mini-3b-2507","regions":[{"code":"eu","name":"Europe"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"amazon/mistral.voxtral-mini-3b-2507","object":"model","created":1767692616,"owned_by":"amazon","model_name":"mistral.voxtral-mini-3b-2507","context_length":32768,"max_input_tokens":32768,"max_output_tokens":8192,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","audio"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4e-8,"output_cost_per_token":4e-8,"input_cost_per_token_flex":2e-8,"output_cost_per_token_flex":2e-8,"input_cost_per_token_priority":7e-8,"output_cost_per_token_priority":7e-8},"list_pricing":{"input_cost_per_token":4e-8,"output_cost_per_token":4e-8,"input_cost_per_token_flex":2e-8,"output_cost_per_token_flex":2e-8,"input_cost_per_token_priority":7e-8,"output_cost_per_token_priority":7e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/mistral.voxtral-mini-3b-2507@us","object":"model","created":1767692616,"owned_by":"amazon","model_name":"mistral.voxtral-mini-3b-2507","context_length":32768,"max_input_tokens":32768,"max_output_tokens":8192,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","audio"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4e-8,"output_cost_per_token":4e-8,"input_cost_per_token_flex":2e-8,"output_cost_per_token_flex":2e-8,"input_cost_per_token_priority":7e-8,"output_cost_per_token_priority":7e-8},"list_pricing":{"input_cost_per_token":4e-8,"output_cost_per_token":4e-8,"input_cost_per_token_flex":2e-8,"output_cost_per_token_flex":2e-8,"input_cost_per_token_priority":7e-8,"output_cost_per_token_priority":7e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"voxtral-small-24b-2507","object":"model","created":1767692616,"owned_by":"mistral","mode":"chat","context_length":32768,"capabilities":{"input_modalities":["text","audio"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":3e-7,"input_cost_per_token_flex":5e-8,"output_cost_per_token_flex":1.5e-7,"input_cost_per_token_priority":1.7e-7,"output_cost_per_token_priority":5.2e-7},"pricing_endpoint":"amazon/mistral.voxtral-small-24b-2507","regions":[{"code":"eu","name":"Europe"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"amazon/mistral.voxtral-small-24b-2507","object":"model","created":1767692616,"owned_by":"amazon","model_name":"mistral.voxtral-small-24b-2507","context_length":32768,"max_input_tokens":32768,"max_output_tokens":26214,"quantization":null,"retirement_date":null,"description":"Voxtral Small is an enhancement of Mistral Small 3, incorporating state-of-the-art audio input capabilities while retaining best-in-class text performance. It excels at speech transcription, translation and audio understanding.","source":null,"capabilities":{"input_modalities":["text","audio"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":3e-7,"input_cost_per_token_flex":5e-8,"output_cost_per_token_flex":1.5e-7,"input_cost_per_token_priority":1.7e-7,"output_cost_per_token_priority":5.2e-7},"list_pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":3e-7,"input_cost_per_token_flex":5e-8,"output_cost_per_token_flex":1.5e-7,"input_cost_per_token_priority":1.7e-7,"output_cost_per_token_priority":5.2e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/mistral.voxtral-small-24b-2507@us","object":"model","created":1767692616,"owned_by":"amazon","model_name":"mistral.voxtral-small-24b-2507","context_length":32768,"max_input_tokens":32768,"max_output_tokens":26214,"quantization":null,"retirement_date":null,"description":"Voxtral Small is an enhancement of Mistral Small 3, incorporating state-of-the-art audio input capabilities while retaining best-in-class text performance. It excels at speech transcription, translation and audio understanding.","source":null,"capabilities":{"input_modalities":["text","audio"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":true,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":3e-7,"input_cost_per_token_flex":5e-8,"output_cost_per_token_flex":1.5e-7,"input_cost_per_token_priority":1.7e-7,"output_cost_per_token_priority":5.2e-7},"list_pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":3e-7,"input_cost_per_token_flex":5e-8,"output_cost_per_token_flex":1.5e-7,"input_cost_per_token_priority":1.7e-7,"output_cost_per_token_priority":5.2e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"gemini-3-flash-preview","object":"model","created":1765987078,"owned_by":"google","mode":"chat","context_length":1048576,"capabilities":{"input_modalities":["text","image","file","audio","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":3e-6,"input_cost_per_token_flex":2.5e-7,"input_cost_per_audio_token":1e-6,"input_cost_per_image_token":5e-7,"output_cost_per_token_flex":1.5e-6,"cache_read_input_token_cost":5e-8,"input_cost_per_token_priority":9e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":5.4e-6,"cache_creation_input_token_cost":8.33333333333333e-8,"input_cost_per_audio_token_flex":5e-7,"output_cost_per_reasoning_token":3e-6,"cache_read_input_token_cost_flex":5e-8,"cache_read_input_audio_token_cost":1e-7,"input_cost_per_audio_token_priority":1.8e-6,"cache_read_input_token_cost_priority":9e-8,"google_maps_grounding_cost_per_query":0.014,"cache_read_input_audio_token_cost_flex":1e-7,"cache_read_input_audio_token_cost_priority":1.8e-7},"pricing_endpoint":"google/gemini-3-flash-preview","regions":[{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"google/gemini-3-flash-preview","object":"model","created":1765987078,"owned_by":"google","model_name":"gemini-3-flash-preview","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance.","source":"https://cloud.google.com/vertex-ai/generative-ai/pricing","capabilities":{"input_modalities":["text","image","file","audio","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":3e-6,"input_cost_per_token_flex":2.5e-7,"input_cost_per_audio_token":1e-6,"input_cost_per_image_token":5e-7,"output_cost_per_token_flex":1.5e-6,"cache_read_input_token_cost":5e-8,"input_cost_per_token_priority":9e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":5.4e-6,"cache_creation_input_token_cost":8.33333333333333e-8,"input_cost_per_audio_token_flex":5e-7,"output_cost_per_reasoning_token":3e-6,"cache_read_input_token_cost_flex":5e-8,"cache_read_input_audio_token_cost":1e-7,"input_cost_per_audio_token_priority":1.8e-6,"cache_read_input_token_cost_priority":9e-8,"google_maps_grounding_cost_per_query":0.014,"cache_read_input_audio_token_cost_flex":1e-7,"cache_read_input_audio_token_cost_priority":1.8e-7},"list_pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":3e-6,"input_cost_per_token_flex":2.5e-7,"input_cost_per_audio_token":1e-6,"input_cost_per_image_token":5e-7,"output_cost_per_token_flex":1.5e-6,"cache_read_input_token_cost":5e-8,"input_cost_per_token_priority":9e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":5.4e-6,"cache_creation_input_token_cost":8.33333333333333e-8,"input_cost_per_audio_token_flex":5e-7,"output_cost_per_reasoning_token":3e-6,"cache_read_input_token_cost_flex":5e-8,"cache_read_input_audio_token_cost":1e-7,"input_cost_per_audio_token_priority":1.8e-6,"cache_read_input_token_cost_priority":9e-8,"google_maps_grounding_cost_per_query":0.014,"cache_read_input_audio_token_cost_flex":1e-7,"cache_read_input_audio_token_cost_priority":1.8e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"vertex/gemini-3-flash-preview","object":"model","created":1765987078,"owned_by":"vertex","model_name":"gemini-3-flash-preview","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance.","source":null,"capabilities":{"input_modalities":["text","image","file","audio","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":true,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":3e-6,"input_cost_per_token_flex":2.5e-7,"input_cost_per_audio_token":1e-6,"input_cost_per_image_token":5e-7,"output_cost_per_token_flex":1.5e-6,"cache_read_input_token_cost":5e-8,"input_cost_per_token_priority":9e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":5.4e-6,"cache_creation_input_token_cost":8.33333333333333e-8,"input_cost_per_audio_token_flex":5e-7,"output_cost_per_reasoning_token":3e-6,"cache_read_input_audio_token_cost":1e-7,"input_cost_per_audio_token_priority":1.8e-6,"cache_read_input_token_cost_priority":9e-8,"google_maps_grounding_cost_per_query":0.014,"cache_read_input_audio_token_cost_priority":1.8e-7,"input_cost_per_audio_token_above_200k_tokens":1e-6,"input_cost_per_audio_token_above_200k_tokens_flex":5e-7,"input_cost_per_audio_token_above_200k_tokens_priority":1.8e-6},"list_pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":3e-6,"input_cost_per_token_flex":2.5e-7,"input_cost_per_audio_token":1e-6,"input_cost_per_image_token":5e-7,"output_cost_per_token_flex":1.5e-6,"cache_read_input_token_cost":5e-8,"input_cost_per_token_priority":9e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":5.4e-6,"cache_creation_input_token_cost":8.33333333333333e-8,"input_cost_per_audio_token_flex":5e-7,"output_cost_per_reasoning_token":3e-6,"cache_read_input_audio_token_cost":1e-7,"input_cost_per_audio_token_priority":1.8e-6,"cache_read_input_token_cost_priority":9e-8,"google_maps_grounding_cost_per_query":0.014,"cache_read_input_audio_token_cost_priority":1.8e-7,"input_cost_per_audio_token_above_200k_tokens":1e-6,"input_cost_per_audio_token_above_200k_tokens_flex":5e-7,"input_cost_per_audio_token_above_200k_tokens_priority":1.8e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"gpt-5.2-pro","object":"model","created":1765389780,"owned_by":"openai","mode":"chat","context_length":400000,"capabilities":{"input_modalities":["image","text","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":0.000021,"output_cost_per_token":0.000168,"input_cost_per_token_batches":0.0000105,"output_cost_per_token_batches":0.000084,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01}},"pricing_endpoint":"openai/gpt-5.2-pro","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"openai/gpt-5.2-pro","object":"model","created":1765389780,"owned_by":"openai","model_name":"gpt-5.2-pro","context_length":400000,"max_input_tokens":272000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5.2 Pro is OpenAI’s most advanced model, offering major improvements in agentic coding and long context performance over GPT-5 Pro.","source":null,"capabilities":{"input_modalities":["image","text","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":0.000021,"output_cost_per_token":0.000168,"input_cost_per_token_batches":0.0000105,"output_cost_per_token_batches":0.000084,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01}},"list_pricing":{"input_cost_per_token":0.000021,"output_cost_per_token":0.000168,"input_cost_per_token_batches":0.0000105,"output_cost_per_token_batches":0.000084,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01}},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":1},{"id":"gpt-5.2-pro-2025-12-11","object":"model","created":1765389780,"owned_by":"openai","mode":"chat","context_length":400000,"capabilities":{"input_modalities":["image","text","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":0.000021,"output_cost_per_token":0.000168,"input_cost_per_token_batches":0.0000105,"output_cost_per_token_batches":0.000084,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01}},"pricing_endpoint":"openai/gpt-5.2-pro-2025-12-11","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"openai/gpt-5.2-pro-2025-12-11","object":"model","created":1765389780,"owned_by":"openai","model_name":"gpt-5.2-pro-2025-12-11","context_length":400000,"max_input_tokens":272000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5.2 Pro is OpenAI’s most advanced model, offering major improvements in agentic coding and long context performance over GPT-5 Pro.","source":null,"capabilities":{"input_modalities":["image","text","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":0.000021,"output_cost_per_token":0.000168,"input_cost_per_token_batches":0.0000105,"output_cost_per_token_batches":0.000084,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01}},"list_pricing":{"input_cost_per_token":0.000021,"output_cost_per_token":0.000168,"input_cost_per_token_batches":0.0000105,"output_cost_per_token_batches":0.000084,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01}},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":1},{"id":"gpt-5.2-2025-12-11","object":"model","created":1765389775,"owned_by":"openai","mode":"chat","context_length":400000,"capabilities":{"input_modalities":["file","image","text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.75e-6,"output_cost_per_token":0.000014,"input_cost_per_token_flex":8.75e-7,"output_cost_per_token_flex":7e-6,"cache_read_input_token_cost":1.75e-7,"input_cost_per_token_batches":8.75e-7,"input_cost_per_token_priority":3.5e-6,"output_cost_per_token_batches":7e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"output_cost_per_token_priority":0.000028,"cache_read_input_token_cost_flex":8.75e-8,"cache_read_input_token_cost_batches":8.75e-8,"cache_read_input_token_cost_priority":3.5e-7},"pricing_endpoint":"openai/gpt-5.2-2025-12-11","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"openai/gpt-5.2-2025-12-11","object":"model","created":1765389775,"owned_by":"openai","model_name":"gpt-5.2-2025-12-11","context_length":400000,"max_input_tokens":272000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5.2 is the latest frontier-grade model in the GPT-5 series, offering stronger agentic and long context perfomance compared to GPT-5.1.","source":null,"capabilities":{"input_modalities":["file","image","text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.75e-6,"output_cost_per_token":0.000014,"input_cost_per_token_flex":8.75e-7,"output_cost_per_token_flex":7e-6,"cache_read_input_token_cost":1.75e-7,"input_cost_per_token_batches":8.75e-7,"input_cost_per_token_priority":3.5e-6,"output_cost_per_token_batches":7e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"output_cost_per_token_priority":0.000028,"cache_read_input_token_cost_flex":8.75e-8,"cache_read_input_token_cost_batches":8.75e-8,"cache_read_input_token_cost_priority":3.5e-7},"list_pricing":{"input_cost_per_token":1.75e-6,"output_cost_per_token":0.000014,"input_cost_per_token_flex":8.75e-7,"output_cost_per_token_flex":7e-6,"cache_read_input_token_cost":1.75e-7,"input_cost_per_token_batches":8.75e-7,"input_cost_per_token_priority":3.5e-6,"output_cost_per_token_batches":7e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"output_cost_per_token_priority":0.000028,"cache_read_input_token_cost_flex":8.75e-8,"cache_read_input_token_cost_batches":8.75e-8,"cache_read_input_token_cost_priority":3.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":1},{"id":"devstral-2512","object":"model","created":1765285419,"owned_by":"mistral","mode":"chat","context_length":262144,"capabilities":{"input_modalities":["text","file"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4e-7,"output_cost_per_token":2e-6,"cache_read_input_token_cost":4e-8},"pricing_endpoint":"mistral/devstral-2512","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"mistral/devstral-2512@eu","object":"model","created":1765285419,"owned_by":"mistral","model_name":"devstral-2512","context_length":262144,"max_input_tokens":null,"max_output_tokens":209715,"quantization":null,"retirement_date":"2026-08-31","description":"Devstral 2 is a state-of-the-art open-source model by Mistral AI specializing in agentic coding. It is a 123B-parameter dense transformer model supporting a 256K context window.","source":"https://mistral.ai/news/devstral-2-vibe-cli","capabilities":{"input_modalities":["text","file"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4.4e-7,"output_cost_per_token":2.2e-6,"cache_read_input_token_cost":4.4000000000000004e-8},"list_pricing":{"input_cost_per_token":4.4e-7,"output_cost_per_token":2.2e-6,"cache_read_input_token_cost":4.4000000000000004e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"mistral/devstral-2512","object":"model","created":1765285419,"owned_by":"mistral","model_name":"devstral-2512","context_length":262144,"max_input_tokens":null,"max_output_tokens":209715,"quantization":null,"retirement_date":"2026-08-31","description":"Devstral 2 is a state-of-the-art open-source model by Mistral AI specializing in agentic coding. It is a 123B-parameter dense transformer model supporting a 256K context window.","source":"https://mistral.ai/news/devstral-2-vibe-cli","capabilities":{"input_modalities":["text","file"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4e-7,"output_cost_per_token":2e-6,"cache_read_input_token_cost":4e-8},"list_pricing":{"input_cost_per_token":4e-7,"output_cost_per_token":2e-6,"cache_read_input_token_cost":4e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"glm-4.6v","object":"model","created":1765207462,"owned_by":"zai","mode":"chat","context_length":131072,"capabilities":{"input_modalities":["image","text","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":9e-7,"cache_read_input_token_cost":5e-8},"pricing_endpoint":"zai/glm-4.6v","regions":[{"code":"ap","name":"Asia"}],"alias_of":null,"endpoints":[{"id":"zai/glm-4.6v","object":"model","created":1765207462,"owned_by":"zai","model_name":"glm-4.6v","context_length":131072,"max_input_tokens":null,"max_output_tokens":32768,"quantization":"fp8","retirement_date":null,"description":"GLM-4.6V is a large multimodal model designed for high-fidelity visual understanding and long-context reasoning across images, documents, and mixed media.","source":null,"capabilities":{"input_modalities":["image","text","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":9e-7,"cache_read_input_token_cost":5e-8},"list_pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":9e-7,"cache_read_input_token_cost":5e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"ap","name":"Asia"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"nova-2-lite","object":"model","created":1764696672,"owned_by":"amazon","mode":"chat","context_length":1000000,"capabilities":{"input_modalities":["text","image","video","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":2.5e-6,"cache_read_input_token_cost":7.5e-8,"input_cost_per_token_priority":5.25e-7,"output_cost_per_token_priority":4.375e-6,"cache_read_input_token_cost_priority":1.3125e-7},"pricing_endpoint":"amazon/amazon.nova-2-lite-v1:0","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"amazon/amazon.nova-2-lite-v1:0@eu","object":"model","created":1764696672,"owned_by":"amazon","model_name":"amazon.nova-2-lite-v1:0","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":65535,"quantization":null,"retirement_date":null,"description":"Nova 2 Lite is a fast, cost-effective reasoning model for everyday workloads that can process text, images, and videos to generate text.","source":null,"capabilities":{"input_modalities":["text","image","video","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":2.5e-6,"cache_read_input_token_cost":7.5e-8,"input_cost_per_token_priority":5.25e-7,"output_cost_per_token_priority":4.375e-6,"cache_read_input_token_cost_priority":1.3125e-7},"list_pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":2.5e-6,"cache_read_input_token_cost":7.5e-8,"input_cost_per_token_priority":5.25e-7,"output_cost_per_token_priority":4.375e-6,"cache_read_input_token_cost_priority":1.3125e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/amazon.nova-2-lite-v1:0","object":"model","created":1764696672,"owned_by":"amazon","model_name":"amazon.nova-2-lite-v1:0","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":65535,"quantization":null,"retirement_date":null,"description":"Nova 2 Lite is a fast, cost-effective reasoning model for everyday workloads that can process text, images, and videos to generate text.","source":null,"capabilities":{"input_modalities":["text","image","video","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":2.5e-6,"cache_read_input_token_cost":7.5e-8,"input_cost_per_token_priority":5.25e-7,"output_cost_per_token_priority":4.375e-6,"cache_read_input_token_cost_priority":1.3125e-7},"list_pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":2.5e-6,"cache_read_input_token_cost":7.5e-8,"input_cost_per_token_priority":5.25e-7,"output_cost_per_token_priority":4.375e-6,"cache_read_input_token_cost_priority":1.3125e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/amazon.nova-2-lite-v1:0@us","object":"model","created":1764696672,"owned_by":"amazon","model_name":"amazon.nova-2-lite-v1:0","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":65535,"quantization":null,"retirement_date":null,"description":"Nova 2 Lite is a fast, cost-effective reasoning model for everyday workloads that can process text, images, and videos to generate text.","source":null,"capabilities":{"input_modalities":["text","image","video","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":2.5e-6,"cache_read_input_token_cost":7.5e-8,"input_cost_per_token_priority":5.25e-7,"output_cost_per_token_priority":4.375e-6,"cache_read_input_token_cost_priority":1.3125e-7},"list_pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":2.5e-6,"cache_read_input_token_cost":7.5e-8,"input_cost_per_token_priority":5.25e-7,"output_cost_per_token_priority":4.375e-6,"cache_read_input_token_cost_priority":1.3125e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":3},{"id":"ministral-14b-2512","object":"model","created":1764681735,"owned_by":"mistral","mode":"chat","context_length":262144,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":2e-7,"cache_read_input_token_cost":2e-8,"input_cost_per_token_batches":1e-7,"output_cost_per_token_batches":1e-7,"cache_read_input_token_cost_batches":1e-8},"pricing_endpoint":"mistral/ministral-14b-2512","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"mistral/ministral-14b-2512@eu","object":"model","created":1764681735,"owned_by":"mistral","model_name":"ministral-14b-2512","context_length":262144,"max_input_tokens":262144,"max_output_tokens":209715,"quantization":null,"retirement_date":null,"description":"The largest model in the Ministral 3 family, Ministral 3 14B offers frontier capabilities and performance comparable to its larger Mistral Small 3.2 24B counterpart.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.2e-7,"output_cost_per_token":2.2e-7,"cache_read_input_token_cost":2.2000000000000002e-8,"input_cost_per_token_batches":1.1e-7,"output_cost_per_token_batches":1.1e-7,"cache_read_input_token_cost_batches":1.1000000000000001e-8},"list_pricing":{"input_cost_per_token":2.2e-7,"output_cost_per_token":2.2e-7,"cache_read_input_token_cost":2.2000000000000002e-8,"input_cost_per_token_batches":1.1e-7,"output_cost_per_token_batches":1.1e-7,"cache_read_input_token_cost_batches":1.1000000000000001e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"mistral/ministral-14b-2512","object":"model","created":1764681735,"owned_by":"mistral","model_name":"ministral-14b-2512","context_length":262144,"max_input_tokens":262144,"max_output_tokens":209715,"quantization":null,"retirement_date":null,"description":"The largest model in the Ministral 3 family, Ministral 3 14B offers frontier capabilities and performance comparable to its larger Mistral Small 3.2 24B counterpart.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":2e-7,"cache_read_input_token_cost":2e-8,"input_cost_per_token_batches":1e-7,"output_cost_per_token_batches":1e-7,"cache_read_input_token_cost_batches":1e-8},"list_pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":2e-7,"cache_read_input_token_cost":2e-8,"input_cost_per_token_batches":1e-7,"output_cost_per_token_batches":1e-7,"cache_read_input_token_cost_batches":1e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"ministral-8b-2512","object":"model","created":1764681654,"owned_by":"mistral","mode":"chat","context_length":262144,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":1.5e-7,"cache_read_input_token_cost":1.5e-8,"input_cost_per_token_batches":7.5e-8,"output_cost_per_token_batches":7.5e-8,"cache_read_input_token_cost_batches":7.5e-9},"pricing_endpoint":"mistral/ministral-8b-2512","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"mistral/ministral-8b-2512@eu","object":"model","created":1764681654,"owned_by":"mistral","model_name":"ministral-8b-2512","context_length":262144,"max_input_tokens":262144,"max_output_tokens":209715,"quantization":null,"retirement_date":null,"description":"A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.","source":"https://mistral.ai/pricing","capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.65e-7,"output_cost_per_token":1.65e-7,"cache_read_input_token_cost":1.65e-8,"input_cost_per_token_batches":8.25e-8,"output_cost_per_token_batches":8.25e-8,"cache_read_input_token_cost_batches":8.25e-9},"list_pricing":{"input_cost_per_token":1.65e-7,"output_cost_per_token":1.65e-7,"cache_read_input_token_cost":1.65e-8,"input_cost_per_token_batches":8.25e-8,"output_cost_per_token_batches":8.25e-8,"cache_read_input_token_cost_batches":8.25e-9},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"mistral/ministral-8b-2512","object":"model","created":1764681654,"owned_by":"mistral","model_name":"ministral-8b-2512","context_length":262144,"max_input_tokens":262144,"max_output_tokens":209715,"quantization":null,"retirement_date":null,"description":"A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.","source":"https://mistral.ai/pricing","capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":1.5e-7,"cache_read_input_token_cost":1.5e-8,"input_cost_per_token_batches":7.5e-8,"output_cost_per_token_batches":7.5e-8,"cache_read_input_token_cost_batches":7.5e-9},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":1.5e-7,"cache_read_input_token_cost":1.5e-8,"input_cost_per_token_batches":7.5e-8,"output_cost_per_token_batches":7.5e-8,"cache_read_input_token_cost_batches":7.5e-9},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"ministral-3b-2512","object":"model","created":1764681560,"owned_by":"mistral","mode":"chat","context_length":131072,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":1e-7,"cache_read_input_token_cost":1e-8,"input_cost_per_token_batches":5e-8,"output_cost_per_token_batches":5e-8,"cache_read_input_token_cost_batches":5e-9},"pricing_endpoint":"mistral/ministral-3b-2512","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"mistral/ministral-3b-2512@eu","object":"model","created":1764681560,"owned_by":"mistral","model_name":"ministral-3b-2512","context_length":131072,"max_input_tokens":131072,"max_output_tokens":104857,"quantization":null,"retirement_date":null,"description":"The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.1e-7,"output_cost_per_token":1.1e-7,"cache_read_input_token_cost":1.1000000000000001e-8,"input_cost_per_token_batches":5.5e-8,"output_cost_per_token_batches":5.5e-8,"cache_read_input_token_cost_batches":5.5000000000000004e-9},"list_pricing":{"input_cost_per_token":1.1e-7,"output_cost_per_token":1.1e-7,"cache_read_input_token_cost":1.1000000000000001e-8,"input_cost_per_token_batches":5.5e-8,"output_cost_per_token_batches":5.5e-8,"cache_read_input_token_cost_batches":5.5000000000000004e-9},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"mistral/ministral-3b-2512","object":"model","created":1764681560,"owned_by":"mistral","model_name":"ministral-3b-2512","context_length":131072,"max_input_tokens":131072,"max_output_tokens":104857,"quantization":null,"retirement_date":null,"description":"The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":1e-7,"cache_read_input_token_cost":1e-8,"input_cost_per_token_batches":5e-8,"output_cost_per_token_batches":5e-8,"cache_read_input_token_cost_batches":5e-9},"list_pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":1e-7,"cache_read_input_token_cost":1e-8,"input_cost_per_token_batches":5e-8,"output_cost_per_token_batches":5e-8,"cache_read_input_token_cost_batches":5e-9},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"mistral-large-2512","object":"model","created":1764624472,"owned_by":"mistral","mode":"chat","context_length":262144,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":1.5e-6,"cache_read_input_token_cost":5e-8,"input_cost_per_token_batches":2.5e-7,"output_cost_per_token_batches":7.5e-7,"cache_read_input_token_cost_batches":2.5e-8},"pricing_endpoint":"mistral/mistral-large-2512","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"mistral/mistral-large-2512@eu","object":"model","created":1764624472,"owned_by":"mistral","model_name":"mistral-large-2512","context_length":262144,"max_input_tokens":262144,"max_output_tokens":209715,"quantization":null,"retirement_date":null,"description":"Mistral Large 3 2512 is Mistral’s most capable model to date, featuring a sparse mixture-of-experts architecture with 41B active parameters (675B total), and released under the Apache 2.0 license.","source":"https://docs.mistral.ai/models/mistral-large-3-25-12","capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5.5e-7,"output_cost_per_token":1.65e-6,"cache_read_input_token_cost":5.5e-8,"input_cost_per_token_batches":2.75e-7,"output_cost_per_token_batches":8.25e-7,"cache_read_input_token_cost_batches":2.75e-8},"list_pricing":{"input_cost_per_token":5.5e-7,"output_cost_per_token":1.65e-6,"cache_read_input_token_cost":5.5e-8,"input_cost_per_token_batches":2.75e-7,"output_cost_per_token_batches":8.25e-7,"cache_read_input_token_cost_batches":2.75e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"mistral/mistral-large-2512","object":"model","created":1764624472,"owned_by":"mistral","model_name":"mistral-large-2512","context_length":262144,"max_input_tokens":262144,"max_output_tokens":209715,"quantization":null,"retirement_date":null,"description":"Mistral Large 3 2512 is Mistral’s most capable model to date, featuring a sparse mixture-of-experts architecture with 41B active parameters (675B total), and released under the Apache 2.0 license.","source":"https://docs.mistral.ai/models/mistral-large-3-25-12","capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":1.5e-6,"cache_read_input_token_cost":5e-8,"input_cost_per_token_batches":2.5e-7,"output_cost_per_token_batches":7.5e-7,"cache_read_input_token_cost_batches":2.5e-8},"list_pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":1.5e-6,"cache_read_input_token_cost":5e-8,"input_cost_per_token_batches":2.5e-7,"output_cost_per_token_batches":7.5e-7,"cache_read_input_token_cost_batches":2.5e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"gemini-3-pro-image-preview","object":"model","created":1763653797,"owned_by":"google","mode":"chat","context_length":65536,"capabilities":{"input_modalities":["image","text"],"output_modalities":["image","text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":false,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"supports_service_tier":true},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.000012,"input_cost_per_audio_token":2e-6,"input_cost_per_image_token":2e-6,"cache_read_input_token_cost":2e-7,"output_cost_per_image_token":0.00012,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"cache_creation_input_token_cost":3.75e-7,"output_cost_per_reasoning_token":0.000012,"cache_read_input_audio_token_cost":2e-7},"pricing_endpoint":"google/gemini-3-pro-image-preview","regions":[{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"google/gemini-3-pro-image-preview","object":"model","created":1763653797,"owned_by":"google","model_name":"gemini-3-pro-image-preview","context_length":65536,"max_input_tokens":65536,"max_output_tokens":32768,"quantization":null,"retirement_date":null,"description":"Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro.","source":"https://ai.google.dev/gemini-api/docs/pricing","capabilities":{"input_modalities":["image","text"],"output_modalities":["image","text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":false,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"supports_service_tier":true},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.000012,"input_cost_per_audio_token":2e-6,"input_cost_per_image_token":2e-6,"cache_read_input_token_cost":2e-7,"output_cost_per_image_token":0.00012,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"cache_creation_input_token_cost":3.75e-7,"output_cost_per_reasoning_token":0.000012,"cache_read_input_audio_token_cost":2e-7},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":0.000012,"input_cost_per_audio_token":2e-6,"input_cost_per_image_token":2e-6,"cache_read_input_token_cost":2e-7,"output_cost_per_image_token":0.00012,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"cache_creation_input_token_cost":3.75e-7,"output_cost_per_reasoning_token":0.000012,"cache_read_input_audio_token_cost":2e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":1},{"id":"grok-4-1-fast","object":"model","created":1763587502,"owned_by":"xai","mode":"chat","context_length":2000000,"capabilities":{"input_modalities":["audio","image","text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":5e-8,"input_cost_per_token_above_128k_tokens":4e-7,"output_cost_per_token_above_128k_tokens":1e-6},"pricing_endpoint":"xai/grok-4-1-fast","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"xai/grok-4-1-fast","object":"model","created":1763587502,"owned_by":"xai","model_name":"grok-4-1-fast","context_length":2000000,"max_input_tokens":2000000,"max_output_tokens":2000000,"quantization":null,"retirement_date":null,"description":"Grok 4.1 Fast is xAI's best agentic tool calling model that shines in real-world use cases like customer support and deep research. 2M context window. Reasoning can be enabled/disabled using...","source":"https://docs.x.ai/docs/models/grok-4-1-fast-reasoning","capabilities":{"input_modalities":["audio","image","text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":5e-8,"input_cost_per_token_above_128k_tokens":4e-7,"output_cost_per_token_above_128k_tokens":1e-6},"list_pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":5e-8,"input_cost_per_token_above_128k_tokens":4e-7,"output_cost_per_token_above_128k_tokens":1e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"gpt-5.1-2025-11-13","object":"model","created":1763060305,"owned_by":"openai","mode":"chat","context_length":400000,"capabilities":{"input_modalities":["image","text","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":0.00001,"input_cost_per_token_flex":6.25e-7,"output_cost_per_token_flex":5e-6,"cache_read_input_token_cost":1.25e-7,"input_cost_per_token_batches":6.25e-7,"input_cost_per_token_priority":2.5e-6,"output_cost_per_token_batches":5e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"output_cost_per_token_priority":0.00002,"cache_read_input_token_cost_flex":6.25e-8,"cache_read_input_token_cost_batches":6.25e-8,"cache_read_input_token_cost_priority":2.5e-7},"pricing_endpoint":"openai/gpt-5.1-2025-11-13","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"openai/gpt-5.1-2025-11-13","object":"model","created":1763060305,"owned_by":"openai","model_name":"gpt-5.1-2025-11-13","context_length":400000,"max_input_tokens":272000,"max_output_tokens":128000,"quantization":null,"retirement_date":null,"description":"GPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adherence, and a more natural conversational style compared to GPT-5.","source":null,"capabilities":{"input_modalities":["image","text","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":0.00001,"input_cost_per_token_flex":6.25e-7,"output_cost_per_token_flex":5e-6,"cache_read_input_token_cost":1.25e-7,"input_cost_per_token_batches":6.25e-7,"input_cost_per_token_priority":2.5e-6,"output_cost_per_token_batches":5e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"output_cost_per_token_priority":0.00002,"cache_read_input_token_cost_flex":6.25e-8,"cache_read_input_token_cost_batches":6.25e-8,"cache_read_input_token_cost_priority":2.5e-7},"list_pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":0.00001,"input_cost_per_token_flex":6.25e-7,"output_cost_per_token_flex":5e-6,"cache_read_input_token_cost":1.25e-7,"input_cost_per_token_batches":6.25e-7,"input_cost_per_token_priority":2.5e-6,"output_cost_per_token_batches":5e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"output_cost_per_token_priority":0.00002,"cache_read_input_token_cost_flex":6.25e-8,"cache_read_input_token_cost_batches":6.25e-8,"cache_read_input_token_cost_priority":2.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":1},{"id":"granite-4.0-h-micro","object":"model","created":1760927695,"owned_by":"ibm","mode":"chat","context_length":131000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.7e-8,"output_cost_per_token":1.12e-7},"pricing_endpoint":"cloudflare/@cf/ibm-granite/granite-4.0-h-micro","regions":[{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"cloudflare/@cf/ibm-granite/granite-4.0-h-micro","object":"model","created":1760927695,"owned_by":"cloudflare","model_name":"@cf/ibm-granite/granite-4.0-h-micro","context_length":131000,"max_input_tokens":131000,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"Granite-4.0-H-Micro is a 3B parameter from the Granite 4 family of models. These models are the latest in a series of models released by IBM.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.7e-8,"output_cost_per_token":1.12e-7},"list_pricing":{"input_cost_per_token":1.7e-8,"output_cost_per_token":1.12e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"o3-deep-research","object":"model","created":1760129661,"owned_by":"openai","mode":"chat","context_length":200000,"capabilities":{"input_modalities":["image","text","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":0.00001,"output_cost_per_token":0.00004,"cache_read_input_token_cost":2.5e-6},"pricing_endpoint":"openai/o3-deep-research","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"openai/o3-deep-research","object":"model","created":1760129661,"owned_by":"openai","model_name":"o3-deep-research","context_length":200000,"max_input_tokens":null,"max_output_tokens":100000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["image","text","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":0.00001,"output_cost_per_token":0.00004,"cache_read_input_token_cost":2.5e-6},"list_pricing":{"input_cost_per_token":0.00001,"output_cost_per_token":0.00004,"cache_read_input_token_cost":2.5e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":1},{"id":"o3-deep-research-2025-06-26","object":"model","created":1760129661,"owned_by":"openai","mode":"chat","context_length":200000,"capabilities":{"input_modalities":["image","text","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":0.00001,"output_cost_per_token":0.00004,"cache_read_input_token_cost":2.5e-6},"pricing_endpoint":"openai/o3-deep-research-2025-06-26","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"openai/o3-deep-research-2025-06-26","object":"model","created":1760129661,"owned_by":"openai","model_name":"o3-deep-research-2025-06-26","context_length":200000,"max_input_tokens":null,"max_output_tokens":100000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["image","text","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":0.00001,"output_cost_per_token":0.00004,"cache_read_input_token_cost":2.5e-6},"list_pricing":{"input_cost_per_token":0.00001,"output_cost_per_token":0.00004,"cache_read_input_token_cost":2.5e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":1},{"id":"o4-mini-deep-research","object":"model","created":1760129642,"owned_by":"openai","mode":"chat","context_length":200000,"capabilities":{"input_modalities":["file","image","text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":8e-6,"cache_read_input_token_cost":5e-7},"pricing_endpoint":"openai/o4-mini-deep-research","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"openai/o4-mini-deep-research","object":"model","created":1760129642,"owned_by":"openai","model_name":"o4-mini-deep-research","context_length":200000,"max_input_tokens":null,"max_output_tokens":100000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["file","image","text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":8e-6,"cache_read_input_token_cost":5e-7},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":8e-6,"cache_read_input_token_cost":5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":1},{"id":"o4-mini-deep-research-2025-06-26","object":"model","created":1760129642,"owned_by":"openai","mode":"chat","context_length":200000,"capabilities":{"input_modalities":["file","image","text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":8e-6,"cache_read_input_token_cost":5e-7},"pricing_endpoint":"openai/o4-mini-deep-research-2025-06-26","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"openai/o4-mini-deep-research-2025-06-26","object":"model","created":1760129642,"owned_by":"openai","model_name":"o4-mini-deep-research-2025-06-26","context_length":200000,"max_input_tokens":null,"max_output_tokens":100000,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["file","image","text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":8e-6,"cache_read_input_token_cost":5e-7},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":8e-6,"cache_read_input_token_cost":5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":1},{"id":"llama-3.3-nemotron-super-49b-v1.5","object":"model","created":1760101395,"owned_by":"nvidia","mode":"chat","context_length":131072,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4e-7,"output_cost_per_token":4e-7},"pricing_endpoint":"deepinfra/nvidia/Llama-3.3-Nemotron-Super-49B-v1.5","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"deepinfra/nvidia/Llama-3.3-Nemotron-Super-49B-v1.5","object":"model","created":1760101395,"owned_by":"deepinfra","model_name":"nvidia/Llama-3.3-Nemotron-Super-49B-v1.5","context_length":131072,"max_input_tokens":null,"max_output_tokens":16384,"quantization":null,"retirement_date":"2026-07-17","description":"Llama-3.3-Nemotron-Super-49B-v1.5 is a 49B-parameter, English-centric reasoning/chat model derived from Meta’s Llama-3.3-70B-Instruct with a 128K context. It’s post-trained for agentic workflows (RAG, tool calling) via SFT across math, code, science, and...","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4e-7,"output_cost_per_token":4e-7},"list_pricing":{"input_cost_per_token":4e-7,"output_cost_per_token":4e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"gemini-2.5-flash-image","object":"model","created":1759870431,"owned_by":"google","mode":"chat","context_length":32768,"capabilities":{"input_modalities":["audio","image","text","video"],"output_modalities":["image","text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":false,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true,"supports_url_context":true,"supports_service_tier":true},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":2.5e-6,"input_cost_per_audio_token":1e-6,"input_cost_per_image_token":3e-7,"cache_read_input_token_cost":3e-8,"output_cost_per_image_token":0.00003,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"cache_creation_input_token_cost":8.33333333333333e-8,"output_cost_per_reasoning_token":2.5e-6,"cache_read_input_audio_token_cost":1e-7},"pricing_endpoint":"google/gemini-2.5-flash-image","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"google/gemini-2.5-flash-image","object":"model","created":1759870431,"owned_by":"google","model_name":"gemini-2.5-flash-image","context_length":32768,"max_input_tokens":32768,"max_output_tokens":32768,"quantization":null,"retirement_date":null,"description":"Gemini 2.5 Flash Image, a.k.a. \"Nano Banana,\" is now generally available. It is a state of the art image generation model with contextual understanding.","source":"https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-flash-image","capabilities":{"input_modalities":["audio","image","text","video"],"output_modalities":["image","text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":false,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true,"supports_url_context":true,"supports_service_tier":true},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":2.5e-6,"input_cost_per_audio_token":1e-6,"input_cost_per_image_token":3e-7,"cache_read_input_token_cost":3e-8,"output_cost_per_image_token":0.00003,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"cache_creation_input_token_cost":8.33333333333333e-8,"output_cost_per_reasoning_token":2.5e-6,"cache_read_input_audio_token_cost":1e-7},"list_pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":2.5e-6,"input_cost_per_audio_token":1e-6,"input_cost_per_image_token":3e-7,"cache_read_input_token_cost":3e-8,"output_cost_per_image_token":0.00003,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"cache_creation_input_token_cost":8.33333333333333e-8,"output_cost_per_reasoning_token":2.5e-6,"cache_read_input_audio_token_cost":1e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"vertex/gemini-2.5-flash-image","object":"model","created":1759870431,"owned_by":"vertex","model_name":"gemini-2.5-flash-image","context_length":32768,"max_input_tokens":null,"max_output_tokens":8192,"quantization":null,"retirement_date":null,"description":"Gemini 2.5 Flash Image, a.k.a. \"Nano Banana,\" is now generally available. It is a state of the art image generation model with contextual understanding.","source":null,"capabilities":{"input_modalities":["image","text"],"output_modalities":["image","text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":2.5e-6,"input_cost_per_audio_token":1e-6,"input_cost_per_image_token":3e-7,"cache_read_input_token_cost":3e-8,"output_cost_per_image_token":0.00003,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"cache_creation_input_token_cost":8.33333333333333e-8,"output_cost_per_reasoning_token":2.5e-6,"cache_read_input_audio_token_cost":1e-7},"list_pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":2.5e-6,"input_cost_per_audio_token":1e-6,"input_cost_per_image_token":3e-7,"cache_read_input_token_cost":3e-8,"output_cost_per_image_token":0.00003,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"cache_creation_input_token_cost":8.33333333333333e-8,"output_cost_per_reasoning_token":2.5e-6,"cache_read_input_audio_token_cost":1e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"qwen3-vl-30b-a3b-instruct","object":"model","created":1759794476,"owned_by":"qwen","mode":"chat","context_length":262144,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7},"pricing_endpoint":"deepinfra/Qwen/Qwen3-VL-30B-A3B-Instruct","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"deepinfra/Qwen/Qwen3-VL-30B-A3B-Instruct","object":"model","created":1759794476,"owned_by":"deepinfra","model_name":"Qwen/Qwen3-VL-30B-A3B-Instruct","context_length":262144,"max_input_tokens":262144,"max_output_tokens":16384,"quantization":"fp8","retirement_date":null,"description":"Qwen3-VL-30B-A3B-Instruct is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Instruct variant optimizes instruction-following for general multimodal tasks.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"gpt-5-pro-2025-10-06","object":"model","created":1759776663,"owned_by":"openai","mode":"chat","context_length":400000,"capabilities":{"input_modalities":["image","text","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":0.000015,"output_cost_per_token":0.00012,"input_cost_per_token_batches":7.5e-6,"output_cost_per_token_batches":0.00006,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01}},"pricing_endpoint":"openai/gpt-5-pro-2025-10-06","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"openai/gpt-5-pro-2025-10-06","object":"model","created":1759776663,"owned_by":"openai","model_name":"gpt-5-pro-2025-10-06","context_length":400000,"max_input_tokens":272000,"max_output_tokens":128000,"quantization":null,"retirement_date":"2026-12-11","description":"GPT-5 Pro is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience.","source":null,"capabilities":{"input_modalities":["image","text","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":0.000015,"output_cost_per_token":0.00012,"input_cost_per_token_batches":7.5e-6,"output_cost_per_token_batches":0.00006,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01}},"list_pricing":{"input_cost_per_token":0.000015,"output_cost_per_token":0.00012,"input_cost_per_token_batches":7.5e-6,"output_cost_per_token_batches":0.00006,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01}},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":1},{"id":"glm-4.6","object":"model","created":1759235576,"owned_by":"zai","mode":"chat","context_length":202752,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":2e-6,"cache_read_input_token_cost":1.0000000000000001e-7},"pricing_endpoint":"deepinfra/zai-org/GLM-4.6","regions":[{"code":"ap","name":"Asia"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"deepinfra/zai-org/GLM-4.6","object":"model","created":1759235576,"owned_by":"deepinfra","model_name":"zai-org/GLM-4.6","context_length":202752,"max_input_tokens":202752,"max_output_tokens":131072,"quantization":"fp4","retirement_date":null,"description":"Compared with GLM-4.5, this generation brings several key improvements: Longer context window: The context window has been expanded from 128K to 200K tokens, enabling the model to handle more complex...","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":2e-6,"cache_read_input_token_cost":1.0000000000000001e-7},"list_pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":2e-6,"cache_read_input_token_cost":1.0000000000000001e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null},{"id":"zai/glm-4.6","object":"model","created":1759235576,"owned_by":"zai","model_name":"glm-4.6","context_length":202752,"max_input_tokens":200000,"max_output_tokens":131072,"quantization":"fp4","retirement_date":null,"description":"Compared with GLM-4.5, this generation brings several key improvements: Longer context window: The context window has been expanded from 128K to 200K tokens, enabling the model to handle more complex...","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6e-7,"output_cost_per_token":2.2e-6,"cache_read_input_token_cost":1.1e-7,"cache_creation_input_token_cost":0.0},"list_pricing":{"input_cost_per_token":6e-7,"output_cost_per_token":2.2e-6,"cache_read_input_token_cost":1.1e-7,"cache_creation_input_token_cost":0.0},"discount":null,"discount_ends_at":null,"regions":[{"code":"ap","name":"Asia"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"qwen3-vl-235b-a22b-instruct","object":"model","created":1758668687,"owned_by":"qwen","mode":"chat","context_length":262144,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.0000000000000002e-7,"output_cost_per_token":8.799999999999999e-7,"cache_read_input_token_cost":1.1000000000000002e-7},"pricing_endpoint":"deepinfra/Qwen/Qwen3-VL-235B-A22B-Instruct","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"deepinfra/Qwen/Qwen3-VL-235B-A22B-Instruct","object":"model","created":1758668687,"owned_by":"deepinfra","model_name":"Qwen/Qwen3-VL-235B-A22B-Instruct","context_length":262144,"max_input_tokens":262144,"max_output_tokens":16384,"quantization":"fp8","retirement_date":null,"description":"Qwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies strong text generation with visual understanding across images and video.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.0000000000000002e-7,"output_cost_per_token":8.799999999999999e-7,"cache_read_input_token_cost":1.1000000000000002e-7},"list_pricing":{"input_cost_per_token":2.0000000000000002e-7,"output_cost_per_token":8.799999999999999e-7,"cache_read_input_token_cost":1.1000000000000002e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"deepseek-v3.1-terminus","object":"model","created":1758548275,"owned_by":"deepseek","mode":"chat","context_length":163840,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.7e-7,"output_cost_per_token":9.5e-7,"cache_read_input_token_cost":1.3e-7},"pricing_endpoint":"deepinfra/deepseek-ai/DeepSeek-V3.1-Terminus","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"deepinfra/deepseek-ai/DeepSeek-V3.1-Terminus","object":"model","created":1758548275,"owned_by":"deepinfra","model_name":"deepseek-ai/DeepSeek-V3.1-Terminus","context_length":163840,"max_input_tokens":null,"max_output_tokens":32768,"quantization":null,"retirement_date":"2026-08-17","description":"DeepSeek-V3.1 Terminus is an update to [DeepSeek V3.1](/deepseek/deepseek-chat-v3.1) that maintains the model's original capabilities while addressing issues reported by users, including language consistency and agent capabilities, further optimizing the model's...","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.7e-7,"output_cost_per_token":9.5e-7,"cache_read_input_token_cost":1.3e-7},"list_pricing":{"input_cost_per_token":2.7e-7,"output_cost_per_token":9.5e-7,"cache_read_input_token_cost":1.3e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"grok-4-fast","object":"model","created":1758240090,"owned_by":"xai","mode":"chat","context_length":2000000,"capabilities":{"input_modalities":["file","image","text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":5e-8,"search_context_cost_per_query":0.005},"pricing_endpoint":"xai/grok-4-fast","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"xai/grok-4-fast","object":"model","created":1758240090,"owned_by":"xai","model_name":"grok-4-fast","context_length":2000000,"max_input_tokens":2000000,"max_output_tokens":30000,"quantization":null,"retirement_date":null,"description":"Grok 4 Fast is xAI's latest multimodal model with SOTA cost-efficiency and a 2M token context window. It comes in two flavors: non-reasoning and reasoning. Read more about the model...","source":null,"capabilities":{"input_modalities":["file","image","text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":5e-8,"search_context_cost_per_query":0.005},"list_pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":5e-7,"cache_read_input_token_cost":5e-8,"search_context_cost_per_query":0.005},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"qwen3-coder-flash","object":"model","created":1758115536,"owned_by":"qwen","mode":"chat","context_length":1000000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"tiered_pricing":[{"range":[0,32000],"input_cost_per_token":1.9499999999999999e-7,"output_cost_per_token":9.75e-7,"cache_read_input_token_cost":3.9e-8,"cache_creation_input_token_cost":2.4375e-7},{"range":[32000,128000],"input_cost_per_token":3.25e-7,"output_cost_per_token":1.6250000000000001e-6,"cache_read_input_token_cost":6.500000000000001e-8,"cache_creation_input_token_cost":4.0625000000000003e-7},{"range":[128000,256000],"input_cost_per_token":5.200000000000001e-7,"output_cost_per_token":2.6e-6,"cache_read_input_token_cost":1.04e-7,"cache_creation_input_token_cost":6.5e-7},{"range":[256000,1000000],"input_cost_per_token":1.0400000000000002e-6,"output_cost_per_token":6.2399999999999995e-6,"cache_read_input_token_cost":2.08e-7,"cache_creation_input_token_cost":1.3e-6}],"input_cost_per_token":1.9499999999999999e-7,"output_cost_per_token":9.75e-7,"cache_read_input_token_cost":3.9e-8,"cache_creation_input_token_cost":2.4375e-7},"pricing_endpoint":"qwen/qwen3-coder-flash","regions":[{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"qwen/qwen3-coder-flash","object":"model","created":1758115536,"owned_by":"qwen","model_name":"qwen3-coder-flash","context_length":1000000,"max_input_tokens":997952,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"Qwen3-based code generation model that inherits the coding agent ability of Qwen3-Coder-Plus, supports multi-turn tool interaction, focuses on optimizing repository-level understanding and increasing tool-calling stability.","source":"https://www.alibabacloud.com/help/en/model-studio/models","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"tiered_pricing":[{"range":[0,32000],"input_cost_per_token":1.9499999999999999e-7,"output_cost_per_token":9.75e-7,"cache_read_input_token_cost":3.9e-8,"cache_creation_input_token_cost":2.4375e-7},{"range":[32000,128000],"input_cost_per_token":3.25e-7,"output_cost_per_token":1.6250000000000001e-6,"cache_read_input_token_cost":6.500000000000001e-8,"cache_creation_input_token_cost":4.0625000000000003e-7},{"range":[128000,256000],"input_cost_per_token":5.200000000000001e-7,"output_cost_per_token":2.6e-6,"cache_read_input_token_cost":1.04e-7,"cache_creation_input_token_cost":6.5e-7},{"range":[256000,1000000],"input_cost_per_token":1.0400000000000002e-6,"output_cost_per_token":6.2399999999999995e-6,"cache_read_input_token_cost":2.08e-7,"cache_creation_input_token_cost":1.3e-6}],"input_cost_per_token":1.9499999999999999e-7,"output_cost_per_token":9.75e-7,"cache_read_input_token_cost":3.9e-8,"cache_creation_input_token_cost":2.4375e-7},"list_pricing":{"tiered_pricing":[{"range":[0,32000],"input_cost_per_token":3e-7,"output_cost_per_token":1.5e-6,"cache_read_input_token_cost":6e-8,"cache_creation_input_token_cost":3.75e-7},{"range":[32000,128000],"input_cost_per_token":5e-7,"output_cost_per_token":2.5e-6,"cache_read_input_token_cost":1.0000000000000001e-7,"cache_creation_input_token_cost":6.25e-7},{"range":[128000,256000],"input_cost_per_token":8.000000000000001e-7,"output_cost_per_token":4e-6,"cache_read_input_token_cost":1.6e-7,"cache_creation_input_token_cost":1e-6},{"range":[256000,1000000],"input_cost_per_token":1.6000000000000001e-6,"output_cost_per_token":9.6e-6,"cache_read_input_token_cost":3.2e-7,"cache_creation_input_token_cost":2e-6}],"input_cost_per_token":3e-7,"output_cost_per_token":1.5e-6,"cache_read_input_token_cost":6e-8,"cache_creation_input_token_cost":3.75e-7},"discount":0.35,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":1},{"id":"qwen3-coder-flash-2025-07-28","object":"model","created":1758115536,"owned_by":"qwen","mode":"chat","context_length":1000000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"tiered_pricing":[{"range":[0,32000],"input_cost_per_token":1.9499999999999999e-7,"output_cost_per_token":9.75e-7},{"range":[32000,128000],"input_cost_per_token":3.25e-7,"output_cost_per_token":1.6250000000000001e-6},{"range":[128000,256000],"input_cost_per_token":5.200000000000001e-7,"output_cost_per_token":2.6e-6},{"range":[256000,1000000],"input_cost_per_token":1.0400000000000002e-6,"output_cost_per_token":6.2399999999999995e-6}],"input_cost_per_token":1.9499999999999999e-7,"output_cost_per_token":9.75e-7},"pricing_endpoint":"qwen/qwen3-coder-flash-2025-07-28","regions":[{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"qwen/qwen3-coder-flash-2025-07-28","object":"model","created":1758115536,"owned_by":"qwen","model_name":"qwen3-coder-flash-2025-07-28","context_length":1000000,"max_input_tokens":997952,"max_output_tokens":65536,"quantization":null,"retirement_date":null,"description":"Qwen3-based code generation model that inherits the coding agent ability of Qwen3-Coder-Plus, supports multi-turn tool interaction, focuses on optimizing repository-level understanding and increasing tool-calling stability. This is a snapshot from 28 July, 2025.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"tiered_pricing":[{"range":[0,32000],"input_cost_per_token":1.9499999999999999e-7,"output_cost_per_token":9.75e-7},{"range":[32000,128000],"input_cost_per_token":3.25e-7,"output_cost_per_token":1.6250000000000001e-6},{"range":[128000,256000],"input_cost_per_token":5.200000000000001e-7,"output_cost_per_token":2.6e-6},{"range":[256000,1000000],"input_cost_per_token":1.0400000000000002e-6,"output_cost_per_token":6.2399999999999995e-6}],"input_cost_per_token":1.9499999999999999e-7,"output_cost_per_token":9.75e-7},"list_pricing":{"tiered_pricing":[{"range":[0,32000],"input_cost_per_token":3e-7,"output_cost_per_token":1.5e-6},{"range":[32000,128000],"input_cost_per_token":5e-7,"output_cost_per_token":2.5e-6},{"range":[128000,256000],"input_cost_per_token":8.000000000000001e-7,"output_cost_per_token":4e-6},{"range":[256000,1000000],"input_cost_per_token":1.6000000000000001e-6,"output_cost_per_token":9.6e-6}],"input_cost_per_token":3e-7,"output_cost_per_token":1.5e-6},"discount":0.35,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":1},{"id":"grok-code-fast-1","object":"model","created":1756238927,"owned_by":"xai","mode":"chat","context_length":256000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":1.5e-6,"cache_read_input_token_cost":2e-8},"pricing_endpoint":"xai/grok-code-fast-1","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"xai/grok-code-fast-1","object":"model","created":1756238927,"owned_by":"xai","model_name":"grok-code-fast-1","context_length":256000,"max_input_tokens":256000,"max_output_tokens":256000,"quantization":null,"retirement_date":null,"description":"Grok Code Fast 1 is a speedy and economical reasoning model that excels at agentic coding. With reasoning traces visible in the response, developers can steer Grok Code for high-quality...","source":"https://docs.x.ai/docs/models","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":1.5e-6,"cache_read_input_token_cost":2e-8},"list_pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":1.5e-6,"cache_read_input_token_cost":2e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"hermes-4-405b","object":"model","created":1756235463,"owned_by":"nousresearch","mode":"chat","context_length":131072,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":3e-6,"cache_read_input_token_cost":1e-6},"pricing_endpoint":"nebius/NousResearch/Hermes-4-405B","regions":[{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"nebius/NousResearch/Hermes-4-405B","object":"model","created":1756235463,"owned_by":"nebius","model_name":"NousResearch/Hermes-4-405B","context_length":131072,"max_input_tokens":131072,"max_output_tokens":null,"quantization":"fp8","retirement_date":null,"description":"Hermes 4 is a large-scale reasoning model built on Meta-Llama-3.1-405B and released by Nous Research.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":3e-6,"cache_read_input_token_cost":1e-6},"list_pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":3e-6,"cache_read_input_token_cost":1e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"holo2-30b-a3b","object":"model","created":1755006551,"owned_by":"","mode":"chat","context_length":22000,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.4604989808830504e-7,"output_cost_per_token":8.074497622060451e-7},"pricing_endpoint":"scaleway/holo2-30b-a3b","regions":[{"code":"eu","name":"Europe"}],"alias_of":null,"endpoints":[{"id":"scaleway/holo2-30b-a3b","object":"model","created":1755006551,"owned_by":"scaleway","model_name":"holo2-30b-a3b","context_length":22000,"max_input_tokens":null,"max_output_tokens":32768,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.4604989808830504e-7,"output_cost_per_token":8.074497622060451e-7},"list_pricing":{"input_cost_per_token":3.4604989808830504e-7,"output_cost_per_token":8.074497622060451e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"glm-4.5v","object":"model","created":1754922288,"owned_by":"zai","mode":"chat","context_length":65536,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6e-7,"output_cost_per_token":1.8e-6,"cache_read_input_token_cost":1.1e-7},"pricing_endpoint":"zai/glm-4.5v","regions":[{"code":"ap","name":"Asia"}],"alias_of":null,"endpoints":[{"id":"zai/glm-4.5v","object":"model","created":1754922288,"owned_by":"zai","model_name":"glm-4.5v","context_length":65536,"max_input_tokens":128000,"max_output_tokens":16384,"quantization":"fp8","retirement_date":"2026-12-31","description":"GLM-4.5V is a vision-language foundation model for multimodal agent applications.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6e-7,"output_cost_per_token":1.8e-6,"cache_read_input_token_cost":1.1e-7},"list_pricing":{"input_cost_per_token":6e-7,"output_cost_per_token":1.8e-6,"cache_read_input_token_cost":1.1e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"ap","name":"Asia"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"gpt-5-2025-08-07","object":"model","created":1754587413,"owned_by":"openai","mode":"chat","context_length":400000,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":0.00001,"input_cost_per_token_flex":6.25e-7,"output_cost_per_token_flex":5e-6,"cache_read_input_token_cost":1.25e-7,"input_cost_per_token_batches":6.25e-7,"input_cost_per_token_priority":2.5e-6,"output_cost_per_token_batches":5e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"output_cost_per_token_priority":0.00002,"cache_read_input_token_cost_flex":6.25e-8,"cache_read_input_token_cost_batches":6.25e-8,"cache_read_input_token_cost_priority":2.5e-7},"pricing_endpoint":"openai/gpt-5-2025-08-07","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"openai/gpt-5-2025-08-07","object":"model","created":1754587413,"owned_by":"openai","model_name":"gpt-5-2025-08-07","context_length":400000,"max_input_tokens":272000,"max_output_tokens":128000,"quantization":null,"retirement_date":"2026-12-11","description":"GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":0.00001,"input_cost_per_token_flex":6.25e-7,"output_cost_per_token_flex":5e-6,"cache_read_input_token_cost":1.25e-7,"input_cost_per_token_batches":6.25e-7,"input_cost_per_token_priority":2.5e-6,"output_cost_per_token_batches":5e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"output_cost_per_token_priority":0.00002,"cache_read_input_token_cost_flex":6.25e-8,"cache_read_input_token_cost_batches":6.25e-8,"cache_read_input_token_cost_priority":2.5e-7},"list_pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":0.00001,"input_cost_per_token_flex":6.25e-7,"output_cost_per_token_flex":5e-6,"cache_read_input_token_cost":1.25e-7,"input_cost_per_token_batches":6.25e-7,"input_cost_per_token_priority":2.5e-6,"output_cost_per_token_batches":5e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"output_cost_per_token_priority":0.00002,"cache_read_input_token_cost_flex":6.25e-8,"cache_read_input_token_cost_batches":6.25e-8,"cache_read_input_token_cost_priority":2.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":1},{"id":"gpt-5-mini-2025-08-07","object":"model","created":1754587407,"owned_by":"openai","mode":"chat","context_length":400000,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2.5e-7,"output_cost_per_token":2e-6,"input_cost_per_token_flex":1.25e-7,"output_cost_per_token_flex":1e-6,"cache_read_input_token_cost":2.5e-8,"input_cost_per_token_batches":1.25e-7,"input_cost_per_token_priority":4.5e-7,"output_cost_per_token_batches":1e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"output_cost_per_token_priority":3.6e-6,"cache_read_input_token_cost_flex":1.25e-8,"cache_read_input_token_cost_batches":1.25e-8,"cache_read_input_token_cost_priority":4.5e-8},"pricing_endpoint":"openai/gpt-5-mini-2025-08-07","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"openai/gpt-5-mini-2025-08-07","object":"model","created":1754587407,"owned_by":"openai","model_name":"gpt-5-mini-2025-08-07","context_length":400000,"max_input_tokens":272000,"max_output_tokens":128000,"quantization":null,"retirement_date":"2026-12-11","description":"GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2.5e-7,"output_cost_per_token":2e-6,"input_cost_per_token_flex":1.25e-7,"output_cost_per_token_flex":1e-6,"cache_read_input_token_cost":2.5e-8,"input_cost_per_token_batches":1.25e-7,"input_cost_per_token_priority":4.5e-7,"output_cost_per_token_batches":1e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"output_cost_per_token_priority":3.6e-6,"cache_read_input_token_cost_flex":1.25e-8,"cache_read_input_token_cost_batches":1.25e-8,"cache_read_input_token_cost_priority":4.5e-8},"list_pricing":{"input_cost_per_token":2.5e-7,"output_cost_per_token":2e-6,"input_cost_per_token_flex":1.25e-7,"output_cost_per_token_flex":1e-6,"cache_read_input_token_cost":2.5e-8,"input_cost_per_token_batches":1.25e-7,"input_cost_per_token_priority":4.5e-7,"output_cost_per_token_batches":1e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"output_cost_per_token_priority":3.6e-6,"cache_read_input_token_cost_flex":1.25e-8,"cache_read_input_token_cost_batches":1.25e-8,"cache_read_input_token_cost_priority":4.5e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":1},{"id":"gpt-5-nano-2025-08-07","object":"model","created":1754587402,"owned_by":"openai","mode":"chat","context_length":400000,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":5e-8,"output_cost_per_token":4e-7,"input_cost_per_token_flex":2.5e-8,"output_cost_per_token_flex":2e-7,"cache_read_input_token_cost":5e-9,"input_cost_per_token_batches":2.5e-8,"output_cost_per_token_batches":2e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_read_input_token_cost_flex":2.5e-9,"cache_read_input_token_cost_batches":2.5e-9},"pricing_endpoint":"openai/gpt-5-nano-2025-08-07","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"openai/gpt-5-nano-2025-08-07","object":"model","created":1754587402,"owned_by":"openai","model_name":"gpt-5-nano-2025-08-07","context_length":400000,"max_input_tokens":272000,"max_output_tokens":128000,"quantization":null,"retirement_date":"2026-12-11","description":"GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":5e-8,"output_cost_per_token":4e-7,"input_cost_per_token_flex":2.5e-8,"output_cost_per_token_flex":2e-7,"cache_read_input_token_cost":5e-9,"input_cost_per_token_batches":2.5e-8,"output_cost_per_token_batches":2e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_read_input_token_cost_flex":2.5e-9,"cache_read_input_token_cost_batches":2.5e-9},"list_pricing":{"input_cost_per_token":5e-8,"output_cost_per_token":4e-7,"input_cost_per_token_flex":2.5e-8,"output_cost_per_token_flex":2e-7,"cache_read_input_token_cost":5e-9,"input_cost_per_token_batches":2.5e-8,"output_cost_per_token_batches":2e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_read_input_token_cost_flex":2.5e-9,"cache_read_input_token_cost_batches":2.5e-9},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":1},{"id":"codestral-2508","object":"model","created":1754079630,"owned_by":"mistral","mode":"chat","context_length":256000,"capabilities":{"input_modalities":["text","file"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":9e-7,"cache_read_input_token_cost":3e-8,"input_cost_per_token_batches":1.5e-7,"output_cost_per_token_batches":4.5e-7,"cache_read_input_token_cost_batches":1.5e-8},"pricing_endpoint":"mistral/codestral-2508","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"mistral/codestral-2508@eu","object":"model","created":1754079630,"owned_by":"mistral","model_name":"codestral-2508","context_length":256000,"max_input_tokens":128000,"max_output_tokens":204800,"quantization":null,"retirement_date":null,"description":"Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation.","source":"https://mistral.ai/news/codestral-25-08","capabilities":{"input_modalities":["text","file"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.3e-7,"output_cost_per_token":9.9e-7,"cache_read_input_token_cost":3.3e-8,"input_cost_per_token_batches":1.65e-7,"output_cost_per_token_batches":4.95e-7,"cache_read_input_token_cost_batches":1.65e-8},"list_pricing":{"input_cost_per_token":3.3e-7,"output_cost_per_token":9.9e-7,"cache_read_input_token_cost":3.3e-8,"input_cost_per_token_batches":1.65e-7,"output_cost_per_token_batches":4.95e-7,"cache_read_input_token_cost_batches":1.65e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"mistral/codestral-2508","object":"model","created":1754079630,"owned_by":"mistral","model_name":"codestral-2508","context_length":256000,"max_input_tokens":128000,"max_output_tokens":204800,"quantization":null,"retirement_date":null,"description":"Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation.","source":"https://mistral.ai/news/codestral-25-08","capabilities":{"input_modalities":["text","file"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":9e-7,"cache_read_input_token_cost":3e-8,"input_cost_per_token_batches":1.5e-7,"output_cost_per_token_batches":4.5e-7,"cache_read_input_token_cost_batches":1.5e-8},"list_pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":9e-7,"cache_read_input_token_cost":3e-8,"input_cost_per_token_batches":1.5e-7,"output_cost_per_token_batches":4.5e-7,"cache_read_input_token_cost_batches":1.5e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"qwen3-30b-a3b-instruct-2507","object":"model","created":1753806965,"owned_by":"qwen","mode":"chat","context_length":262144,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":3e-7,"cache_read_input_token_cost":1e-7},"pricing_endpoint":"nebius/Qwen/Qwen3-30B-A3B-Instruct-2507","regions":[{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"nebius/Qwen/Qwen3-30B-A3B-Instruct-2507","object":"model","created":1753806965,"owned_by":"nebius","model_name":"Qwen/Qwen3-30B-A3B-Instruct-2507","context_length":262144,"max_input_tokens":262144,"max_output_tokens":32768,"quantization":"fp8","retirement_date":null,"description":"Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen, with 3.3B active parameters per inference.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":3e-7,"cache_read_input_token_cost":1e-7},"list_pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":3e-7,"cache_read_input_token_cost":1e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"glm-4.5-air","object":"model","created":1753471258,"owned_by":"zai","mode":"chat","context_length":131072,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":1.1e-6,"cache_read_input_token_cost":3e-8},"pricing_endpoint":"zai/glm-4.5-air","regions":[{"code":"ap","name":"Asia"}],"alias_of":null,"endpoints":[{"id":"zai/glm-4.5-air","object":"model","created":1753471258,"owned_by":"zai","model_name":"glm-4.5-air","context_length":131072,"max_input_tokens":128000,"max_output_tokens":98304,"quantization":"fp8","retirement_date":null,"description":"GLM-4.5-Air is the lightweight variant of our latest flagship model family, also purpose-built for agent-centric applications.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":1.1e-6,"cache_read_input_token_cost":3e-8},"list_pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":1.1e-6,"cache_read_input_token_cost":3e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"ap","name":"Asia"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"qwen3-235b-a22b-thinking-2507","object":"model","created":1753449557,"owned_by":"qwen","mode":"chat","context_length":262144,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.3e-7,"output_cost_per_token":2.3e-6,"cache_read_input_token_cost":2e-7},"pricing_endpoint":"deepinfra/Qwen/Qwen3-235B-A22B-Thinking-2507","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"deepinfra/Qwen/Qwen3-235B-A22B-Thinking-2507","object":"model","created":1753449557,"owned_by":"deepinfra","model_name":"Qwen/Qwen3-235B-A22B-Thinking-2507","context_length":262144,"max_input_tokens":null,"max_output_tokens":32768,"quantization":null,"retirement_date":null,"description":"Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks. It activates 22B of its 235B parameters per forward pass and natively supports up to 262,144...","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.3e-7,"output_cost_per_token":2.3e-6,"cache_read_input_token_cost":2e-7},"list_pricing":{"input_cost_per_token":2.3e-7,"output_cost_per_token":2.3e-6,"cache_read_input_token_cost":2e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"gemini-2.5-flash-lite","object":"model","created":1753200276,"owned_by":"google","mode":"chat","context_length":1048576,"capabilities":{"input_modalities":["text","image","file","audio","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":4e-7,"input_cost_per_token_flex":5e-8,"input_cost_per_audio_token":3e-7,"input_cost_per_image_token":1e-7,"output_cost_per_token_flex":2e-7,"cache_read_input_token_cost":1e-8,"input_cost_per_token_priority":1.8e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":7.2e-7,"cache_creation_input_token_cost":8.33333333333333e-8,"input_cost_per_audio_token_flex":1.5e-7,"output_cost_per_reasoning_token":4e-7,"cache_read_input_token_cost_flex":1e-8,"cache_read_input_audio_token_cost":3e-8,"input_cost_per_audio_token_priority":5.4e-7,"cache_read_input_token_cost_priority":1.8e-8,"google_maps_grounding_cost_per_query":0.025,"cache_read_input_audio_token_cost_flex":3e-8,"cache_read_input_audio_token_cost_priority":5.4e-8},"pricing_endpoint":"google/gemini-2.5-flash-lite","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"google/gemini-2.5-flash-lite","object":"model","created":1753200276,"owned_by":"google","model_name":"gemini-2.5-flash-lite","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"quantization":null,"retirement_date":"2026-10-20","description":"Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency.","source":"https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview","capabilities":{"input_modalities":["text","image","file","audio","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":4e-7,"input_cost_per_token_flex":5e-8,"input_cost_per_audio_token":3e-7,"input_cost_per_image_token":1e-7,"output_cost_per_token_flex":2e-7,"cache_read_input_token_cost":1e-8,"input_cost_per_token_priority":1.8e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":7.2e-7,"cache_creation_input_token_cost":8.33333333333333e-8,"input_cost_per_audio_token_flex":1.5e-7,"output_cost_per_reasoning_token":4e-7,"cache_read_input_token_cost_flex":1e-8,"cache_read_input_audio_token_cost":3e-8,"input_cost_per_audio_token_priority":5.4e-7,"cache_read_input_token_cost_priority":1.8e-8,"google_maps_grounding_cost_per_query":0.025,"cache_read_input_audio_token_cost_flex":3e-8,"cache_read_input_audio_token_cost_priority":5.4e-8},"list_pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":4e-7,"input_cost_per_token_flex":5e-8,"input_cost_per_audio_token":3e-7,"input_cost_per_image_token":1e-7,"output_cost_per_token_flex":2e-7,"cache_read_input_token_cost":1e-8,"input_cost_per_token_priority":1.8e-7,"search_context_cost_per_query":{"search_context_size_low":0.014,"search_context_size_high":0.014,"search_context_size_medium":0.014},"output_cost_per_token_priority":7.2e-7,"cache_creation_input_token_cost":8.33333333333333e-8,"input_cost_per_audio_token_flex":1.5e-7,"output_cost_per_reasoning_token":4e-7,"cache_read_input_token_cost_flex":1e-8,"cache_read_input_audio_token_cost":3e-8,"input_cost_per_audio_token_priority":5.4e-7,"cache_read_input_token_cost_priority":1.8e-8,"google_maps_grounding_cost_per_query":0.025,"cache_read_input_audio_token_cost_flex":3e-8,"cache_read_input_audio_token_cost_priority":5.4e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":false,"alias_of":null},{"id":"vertex/gemini-2.5-flash-lite@eu","object":"model","created":1753200276,"owned_by":"vertex","model_name":"gemini-2.5-flash-lite","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"quantization":null,"retirement_date":"2026-10-20","description":"Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency.","source":null,"capabilities":{"input_modalities":["text","image","file","audio","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":4e-7,"input_cost_per_token_flex":5e-8,"input_cost_per_audio_token":3e-7,"output_cost_per_token_flex":2e-7,"cache_read_input_token_cost":1e-8,"input_cost_per_token_priority":1.8e-7,"search_context_cost_per_query":{"search_context_size_low":0.035,"search_context_size_high":0.035,"search_context_size_medium":0.035},"output_cost_per_token_priority":7.2e-7,"input_cost_per_audio_token_flex":5e-8,"output_cost_per_reasoning_token":4e-7,"cache_read_input_token_cost_flex":1e-8,"cache_read_input_audio_token_cost":3e-8,"input_cost_per_audio_token_priority":5.4e-7,"cache_read_input_token_cost_priority":1.8e-8,"google_maps_grounding_cost_per_query":0.025,"cache_read_input_audio_token_cost_priority":5.4e-8,"input_cost_per_audio_token_above_200k_tokens":3e-7,"input_cost_per_audio_token_above_200k_tokens_flex":5e-8,"input_cost_per_audio_token_above_200k_tokens_priority":5.4e-7},"list_pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":4e-7,"input_cost_per_token_flex":5e-8,"input_cost_per_audio_token":3e-7,"output_cost_per_token_flex":2e-7,"cache_read_input_token_cost":1e-8,"input_cost_per_token_priority":1.8e-7,"search_context_cost_per_query":{"search_context_size_low":0.035,"search_context_size_high":0.035,"search_context_size_medium":0.035},"output_cost_per_token_priority":7.2e-7,"input_cost_per_audio_token_flex":5e-8,"output_cost_per_reasoning_token":4e-7,"cache_read_input_token_cost_flex":1e-8,"cache_read_input_audio_token_cost":3e-8,"input_cost_per_audio_token_priority":5.4e-7,"cache_read_input_token_cost_priority":1.8e-8,"google_maps_grounding_cost_per_query":0.025,"cache_read_input_audio_token_cost_priority":5.4e-8,"input_cost_per_audio_token_above_200k_tokens":3e-7,"input_cost_per_audio_token_above_200k_tokens_flex":5e-8,"input_cost_per_audio_token_above_200k_tokens_priority":5.4e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"vertex/gemini-2.5-flash-lite","object":"model","created":1753200276,"owned_by":"vertex","model_name":"gemini-2.5-flash-lite","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"quantization":null,"retirement_date":"2026-10-20","description":"Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency.","source":null,"capabilities":{"input_modalities":["text","image","file","audio","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":4e-7,"input_cost_per_token_flex":5e-8,"input_cost_per_audio_token":3e-7,"output_cost_per_token_flex":2e-7,"cache_read_input_token_cost":1e-8,"input_cost_per_token_priority":1.8e-7,"search_context_cost_per_query":{"search_context_size_low":0.035,"search_context_size_high":0.035,"search_context_size_medium":0.035},"output_cost_per_token_priority":7.2e-7,"input_cost_per_audio_token_flex":5e-8,"output_cost_per_reasoning_token":4e-7,"cache_read_input_token_cost_flex":1e-8,"cache_read_input_audio_token_cost":3e-8,"input_cost_per_audio_token_priority":5.4e-7,"cache_read_input_token_cost_priority":1.8e-8,"google_maps_grounding_cost_per_query":0.025,"cache_read_input_audio_token_cost_priority":5.4e-8,"input_cost_per_audio_token_above_200k_tokens":3e-7,"input_cost_per_audio_token_above_200k_tokens_flex":5e-8,"input_cost_per_audio_token_above_200k_tokens_priority":5.4e-7},"list_pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":4e-7,"input_cost_per_token_flex":5e-8,"input_cost_per_audio_token":3e-7,"output_cost_per_token_flex":2e-7,"cache_read_input_token_cost":1e-8,"input_cost_per_token_priority":1.8e-7,"search_context_cost_per_query":{"search_context_size_low":0.035,"search_context_size_high":0.035,"search_context_size_medium":0.035},"output_cost_per_token_priority":7.2e-7,"input_cost_per_audio_token_flex":5e-8,"output_cost_per_reasoning_token":4e-7,"cache_read_input_token_cost_flex":1e-8,"cache_read_input_audio_token_cost":3e-8,"input_cost_per_audio_token_priority":5.4e-7,"cache_read_input_token_cost_priority":1.8e-8,"google_maps_grounding_cost_per_query":0.025,"cache_read_input_audio_token_cost_priority":5.4e-8,"input_cost_per_audio_token_above_200k_tokens":3e-7,"input_cost_per_audio_token_above_200k_tokens_flex":5e-8,"input_cost_per_audio_token_above_200k_tokens_priority":5.4e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null},{"id":"vertex/gemini-2.5-flash-lite@us","object":"model","created":1753200276,"owned_by":"vertex","model_name":"gemini-2.5-flash-lite","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"quantization":null,"retirement_date":"2026-10-20","description":"Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency.","source":null,"capabilities":{"input_modalities":["text","image","file","audio","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":4e-7,"input_cost_per_token_flex":5e-8,"input_cost_per_audio_token":3e-7,"output_cost_per_token_flex":2e-7,"cache_read_input_token_cost":1e-8,"input_cost_per_token_priority":1.8e-7,"search_context_cost_per_query":{"search_context_size_low":0.035,"search_context_size_high":0.035,"search_context_size_medium":0.035},"output_cost_per_token_priority":7.2e-7,"input_cost_per_audio_token_flex":5e-8,"output_cost_per_reasoning_token":4e-7,"cache_read_input_token_cost_flex":1e-8,"cache_read_input_audio_token_cost":3e-8,"input_cost_per_audio_token_priority":5.4e-7,"cache_read_input_token_cost_priority":1.8e-8,"google_maps_grounding_cost_per_query":0.025,"cache_read_input_audio_token_cost_priority":5.4e-8,"input_cost_per_audio_token_above_200k_tokens":3e-7,"input_cost_per_audio_token_above_200k_tokens_flex":5e-8,"input_cost_per_audio_token_above_200k_tokens_priority":5.4e-7},"list_pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":4e-7,"input_cost_per_token_flex":5e-8,"input_cost_per_audio_token":3e-7,"output_cost_per_token_flex":2e-7,"cache_read_input_token_cost":1e-8,"input_cost_per_token_priority":1.8e-7,"search_context_cost_per_query":{"search_context_size_low":0.035,"search_context_size_high":0.035,"search_context_size_medium":0.035},"output_cost_per_token_priority":7.2e-7,"input_cost_per_audio_token_flex":5e-8,"output_cost_per_reasoning_token":4e-7,"cache_read_input_token_cost_flex":1e-8,"cache_read_input_audio_token_cost":3e-8,"input_cost_per_audio_token_priority":5.4e-7,"cache_read_input_token_cost_priority":1.8e-8,"google_maps_grounding_cost_per_query":0.025,"cache_read_input_audio_token_cost_priority":5.4e-8,"input_cost_per_audio_token_above_200k_tokens":3e-7,"input_cost_per_audio_token_above_200k_tokens_flex":5e-8,"input_cost_per_audio_token_above_200k_tokens_priority":5.4e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":4},{"id":"grok-4","object":"model","created":1752087689,"owned_by":"xai","mode":"chat","context_length":256000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015},"pricing_endpoint":"xai/grok-4","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"xai/grok-4","object":"model","created":1752087689,"owned_by":"xai","model_name":"grok-4","context_length":256000,"max_input_tokens":256000,"max_output_tokens":256000,"quantization":null,"retirement_date":null,"description":"Grok 4 is xAI's latest reasoning model with a 256k context window. It supports parallel tool calling, structured outputs, and both image and text inputs. Note that reasoning is not...","source":"https://docs.x.ai/docs/models","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015},"list_pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"minimax-m1","object":"model","created":1750200414,"owned_by":"minimax","mode":"chat","context_length":1000000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4e-7,"output_cost_per_token":2.2e-6},"pricing_endpoint":"minimax/minimax-m1","regions":[{"code":"ap","name":"Asia"}],"alias_of":null,"endpoints":[{"id":"minimax/minimax-m1","object":"model","created":1750200414,"owned_by":"minimax","model_name":"minimax-m1","context_length":1000000,"max_input_tokens":null,"max_output_tokens":40000,"quantization":null,"retirement_date":null,"description":"MiniMax-M1 is a large-scale, open-weight reasoning model designed for extended context and high-efficiency inference.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4e-7,"output_cost_per_token":2.2e-6},"list_pricing":{"input_cost_per_token":4e-7,"output_cost_per_token":2.2e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"ap","name":"Asia"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":1},{"id":"o3-pro","object":"model","created":1749598352,"owned_by":"openai","mode":"chat","context_length":200000,"capabilities":{"input_modalities":["text","file","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":0.00002,"output_cost_per_token":0.00008,"input_cost_per_token_batches":0.00001,"output_cost_per_token_batches":0.00004,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01}},"pricing_endpoint":"openai/o3-pro","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"openai/o3-pro","object":"model","created":1749598352,"owned_by":"openai","model_name":"o3-pro","context_length":200000,"max_input_tokens":200000,"max_output_tokens":100000,"quantization":null,"retirement_date":"2026-12-11","description":"The o-series of models are trained with reinforcement learning to think before they answer and perform complex reasoning.","source":null,"capabilities":{"input_modalities":["text","file","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":0.00002,"output_cost_per_token":0.00008,"input_cost_per_token_batches":0.00001,"output_cost_per_token_batches":0.00004,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01}},"list_pricing":{"input_cost_per_token":0.00002,"output_cost_per_token":0.00008,"input_cost_per_token_batches":0.00001,"output_cost_per_token_batches":0.00004,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01}},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":1},{"id":"o3-pro-2025-06-10","object":"model","created":1749598352,"owned_by":"openai","mode":"chat","context_length":200000,"capabilities":{"input_modalities":["text","file","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":0.00002,"output_cost_per_token":0.00008,"input_cost_per_token_batches":0.00001,"output_cost_per_token_batches":0.00004,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01}},"pricing_endpoint":"openai/o3-pro-2025-06-10","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"openai/o3-pro-2025-06-10","object":"model","created":1749598352,"owned_by":"openai","model_name":"o3-pro-2025-06-10","context_length":200000,"max_input_tokens":200000,"max_output_tokens":100000,"quantization":null,"retirement_date":"2026-12-11","description":"The o-series of models are trained with reinforcement learning to think before they answer and perform complex reasoning.","source":null,"capabilities":{"input_modalities":["text","file","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":0.00002,"output_cost_per_token":0.00008,"input_cost_per_token_batches":0.00001,"output_cost_per_token_batches":0.00004,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01}},"list_pricing":{"input_cost_per_token":0.00002,"output_cost_per_token":0.00008,"input_cost_per_token_batches":0.00001,"output_cost_per_token_batches":0.00004,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01}},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":1},{"id":"grok-3","object":"model","created":1749582908,"owned_by":"xai","mode":"chat","context_length":131072,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"cache_read_input_token_cost":7.5e-7},"pricing_endpoint":"xai/grok-3","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"xai/grok-3","object":"model","created":1749582908,"owned_by":"xai","model_name":"grok-3","context_length":131072,"max_input_tokens":131072,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"Grok 3 is the latest model from xAI. It's their flagship model that excels at enterprise use cases like data extraction, coding, and text summarization. Possesses deep domain knowledge in...","source":"https://x.ai/api#pricing","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"cache_read_input_token_cost":7.5e-7},"list_pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"cache_read_input_token_cost":7.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"mistral-medium-3","object":"model","created":1746627341,"owned_by":"mistral","mode":"chat","context_length":262144,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4e-7,"output_cost_per_token":2e-6,"cache_read_input_token_cost":4e-8},"pricing_endpoint":"mistral/mistral-medium-3","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"mistral/mistral-medium-3@eu","object":"model","created":1746627341,"owned_by":"mistral","model_name":"mistral-medium-3","context_length":262144,"max_input_tokens":262144,"max_output_tokens":104857,"quantization":null,"retirement_date":null,"description":"Mistral Medium 3 is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4.4e-7,"output_cost_per_token":2.2e-6,"cache_read_input_token_cost":4.4000000000000004e-8},"list_pricing":{"input_cost_per_token":4.4e-7,"output_cost_per_token":2.2e-6,"cache_read_input_token_cost":4.4000000000000004e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"mistral/mistral-medium-3","object":"model","created":1746627341,"owned_by":"mistral","model_name":"mistral-medium-3","context_length":262144,"max_input_tokens":262144,"max_output_tokens":104857,"quantization":null,"retirement_date":null,"description":"Mistral Medium 3 is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4e-7,"output_cost_per_token":2e-6,"cache_read_input_token_cost":4e-8},"list_pricing":{"input_cost_per_token":4e-7,"output_cost_per_token":2e-6,"cache_read_input_token_cost":4e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"llama-guard-4-12b","object":"model","created":1745975193,"owned_by":"meta","mode":"chat","context_length":163840,"capabilities":{"input_modalities":["image","text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.8e-7,"output_cost_per_token":1.8e-7},"pricing_endpoint":"deepinfra/meta-llama/Llama-Guard-4-12B","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"deepinfra/meta-llama/Llama-Guard-4-12B","object":"model","created":1745975193,"owned_by":"deepinfra","model_name":"meta-llama/Llama-Guard-4-12B","context_length":163840,"max_input_tokens":163840,"max_output_tokens":16384,"quantization":"bf16","retirement_date":null,"description":"Llama Guard 4 is a Llama 4 Scout-derived multimodal pretrained model, fine-tuned for content safety classification.","source":null,"capabilities":{"input_modalities":["image","text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.8e-7,"output_cost_per_token":1.8e-7},"list_pricing":{"input_cost_per_token":1.8e-7,"output_cost_per_token":1.8e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"o3-2025-04-16","object":"model","created":1744823457,"owned_by":"openai","mode":"chat","context_length":200000,"capabilities":{"input_modalities":["image","text","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":8e-6,"input_cost_per_token_flex":1e-6,"output_cost_per_token_flex":4e-6,"cache_read_input_token_cost":5e-7,"input_cost_per_token_batches":1e-6,"input_cost_per_token_priority":3.5e-6,"output_cost_per_token_batches":4e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"output_cost_per_token_priority":0.000014,"cache_read_input_token_cost_flex":2.5e-7,"cache_read_input_token_cost_priority":8.75e-7},"pricing_endpoint":"openai/o3-2025-04-16","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"openai/o3-2025-04-16","object":"model","created":1744823457,"owned_by":"openai","model_name":"o3-2025-04-16","context_length":200000,"max_input_tokens":200000,"max_output_tokens":100000,"quantization":null,"retirement_date":"2026-12-11","description":"o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks.","source":null,"capabilities":{"input_modalities":["image","text","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":8e-6,"input_cost_per_token_flex":1e-6,"output_cost_per_token_flex":4e-6,"cache_read_input_token_cost":5e-7,"input_cost_per_token_batches":1e-6,"input_cost_per_token_priority":3.5e-6,"output_cost_per_token_batches":4e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"output_cost_per_token_priority":0.000014,"cache_read_input_token_cost_flex":2.5e-7,"cache_read_input_token_cost_priority":8.75e-7},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":8e-6,"input_cost_per_token_flex":1e-6,"output_cost_per_token_flex":4e-6,"cache_read_input_token_cost":5e-7,"input_cost_per_token_batches":1e-6,"input_cost_per_token_priority":3.5e-6,"output_cost_per_token_batches":4e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"output_cost_per_token_priority":0.000014,"cache_read_input_token_cost_flex":2.5e-7,"cache_read_input_token_cost_priority":8.75e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":1},{"id":"gpt-4.1-2025-04-14","object":"model","created":1744651385,"owned_by":"openai","mode":"chat","context_length":1047576,"capabilities":{"input_modalities":["image","text","file"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":8e-6,"cache_read_input_token_cost":5e-7,"input_cost_per_token_batches":1e-6,"input_cost_per_token_priority":3.5e-6,"output_cost_per_token_batches":4e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"output_cost_per_token_priority":0.000014,"cache_read_input_token_cost_priority":8.75e-7},"pricing_endpoint":"openai/gpt-4.1-2025-04-14","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"openai/gpt-4.1-2025-04-14","object":"model","created":1744651385,"owned_by":"openai","model_name":"gpt-4.1-2025-04-14","context_length":1047576,"max_input_tokens":1047576,"max_output_tokens":32768,"quantization":null,"retirement_date":null,"description":"GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning.","source":null,"capabilities":{"input_modalities":["image","text","file"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":8e-6,"cache_read_input_token_cost":5e-7,"input_cost_per_token_batches":1e-6,"input_cost_per_token_priority":3.5e-6,"output_cost_per_token_batches":4e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"output_cost_per_token_priority":0.000014,"cache_read_input_token_cost_priority":8.75e-7},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":8e-6,"cache_read_input_token_cost":5e-7,"input_cost_per_token_batches":1e-6,"input_cost_per_token_priority":3.5e-6,"output_cost_per_token_batches":4e-6,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"output_cost_per_token_priority":0.000014,"cache_read_input_token_cost_priority":8.75e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":1},{"id":"gpt-4.1-mini-2025-04-14","object":"model","created":1744651381,"owned_by":"openai","mode":"chat","context_length":1047576,"capabilities":{"input_modalities":["image","text","file"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":4e-7,"output_cost_per_token":1.6e-6,"cache_read_input_token_cost":1e-7,"input_cost_per_token_batches":2e-7,"input_cost_per_token_priority":7e-7,"output_cost_per_token_batches":8e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"output_cost_per_token_priority":2.8e-6,"cache_read_input_token_cost_priority":1.75e-7},"pricing_endpoint":"openai/gpt-4.1-mini-2025-04-14","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"openai/gpt-4.1-mini-2025-04-14","object":"model","created":1744651381,"owned_by":"openai","model_name":"gpt-4.1-mini-2025-04-14","context_length":1047576,"max_input_tokens":1047576,"max_output_tokens":32768,"quantization":null,"retirement_date":null,"description":"GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost.","source":null,"capabilities":{"input_modalities":["image","text","file"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":4e-7,"output_cost_per_token":1.6e-6,"cache_read_input_token_cost":1e-7,"input_cost_per_token_batches":2e-7,"input_cost_per_token_priority":7e-7,"output_cost_per_token_batches":8e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"output_cost_per_token_priority":2.8e-6,"cache_read_input_token_cost_priority":1.75e-7},"list_pricing":{"input_cost_per_token":4e-7,"output_cost_per_token":1.6e-6,"cache_read_input_token_cost":1e-7,"input_cost_per_token_batches":2e-7,"input_cost_per_token_priority":7e-7,"output_cost_per_token_batches":8e-7,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"output_cost_per_token_priority":2.8e-6,"cache_read_input_token_cost_priority":1.75e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":1},{"id":"grok-3-beta","object":"model","created":1744240068,"owned_by":"xai","mode":"chat","context_length":131072,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"cache_read_input_token_cost":7.5e-7},"pricing_endpoint":"xai/grok-3-beta","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"xai/grok-3-beta","object":"model","created":1744240068,"owned_by":"xai","model_name":"grok-3-beta","context_length":131072,"max_input_tokens":131072,"max_output_tokens":131072,"quantization":null,"retirement_date":null,"description":"Grok 3 is the latest model from xAI. It's their flagship model that excels at enterprise use cases like data extraction, coding, and text summarization. Possesses deep domain knowledge in...","source":"https://x.ai/api#pricing","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":true,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"cache_read_input_token_cost":7.5e-7},"list_pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"cache_read_input_token_cost":7.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"mistral-small-3.1-24b-instruct","object":"model","created":1742238937,"owned_by":"mistral","mode":"chat","context_length":128000,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.5099999999999995e-7,"output_cost_per_token":5.550000000000001e-7},"pricing_endpoint":"cloudflare/@cf/mistralai/mistral-small-3.1-24b-instruct","regions":[{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"cloudflare/@cf/mistralai/mistral-small-3.1-24b-instruct","object":"model","created":1742238937,"owned_by":"cloudflare","model_name":"@cf/mistralai/mistral-small-3.1-24b-instruct","context_length":128000,"max_input_tokens":128000,"max_output_tokens":102400,"quantization":null,"retirement_date":null,"description":"Mistral Small 3.1 24B Instruct is an upgraded variant of Mistral Small 3 (2501), featuring 24 billion parameters with advanced multimodal capabilities.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.5099999999999995e-7,"output_cost_per_token":5.550000000000001e-7},"list_pricing":{"input_cost_per_token":3.5099999999999995e-7,"output_cost_per_token":5.550000000000001e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"command-a-03-2025","object":"model","created":1741894342,"owned_by":"cohere","mode":"chat","context_length":288000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.5e-6,"output_cost_per_token":0.00001},"pricing_endpoint":"cohere/command-a-03-2025","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"cohere/command-a-03-2025","object":"model","created":1741894342,"owned_by":"cohere","model_name":"command-a-03-2025","context_length":288000,"max_input_tokens":256000,"max_output_tokens":8192,"quantization":null,"retirement_date":null,"description":"Command A is an open-weights 111B parameter model with a 256k context window focused on delivering great performance across agentic, multilingual, and coding use cases.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.5e-6,"output_cost_per_token":0.00001},"list_pricing":{"input_cost_per_token":2.5e-6,"output_cost_per_token":0.00001},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":1},{"id":"sonar-reasoning-pro","object":"model","created":1741313308,"owned_by":"perplexity","mode":"chat","context_length":128000,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":8e-6,"search_context_cost_per_query":{"search_context_size_low":0.005,"search_context_size_high":0.005,"search_context_size_medium":0.005}},"pricing_endpoint":"perplexityai/sonar-reasoning-pro","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"perplexityai/sonar-reasoning-pro","object":"model","created":1741313308,"owned_by":"perplexityai","model_name":"sonar-reasoning-pro","context_length":128000,"max_input_tokens":128000,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"Note: Sonar Pro pricing includes Perplexity search pricing. Sonar Reasoning Pro is a premier reasoning model powered by DeepSeek R1 with Chain of Thought (CoT).","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":8e-6,"search_context_cost_per_query":{"search_context_size_low":0.005,"search_context_size_high":0.005,"search_context_size_medium":0.005}},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":8e-6,"search_context_cost_per_query":{"search_context_size_low":0.005,"search_context_size_high":0.005,"search_context_size_medium":0.005}},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":1},{"id":"sonar-pro","object":"model","created":1741312423,"owned_by":"perplexity","mode":"chat","context_length":200000,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"search_context_cost_per_query":{"search_context_size_low":0.005,"search_context_size_high":0.005,"search_context_size_medium":0.005}},"pricing_endpoint":"perplexityai/sonar-pro","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"perplexityai/sonar-pro","object":"model","created":1741312423,"owned_by":"perplexityai","model_name":"sonar-pro","context_length":200000,"max_input_tokens":200000,"max_output_tokens":8000,"quantization":null,"retirement_date":null,"description":"Note: Sonar Pro pricing includes Perplexity search pricing.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"search_context_cost_per_query":{"search_context_size_low":0.005,"search_context_size_high":0.005,"search_context_size_medium":0.005}},"list_pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"search_context_cost_per_query":{"search_context_size_low":0.005,"search_context_size_high":0.005,"search_context_size_medium":0.005}},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":1},{"id":"sonar-deep-research","object":"model","created":1741311246,"owned_by":"perplexity","mode":"chat","context_length":128000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":8e-6,"citation_cost_per_token":2e-6,"search_context_cost_per_query":{"search_context_size_low":0.005,"search_context_size_high":0.005,"search_context_size_medium":0.005},"output_cost_per_reasoning_token":3e-6},"pricing_endpoint":"perplexityai/sonar-deep-research","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"perplexityai/sonar-deep-research","object":"model","created":1741311246,"owned_by":"perplexityai","model_name":"sonar-deep-research","context_length":128000,"max_input_tokens":128000,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"Sonar Deep Research is a research-focused model designed for multi-step retrieval, synthesis, and reasoning across complex topics.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":8e-6,"citation_cost_per_token":2e-6,"search_context_cost_per_query":{"search_context_size_low":0.005,"search_context_size_high":0.005,"search_context_size_medium":0.005},"output_cost_per_reasoning_token":3e-6},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":8e-6,"citation_cost_per_token":2e-6,"search_context_cost_per_query":{"search_context_size_low":0.005,"search_context_size_high":0.005,"search_context_size_medium":0.005},"output_cost_per_reasoning_token":3e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":1},{"id":"qwen-plus","object":"model","created":1738409840,"owned_by":"qwen","mode":"chat","context_length":1000000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"tiered_pricing":[{"range":[0,256000],"input_cost_per_token":2.6000000000000005e-7,"output_cost_per_token":7.799999999999999e-7,"cache_read_input_token_cost":5.2e-8,"cache_creation_input_token_cost":3.25e-7,"output_cost_per_reasoning_token":2.6e-6},{"range":[256000,1000000],"input_cost_per_token":7.799999999999999e-7,"output_cost_per_token":2.34e-6,"cache_read_input_token_cost":1.56e-7,"cache_creation_input_token_cost":9.75e-7,"output_cost_per_reasoning_token":7.8e-6}],"input_cost_per_token":2.6000000000000005e-7,"output_cost_per_token":7.799999999999999e-7,"cache_read_input_token_cost":5.2e-8,"cache_creation_input_token_cost":3.25e-7,"output_cost_per_reasoning_token":2.6e-6},"pricing_endpoint":"qwen/qwen-plus","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"qwen/qwen-plus@eu","object":"model","created":1738409840,"owned_by":"qwen","model_name":"qwen-plus","context_length":1000000,"max_input_tokens":995904,"max_output_tokens":32768,"quantization":null,"retirement_date":"2026-10-09","description":"The Plus model of the Qwen3 series, effectively integrates thinking mode and non-thinking mode, allowing for mode switching during conversations. Its reasoning capabilities significantly surpass those of QwQ, and its general capabilities notably exceed those of Qwen2.5-Plus, reaching the SOTA level in the same scale within the industry.","source":"https://www.alibabacloud.com/help/en/model-studio/models","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"tiered_pricing":[{"range":[0,256000],"input_cost_per_token":2.6000000000000005e-7,"output_cost_per_token":7.799999999999999e-7,"cache_read_input_token_cost":5.2e-8,"cache_creation_input_token_cost":3.25e-7,"output_cost_per_reasoning_token":2.6e-6},{"range":[256000,1000000],"input_cost_per_token":7.799999999999999e-7,"output_cost_per_token":2.34e-6,"cache_read_input_token_cost":1.56e-7,"cache_creation_input_token_cost":9.75e-7,"output_cost_per_reasoning_token":7.8e-6}],"input_cost_per_token":2.6000000000000005e-7,"output_cost_per_token":7.799999999999999e-7,"cache_read_input_token_cost":5.2e-8,"cache_creation_input_token_cost":3.25e-7,"output_cost_per_reasoning_token":2.6e-6},"list_pricing":{"tiered_pricing":[{"range":[0,256000],"input_cost_per_token":4.0000000000000003e-7,"output_cost_per_token":1.2e-6,"cache_read_input_token_cost":8e-8,"cache_creation_input_token_cost":5e-7,"output_cost_per_reasoning_token":4e-6},{"range":[256000,1000000],"input_cost_per_token":1.2e-6,"output_cost_per_token":3.6000000000000003e-6,"cache_read_input_token_cost":2.4e-7,"cache_creation_input_token_cost":1.5e-6,"output_cost_per_reasoning_token":0.000012}],"input_cost_per_token":4.0000000000000003e-7,"output_cost_per_token":1.2e-6,"cache_read_input_token_cost":8e-8,"cache_creation_input_token_cost":5e-7,"output_cost_per_reasoning_token":4e-6},"discount":0.35,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"qwen/qwen-plus","object":"model","created":1738409840,"owned_by":"qwen","model_name":"qwen-plus","context_length":1000000,"max_input_tokens":995904,"max_output_tokens":32768,"quantization":null,"retirement_date":"2026-10-09","description":"The Plus model of the Qwen3 series, effectively integrates thinking mode and non-thinking mode, allowing for mode switching during conversations. Its reasoning capabilities significantly surpass those of QwQ, and its general capabilities notably exceed those of Qwen2.5-Plus, reaching the SOTA level in the same scale within the industry.","source":"https://www.alibabacloud.com/help/en/model-studio/models","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"tiered_pricing":[{"range":[0,256000],"input_cost_per_token":2.6000000000000005e-7,"output_cost_per_token":7.799999999999999e-7,"cache_read_input_token_cost":5.2e-8,"cache_creation_input_token_cost":3.25e-7,"output_cost_per_reasoning_token":2.6e-6},{"range":[256000,1000000],"input_cost_per_token":7.799999999999999e-7,"output_cost_per_token":2.34e-6,"cache_read_input_token_cost":1.56e-7,"cache_creation_input_token_cost":9.75e-7,"output_cost_per_reasoning_token":7.8e-6}],"input_cost_per_token":2.6000000000000005e-7,"output_cost_per_token":7.799999999999999e-7,"cache_read_input_token_cost":5.2e-8,"cache_creation_input_token_cost":3.25e-7,"output_cost_per_reasoning_token":2.6e-6},"list_pricing":{"tiered_pricing":[{"range":[0,256000],"input_cost_per_token":4.0000000000000003e-7,"output_cost_per_token":1.2e-6,"cache_read_input_token_cost":8e-8,"cache_creation_input_token_cost":5e-7,"output_cost_per_reasoning_token":4e-6},{"range":[256000,1000000],"input_cost_per_token":1.2e-6,"output_cost_per_token":3.6000000000000003e-6,"cache_read_input_token_cost":2.4e-7,"cache_creation_input_token_cost":1.5e-6,"output_cost_per_reasoning_token":0.000012}],"input_cost_per_token":4.0000000000000003e-7,"output_cost_per_token":1.2e-6,"cache_read_input_token_cost":8e-8,"cache_creation_input_token_cost":5e-7,"output_cost_per_reasoning_token":4e-6},"discount":0.35,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":2},{"id":"qwen-plus-2025-01-25","object":"model","created":1738409840,"owned_by":"qwen","mode":"chat","context_length":131072,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.6000000000000005e-7,"output_cost_per_token":7.799999999999999e-7},"pricing_endpoint":"qwen/qwen-plus-2025-01-25","regions":[{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"qwen/qwen-plus-2025-01-25","object":"model","created":1738409840,"owned_by":"qwen","model_name":"qwen-plus-2025-01-25","context_length":131072,"max_input_tokens":128000,"max_output_tokens":8192,"quantization":null,"retirement_date":"2026-10-09","description":"A balanced model in the Qwen series, with inference effectiveness and speed between Qwen-Max and Qwen-Turbo, making it suitable for moderately complex tasks. Compared to Qwen-Plus-2025-0112, there is a comprehensive upgrade in both Chinese and English capabilities. Notably, there are significant improvements in coding ability, logical reasoning, and multilingual support. The response style has been significantly adjusted to align with human preferences, especially for objective queries such as mathematics, logical reasoning, and knowledge-based questions—both the level of detail in responses and the clarity of formatting have improved noticeably. Additionally, targeted enhancements have been made in creative writing, JSON format compliance, and role-playing abilities. This version is expected to be maintained until one month before the next snapshot release.","source":"https://www.alibabacloud.com/help/en/model-studio/models","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.6000000000000005e-7,"output_cost_per_token":7.799999999999999e-7},"list_pricing":{"input_cost_per_token":4.0000000000000003e-7,"output_cost_per_token":1.2e-6},"discount":0.35,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":1},{"id":"qwen-plus-2025-04-28","object":"model","created":1738409840,"owned_by":"qwen","mode":"chat","context_length":131072,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.6000000000000005e-7,"output_cost_per_token":7.799999999999999e-7,"output_cost_per_reasoning_token":2.6e-6},"pricing_endpoint":"qwen/qwen-plus-2025-04-28","regions":[{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"qwen/qwen-plus-2025-04-28","object":"model","created":1738409840,"owned_by":"qwen","model_name":"qwen-plus-2025-04-28","context_length":131072,"max_input_tokens":98304,"max_output_tokens":8192,"quantization":null,"retirement_date":"2026-10-09","description":"The Plus model of the Qwen3 series, effectively integrates thinking mode and non-thinking mode, allowing for mode switching during conversations. Its reasoning capabilities significantly surpass those of QwQ, and its general capabilities notably exceed those of Qwen2.5-Plus, reaching the SOTA level in the same scale within the industry. This model is the snapshot from April 28, 2025.","source":"https://www.alibabacloud.com/help/en/model-studio/models","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.6000000000000005e-7,"output_cost_per_token":7.799999999999999e-7,"output_cost_per_reasoning_token":2.6e-6},"list_pricing":{"input_cost_per_token":4.0000000000000003e-7,"output_cost_per_token":1.2e-6,"output_cost_per_reasoning_token":4e-6},"discount":0.35,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":1},{"id":"qwen-plus-2025-07-14","object":"model","created":1738409840,"owned_by":"qwen","mode":"chat","context_length":131072,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.6000000000000005e-7,"output_cost_per_token":7.799999999999999e-7,"output_cost_per_reasoning_token":2.6e-6},"pricing_endpoint":"qwen/qwen-plus-2025-07-14","regions":[{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"qwen/qwen-plus-2025-07-14","object":"model","created":1738409840,"owned_by":"qwen","model_name":"qwen-plus-2025-07-14","context_length":131072,"max_input_tokens":98304,"max_output_tokens":16384,"quantization":null,"retirement_date":"2026-10-09","description":"The Plus model of the Qwen3 Series, achieving effective integration of thinking mode and non-thinking mode, allows switching modes during conversations. This is a snapshot from July 14, 2025. Compared to the previous version, there has been a significant improvement in both Chinese and English capabilities under non-thinking mode, with enhanced tool-calling abilities.","source":"https://www.alibabacloud.com/help/en/model-studio/models","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.6000000000000005e-7,"output_cost_per_token":7.799999999999999e-7,"output_cost_per_reasoning_token":2.6e-6},"list_pricing":{"input_cost_per_token":4.0000000000000003e-7,"output_cost_per_token":1.2e-6,"output_cost_per_reasoning_token":4e-6},"discount":0.35,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":1},{"id":"qwen-plus-2025-12-01","object":"model","created":1738409840,"owned_by":"qwen","mode":"chat","context_length":1000000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"tiered_pricing":[{"range":[0,256000],"input_cost_per_token":2.6000000000000005e-7,"output_cost_per_token":7.799999999999999e-7,"output_cost_per_reasoning_token":2.6e-6},{"range":[256000,1000000],"input_cost_per_token":7.799999999999999e-7,"output_cost_per_token":2.34e-6,"output_cost_per_reasoning_token":7.8e-6}],"input_cost_per_token":2.6000000000000005e-7,"output_cost_per_token":7.799999999999999e-7,"output_cost_per_reasoning_token":2.6e-6},"pricing_endpoint":"qwen/qwen-plus-2025-12-01","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"qwen/qwen-plus-2025-12-01@eu","object":"model","created":1738409840,"owned_by":"qwen","model_name":"qwen-plus-2025-12-01","context_length":1000000,"max_input_tokens":997952,"max_output_tokens":32768,"quantization":null,"retirement_date":"2026-10-09","description":"This version is a snapshot as of December 1, 2025, and features improved reasoning capabilities compared to the July 28 snapshot. Agent capabilities and multi-turn tool invocation abilities have been further enhanced, and performance on subjective creative tasks has improved significantly. It supports a context length of up to 1 million tokens, with tiered pricing based on context length.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"tiered_pricing":[{"range":[0,256000],"input_cost_per_token":2.6000000000000005e-7,"output_cost_per_token":7.799999999999999e-7,"output_cost_per_reasoning_token":2.6e-6},{"range":[256000,1000000],"input_cost_per_token":7.799999999999999e-7,"output_cost_per_token":2.34e-6,"output_cost_per_reasoning_token":7.8e-6}],"input_cost_per_token":2.6000000000000005e-7,"output_cost_per_token":7.799999999999999e-7,"output_cost_per_reasoning_token":2.6e-6},"list_pricing":{"tiered_pricing":[{"range":[0,256000],"input_cost_per_token":4.0000000000000003e-7,"output_cost_per_token":1.2e-6,"output_cost_per_reasoning_token":4e-6},{"range":[256000,1000000],"input_cost_per_token":1.2e-6,"output_cost_per_token":3.6000000000000003e-6,"output_cost_per_reasoning_token":0.000012}],"input_cost_per_token":4.0000000000000003e-7,"output_cost_per_token":1.2e-6,"output_cost_per_reasoning_token":4e-6},"discount":0.35,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":null,"alias_of":null},{"id":"qwen/qwen-plus-2025-12-01","object":"model","created":1738409840,"owned_by":"qwen","model_name":"qwen-plus-2025-12-01","context_length":1000000,"max_input_tokens":997952,"max_output_tokens":32768,"quantization":null,"retirement_date":"2026-10-09","description":"This version is a snapshot as of December 1, 2025, and features improved reasoning capabilities compared to the July 28 snapshot. Agent capabilities and multi-turn tool invocation abilities have been further enhanced, and performance on subjective creative tasks has improved significantly. It supports a context length of up to 1 million tokens, with tiered pricing based on context length.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"tiered_pricing":[{"range":[0,256000],"input_cost_per_token":2.6000000000000005e-7,"output_cost_per_token":7.799999999999999e-7,"output_cost_per_reasoning_token":2.6e-6},{"range":[256000,1000000],"input_cost_per_token":7.799999999999999e-7,"output_cost_per_token":2.34e-6,"output_cost_per_reasoning_token":7.8e-6}],"input_cost_per_token":2.6000000000000005e-7,"output_cost_per_token":7.799999999999999e-7,"output_cost_per_reasoning_token":2.6e-6},"list_pricing":{"tiered_pricing":[{"range":[0,256000],"input_cost_per_token":4.0000000000000003e-7,"output_cost_per_token":1.2e-6,"output_cost_per_reasoning_token":4e-6},{"range":[256000,1000000],"input_cost_per_token":1.2e-6,"output_cost_per_token":3.6000000000000003e-6,"output_cost_per_reasoning_token":0.000012}],"input_cost_per_token":4.0000000000000003e-7,"output_cost_per_token":1.2e-6,"output_cost_per_reasoning_token":4e-6},"discount":0.35,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":2},{"id":"qwen-plus-latest","object":"model","created":1738409840,"owned_by":"qwen","mode":"chat","context_length":1000000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"tiered_pricing":[{"range":[0,256000],"input_cost_per_token":2.6000000000000005e-7,"output_cost_per_token":7.799999999999999e-7,"output_cost_per_reasoning_token":2.6e-6},{"range":[256000,1000000],"input_cost_per_token":7.799999999999999e-7,"output_cost_per_token":2.34e-6,"output_cost_per_reasoning_token":7.8e-6}],"input_cost_per_token":2.6000000000000005e-7,"output_cost_per_token":7.799999999999999e-7,"output_cost_per_reasoning_token":2.6e-6},"pricing_endpoint":"qwen/qwen-plus-latest","regions":[{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"qwen/qwen-plus-latest","object":"model","created":1738409840,"owned_by":"qwen","model_name":"qwen-plus-latest","context_length":1000000,"max_input_tokens":995904,"max_output_tokens":32768,"quantization":null,"retirement_date":"2026-10-09","description":"Balanced model in the Qwen series, balancing inference quality and speed between Qwen-Max and Qwen-Turbo, suitable for medium-complexity tasks. This model is dynamically updated; model updates are not announced in advance.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"tiered_pricing":[{"range":[0,256000],"input_cost_per_token":2.6000000000000005e-7,"output_cost_per_token":7.799999999999999e-7,"output_cost_per_reasoning_token":2.6e-6},{"range":[256000,1000000],"input_cost_per_token":7.799999999999999e-7,"output_cost_per_token":2.34e-6,"output_cost_per_reasoning_token":7.8e-6}],"input_cost_per_token":2.6000000000000005e-7,"output_cost_per_token":7.799999999999999e-7,"output_cost_per_reasoning_token":2.6e-6},"list_pricing":{"tiered_pricing":[{"range":[0,256000],"input_cost_per_token":4.0000000000000003e-7,"output_cost_per_token":1.2e-6,"output_cost_per_reasoning_token":4e-6},{"range":[256000,1000000],"input_cost_per_token":1.2e-6,"output_cost_per_token":3.6000000000000003e-6,"output_cost_per_reasoning_token":0.000012}],"input_cost_per_token":4.0000000000000003e-7,"output_cost_per_token":1.2e-6,"output_cost_per_reasoning_token":4e-6},"discount":0.35,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":1},{"id":"sonar","object":"model","created":1738013808,"owned_by":"perplexity","mode":"chat","context_length":127072,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":1e-6,"search_context_cost_per_query":{"search_context_size_low":0.005,"search_context_size_high":0.005,"search_context_size_medium":0.005}},"pricing_endpoint":"perplexityai/sonar","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"perplexityai/sonar","object":"model","created":1738013808,"owned_by":"perplexityai","model_name":"sonar","context_length":127072,"max_input_tokens":128000,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"Sonar is lightweight, affordable, fast, and simple to use — now featuring citations and the ability to customize sources.","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":1e-6,"search_context_cost_per_query":{"search_context_size_low":0.005,"search_context_size_high":0.005,"search_context_size_medium":0.005}},"list_pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":1e-6,"search_context_cost_per_query":{"search_context_size_low":0.005,"search_context_size_high":0.005,"search_context_size_medium":0.005}},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":1},{"id":"deepseek-r1-distill-llama-70b","object":"model","created":1737663169,"owned_by":"deepseek","mode":"chat","context_length":131072,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":7e-7,"output_cost_per_token":8e-7},"pricing_endpoint":"deepinfra/deepseek-ai/DeepSeek-R1-Distill-Llama-70B","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"deepinfra/deepseek-ai/DeepSeek-R1-Distill-Llama-70B","object":"model","created":1737663169,"owned_by":"deepinfra","model_name":"deepseek-ai/DeepSeek-R1-Distill-Llama-70B","context_length":131072,"max_input_tokens":null,"max_output_tokens":16384,"quantization":null,"retirement_date":"2026-06-11","description":"DeepSeek R1 Distill Llama 70B is a distilled large language model based on [Llama-3.3-70B-Instruct](/meta-llama/llama-3.3-70b-instruct), using outputs from [DeepSeek R1](/deepseek/deepseek-r1). The model combines advanced distillation techniques to achieve high performance across...","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":7e-7,"output_cost_per_token":8e-7},"list_pricing":{"input_cost_per_token":7e-7,"output_cost_per_token":8e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"phi-4","object":"model","created":1736489872,"owned_by":"microsoft","mode":"chat","context_length":16384,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":7e-8,"output_cost_per_token":1.4e-7},"pricing_endpoint":"deepinfra/microsoft/phi-4","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"deepinfra/microsoft/phi-4","object":"model","created":1736489872,"owned_by":"deepinfra","model_name":"microsoft/phi-4","context_length":16384,"max_input_tokens":4096,"max_output_tokens":null,"quantization":"bf16","retirement_date":null,"description":"Microsoft Research Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations with limited memory or where quick responses are needed.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":7e-8,"output_cost_per_token":1.4e-7},"list_pricing":{"input_cost_per_token":7e-8,"output_cost_per_token":1.4e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"command-r7b-12-2024","object":"model","created":1734158152,"owned_by":"cohere","mode":"chat","context_length":132000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.75e-8,"output_cost_per_token":1.5e-7},"pricing_endpoint":"cohere/command-r7b-12-2024","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"cohere/command-r7b-12-2024","object":"model","created":1734158152,"owned_by":"cohere","model_name":"command-r7b-12-2024","context_length":132000,"max_input_tokens":128000,"max_output_tokens":4000,"quantization":null,"retirement_date":null,"description":"Command R7B (12-2024) is a small, fast update of the Command R+ model, delivered in December 2024.","source":"https://docs.cohere.com/v2/docs/command-r7b","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.75e-8,"output_cost_per_token":1.5e-7},"list_pricing":{"input_cost_per_token":3.75e-8,"output_cost_per_token":1.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":1},{"id":"nova-lite","object":"model","created":1733437363,"owned_by":"amazon","mode":"chat","context_length":300000,"capabilities":{"input_modalities":["text","image","file","video"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6e-8,"output_cost_per_token":2.4e-7,"cache_read_input_token_cost":1.5e-8},"pricing_endpoint":"amazon/amazon.nova-lite-v1:0","regions":[{"code":"eu","name":"Europe"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"amazon/amazon.nova-lite-v1:0","object":"model","created":1733437363,"owned_by":"amazon","model_name":"amazon.nova-lite-v1:0","context_length":300000,"max_input_tokens":300000,"max_output_tokens":5120,"quantization":null,"retirement_date":null,"description":"Amazon Nova Lite 1.0 is a very low-cost multimodal model from Amazon that focused on fast processing of image, video, and text inputs to generate text output.","source":null,"capabilities":{"input_modalities":["text","image","file","video"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6e-8,"output_cost_per_token":2.4e-7,"cache_read_input_token_cost":1.5e-8},"list_pricing":{"input_cost_per_token":6e-8,"output_cost_per_token":2.4e-7,"cache_read_input_token_cost":1.5e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/amazon.nova-lite-v1:0@us","object":"model","created":1733437363,"owned_by":"amazon","model_name":"amazon.nova-lite-v1:0","context_length":300000,"max_input_tokens":300000,"max_output_tokens":5120,"quantization":null,"retirement_date":null,"description":"Amazon Nova Lite 1.0 is a very low-cost multimodal model from Amazon that focused on fast processing of image, video, and text inputs to generate text output.","source":null,"capabilities":{"input_modalities":["text","image","file","video"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6e-8,"output_cost_per_token":2.4e-7,"cache_read_input_token_cost":1.5e-8},"list_pricing":{"input_cost_per_token":6e-8,"output_cost_per_token":2.4e-7,"cache_read_input_token_cost":1.5e-8},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"nova-micro","object":"model","created":1733437237,"owned_by":"amazon","mode":"chat","context_length":128000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.5e-8,"output_cost_per_token":1.4e-7,"cache_read_input_token_cost":8.75e-9},"pricing_endpoint":"amazon/amazon.nova-micro-v1:0","regions":[{"code":"eu","name":"Europe"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"amazon/amazon.nova-micro-v1:0","object":"model","created":1733437237,"owned_by":"amazon","model_name":"amazon.nova-micro-v1:0","context_length":128000,"max_input_tokens":128000,"max_output_tokens":5120,"quantization":null,"retirement_date":null,"description":"Amazon Nova Micro 1.0 is a text-only model that delivers the lowest latency responses in the Amazon Nova family of models at a very low cost.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.5e-8,"output_cost_per_token":1.4e-7,"cache_read_input_token_cost":8.75e-9},"list_pricing":{"input_cost_per_token":3.5e-8,"output_cost_per_token":1.4e-7,"cache_read_input_token_cost":8.75e-9},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/amazon.nova-micro-v1:0@us","object":"model","created":1733437237,"owned_by":"amazon","model_name":"amazon.nova-micro-v1:0","context_length":128000,"max_input_tokens":128000,"max_output_tokens":5120,"quantization":null,"retirement_date":null,"description":"Amazon Nova Micro 1.0 is a text-only model that delivers the lowest latency responses in the Amazon Nova family of models at a very low cost.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.5e-8,"output_cost_per_token":1.4e-7,"cache_read_input_token_cost":8.75e-9},"list_pricing":{"input_cost_per_token":3.5e-8,"output_cost_per_token":1.4e-7,"cache_read_input_token_cost":8.75e-9},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"nova-pro","object":"model","created":1733436303,"owned_by":"amazon","mode":"chat","context_length":300000,"capabilities":{"input_modalities":["text","image","file","video"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":8e-7,"output_cost_per_token":3.2e-6,"input_cost_per_token_flex":4e-7,"output_cost_per_token_flex":1.6e-6,"cache_read_input_token_cost":2e-7,"input_cost_per_token_priority":1.4e-6,"output_cost_per_token_priority":5.6e-6,"cache_read_input_token_cost_flex":1e-7,"cache_read_input_token_cost_priority":3.5e-7},"pricing_endpoint":"amazon/amazon.nova-pro-v1:0","regions":[{"code":"eu","name":"Europe"},{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"amazon/amazon.nova-pro-v1:0","object":"model","created":1733436303,"owned_by":"amazon","model_name":"amazon.nova-pro-v1:0","context_length":300000,"max_input_tokens":300000,"max_output_tokens":5120,"quantization":null,"retirement_date":null,"description":"Amazon Nova Pro 1.0 is a capable multimodal model from Amazon focused on providing a combination of accuracy, speed, and cost for a wide range of tasks.","source":null,"capabilities":{"input_modalities":["text","image","file","video"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":8e-7,"output_cost_per_token":3.2e-6,"input_cost_per_token_flex":4e-7,"output_cost_per_token_flex":1.6e-6,"cache_read_input_token_cost":2e-7,"input_cost_per_token_priority":1.4e-6,"output_cost_per_token_priority":5.6e-6,"cache_read_input_token_cost_flex":1e-7,"cache_read_input_token_cost_priority":3.5e-7},"list_pricing":{"input_cost_per_token":8e-7,"output_cost_per_token":3.2e-6,"input_cost_per_token_flex":4e-7,"output_cost_per_token_flex":1.6e-6,"cache_read_input_token_cost":2e-7,"input_cost_per_token_priority":1.4e-6,"output_cost_per_token_priority":5.6e-6,"cache_read_input_token_cost_flex":1e-7,"cache_read_input_token_cost_priority":3.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"amazon/amazon.nova-pro-v1:0@us","object":"model","created":1733436303,"owned_by":"amazon","model_name":"amazon.nova-pro-v1:0","context_length":300000,"max_input_tokens":300000,"max_output_tokens":5120,"quantization":null,"retirement_date":null,"description":"Amazon Nova Pro 1.0 is a capable multimodal model from Amazon focused on providing a combination of accuracy, speed, and cost for a wide range of tasks.","source":null,"capabilities":{"input_modalities":["text","image","file","video"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":8e-7,"output_cost_per_token":3.2e-6,"input_cost_per_token_flex":4e-7,"output_cost_per_token_flex":1.6e-6,"cache_read_input_token_cost":2e-7,"input_cost_per_token_priority":1.4e-6,"output_cost_per_token_priority":5.6e-6,"cache_read_input_token_cost_flex":1e-7,"cache_read_input_token_cost_priority":3.5e-7},"list_pricing":{"input_cost_per_token":8e-7,"output_cost_per_token":3.2e-6,"input_cost_per_token_flex":4e-7,"output_cost_per_token_flex":1.6e-6,"cache_read_input_token_cost":2e-7,"input_cost_per_token_priority":1.4e-6,"output_cost_per_token_priority":5.6e-6,"cache_read_input_token_cost_flex":1e-7,"cache_read_input_token_cost_priority":3.5e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"gpt-4o-2024-08-06","object":"model","created":1732127594,"owned_by":"openai","mode":"chat","context_length":128000,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2.5e-6,"output_cost_per_token":0.00001,"cache_read_input_token_cost":1.25e-6,"input_cost_per_token_batches":1.25e-6,"input_cost_per_token_priority":4.25e-6,"output_cost_per_token_batches":5e-6,"output_cost_per_token_priority":0.000017,"cache_read_input_token_cost_priority":2.125e-6},"pricing_endpoint":"openai/gpt-4o-2024-08-06","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"openai/gpt-4o-2024-08-06","object":"model","created":1732127594,"owned_by":"openai","model_name":"gpt-4o-2024-08-06","context_length":128000,"max_input_tokens":128000,"max_output_tokens":16384,"quantization":null,"retirement_date":null,"description":"GPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2.5e-6,"output_cost_per_token":0.00001,"cache_read_input_token_cost":1.25e-6,"input_cost_per_token_batches":1.25e-6,"input_cost_per_token_priority":4.25e-6,"output_cost_per_token_batches":5e-6,"output_cost_per_token_priority":0.000017,"cache_read_input_token_cost_priority":2.125e-6},"list_pricing":{"input_cost_per_token":2.5e-6,"output_cost_per_token":0.00001,"cache_read_input_token_cost":1.25e-6,"input_cost_per_token_batches":1.25e-6,"input_cost_per_token_priority":4.25e-6,"output_cost_per_token_batches":5e-6,"output_cost_per_token_priority":0.000017,"cache_read_input_token_cost_priority":2.125e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":1},{"id":"gpt-4o-2024-11-20","object":"model","created":1732127594,"owned_by":"openai","mode":"chat","context_length":128000,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2.5e-6,"output_cost_per_token":0.00001,"cache_read_input_token_cost":1.25e-6,"input_cost_per_token_batches":1.25e-6,"input_cost_per_token_priority":4.25e-6,"output_cost_per_token_batches":5e-6,"output_cost_per_token_priority":0.000017,"cache_read_input_token_cost_priority":2.125e-6},"pricing_endpoint":"openai/gpt-4o-2024-11-20","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"openai/gpt-4o-2024-11-20","object":"model","created":1732127594,"owned_by":"openai","model_name":"gpt-4o-2024-11-20","context_length":128000,"max_input_tokens":128000,"max_output_tokens":16384,"quantization":null,"retirement_date":null,"description":"GPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":2.5e-6,"output_cost_per_token":0.00001,"cache_read_input_token_cost":1.25e-6,"input_cost_per_token_batches":1.25e-6,"input_cost_per_token_priority":4.25e-6,"output_cost_per_token_batches":5e-6,"output_cost_per_token_priority":0.000017,"cache_read_input_token_cost_priority":2.125e-6},"list_pricing":{"input_cost_per_token":2.5e-6,"output_cost_per_token":0.00001,"cache_read_input_token_cost":1.25e-6,"input_cost_per_token_batches":1.25e-6,"input_cost_per_token_priority":4.25e-6,"output_cost_per_token_batches":5e-6,"output_cost_per_token_priority":0.000017,"cache_read_input_token_cost_priority":2.125e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":1},{"id":"mistral-large-2407","object":"model","created":1731978415,"owned_by":"mistral","mode":"chat","context_length":131072,"capabilities":{"input_modalities":["text","file"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":6e-6,"cache_read_input_token_cost":2e-7},"pricing_endpoint":"mistral/mistral-large-2407","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"mistral/mistral-large-2407@eu","object":"model","created":1731978415,"owned_by":"mistral","model_name":"mistral-large-2407","context_length":131072,"max_input_tokens":null,"max_output_tokens":104857,"quantization":null,"retirement_date":null,"description":"This is Mistral AI's flagship model, Mistral Large 2 (version mistral-large-2407). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more.","source":null,"capabilities":{"input_modalities":["text","file"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.2e-6,"output_cost_per_token":6.6e-6,"cache_read_input_token_cost":2.2e-7},"list_pricing":{"input_cost_per_token":2.2e-6,"output_cost_per_token":6.6e-6,"cache_read_input_token_cost":2.2e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"mistral/mistral-large-2407","object":"model","created":1731978415,"owned_by":"mistral","model_name":"mistral-large-2407","context_length":131072,"max_input_tokens":null,"max_output_tokens":104857,"quantization":null,"retirement_date":null,"description":"This is Mistral AI's flagship model, Mistral Large 2 (version mistral-large-2407). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more.","source":null,"capabilities":{"input_modalities":["text","file"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":6e-6,"cache_read_input_token_cost":2e-7},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":6e-6,"cache_read_input_token_cost":2e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"qwen2.5-coder-32b-instruct","object":"model","created":1731368400,"owned_by":"qwen","mode":"chat","context_length":32768,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6.6e-7,"output_cost_per_token":1e-6},"pricing_endpoint":"cloudflare/@cf/qwen/qwen2.5-coder-32b-instruct","regions":[{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"cloudflare/@cf/qwen/qwen2.5-coder-32b-instruct","object":"model","created":1731368400,"owned_by":"cloudflare","model_name":"@cf/qwen/qwen2.5-coder-32b-instruct","context_length":32768,"max_input_tokens":32768,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen).","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":6.6e-7,"output_cost_per_token":1e-6},"list_pricing":{"input_cost_per_token":6.6e-7,"output_cost_per_token":1e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"ministral-8b-latest","object":"model","created":1729123200,"owned_by":"mistral","mode":"chat","context_length":262144,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":1.5e-7,"cache_read_input_token_cost":1.5e-8,"input_cost_per_token_batches":7.5e-8,"output_cost_per_token_batches":7.5e-8,"cache_read_input_token_cost_batches":7.5e-9},"pricing_endpoint":"mistral/ministral-8b-latest","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"mistral/ministral-8b-latest@eu","object":"model","created":1729123200,"owned_by":"mistral","model_name":"ministral-8b-latest","context_length":262144,"max_input_tokens":262144,"max_output_tokens":102400,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.65e-7,"output_cost_per_token":1.65e-7,"cache_read_input_token_cost":1.65e-8,"input_cost_per_token_batches":8.25e-8,"output_cost_per_token_batches":8.25e-8,"cache_read_input_token_cost_batches":8.25e-9},"list_pricing":{"input_cost_per_token":1.65e-7,"output_cost_per_token":1.65e-7,"cache_read_input_token_cost":1.65e-8,"input_cost_per_token_batches":8.25e-8,"output_cost_per_token_batches":8.25e-8,"cache_read_input_token_cost_batches":8.25e-9},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"mistral/ministral-8b-latest","object":"model","created":1729123200,"owned_by":"mistral","model_name":"ministral-8b-latest","context_length":262144,"max_input_tokens":262144,"max_output_tokens":102400,"quantization":null,"retirement_date":null,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":true,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":1.5e-7,"cache_read_input_token_cost":1.5e-8,"input_cost_per_token_batches":7.5e-8,"output_cost_per_token_batches":7.5e-8,"cache_read_input_token_cost_batches":7.5e-9},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":1.5e-7,"cache_read_input_token_cost":1.5e-8,"input_cost_per_token_batches":7.5e-8,"output_cost_per_token_batches":7.5e-8,"cache_read_input_token_cost_batches":7.5e-9},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"llama-3.2-11b-vision-instruct","object":"model","created":1727222400,"owned_by":"meta","mode":"chat","context_length":131072,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.45e-7,"output_cost_per_token":3.45e-7},"pricing_endpoint":"deepinfra/meta-llama/Llama-3.2-11B-Vision-Instruct","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"deepinfra/meta-llama/Llama-3.2-11B-Vision-Instruct","object":"model","created":1727222400,"owned_by":"deepinfra","model_name":"meta-llama/Llama-3.2-11B-Vision-Instruct","context_length":131072,"max_input_tokens":null,"max_output_tokens":16384,"quantization":null,"retirement_date":"2026-07-17","description":"Llama 3.2 11B Vision is a multimodal model with 11 billion parameters, designed to handle tasks combining visual and textual data. It excels in tasks such as image captioning and...","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.45e-7,"output_cost_per_token":3.45e-7},"list_pricing":{"input_cost_per_token":3.45e-7,"output_cost_per_token":3.45e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"llama-3.2-1b-instruct","object":"model","created":1727222400,"owned_by":"meta","mode":"chat","context_length":60000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.7e-8,"output_cost_per_token":2.01e-7},"pricing_endpoint":"cloudflare/@cf/meta/llama-3.2-1b-instruct","regions":[{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"cloudflare/@cf/meta/llama-3.2-1b-instruct","object":"model","created":1727222400,"owned_by":"cloudflare","model_name":"@cf/meta/llama-3.2-1b-instruct","context_length":60000,"max_input_tokens":60000,"max_output_tokens":null,"quantization":null,"retirement_date":"2026-11-20","description":"Llama 3.2 1B is a 1-billion-parameter language model focused on efficiently performing natural language tasks, such as summarization, dialogue, and multilingual text analysis.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":false,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.7e-8,"output_cost_per_token":2.01e-7},"list_pricing":{"input_cost_per_token":2.7e-8,"output_cost_per_token":2.01e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"qwen2.5-72b-instruct","object":"model","created":1726704000,"owned_by":"qwen","mode":"chat","context_length":32768,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.6e-7,"output_cost_per_token":4.0000000000000003e-7},"pricing_endpoint":"deepinfra/Qwen/Qwen2.5-72B-Instruct","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"deepinfra/Qwen/Qwen2.5-72B-Instruct","object":"model","created":1726704000,"owned_by":"deepinfra","model_name":"Qwen/Qwen2.5-72B-Instruct","context_length":32768,"max_input_tokens":32768,"max_output_tokens":16384,"quantization":"fp8","retirement_date":null,"description":"Qwen2.5 72B is the latest series of Qwen large language models.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3.6e-7,"output_cost_per_token":4.0000000000000003e-7},"list_pricing":{"input_cost_per_token":3.6e-7,"output_cost_per_token":4.0000000000000003e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"command-r-08-2024","object":"model","created":1724976000,"owned_by":"cohere","mode":"chat","context_length":128000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7},"pricing_endpoint":"cohere/command-r-08-2024","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"cohere/command-r-08-2024","object":"model","created":1724976000,"owned_by":"cohere","model_name":"command-r-08-2024","context_length":128000,"max_input_tokens":128000,"max_output_tokens":4000,"quantization":null,"retirement_date":null,"description":"command-r-08-2024 is an update of the Command R with improved performance for multilingual retrieval-augmented generation (RAG) and tool use.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":1},{"id":"command-r-plus-08-2024","object":"model","created":1724976000,"owned_by":"cohere","mode":"chat","context_length":128000,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.5e-6,"output_cost_per_token":0.00001},"pricing_endpoint":"cohere/command-r-plus-08-2024","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"cohere/command-r-plus-08-2024","object":"model","created":1724976000,"owned_by":"cohere","model_name":"command-r-plus-08-2024","context_length":128000,"max_input_tokens":128000,"max_output_tokens":4000,"quantization":null,"retirement_date":null,"description":"command-r-plus-08-2024 is an update of the Command R+ with roughly 50% higher throughput and 25% lower latencies as compared to the previous Command R+ version, while keeping the hardware footprint...","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.5e-6,"output_cost_per_token":0.00001},"list_pricing":{"input_cost_per_token":2.5e-6,"output_cost_per_token":0.00001},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":1},{"id":"hermes-3-llama-3.1-70b","object":"model","created":1723939200,"owned_by":"nousresearch","mode":"chat","context_length":131072,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":7e-7,"output_cost_per_token":7e-7},"pricing_endpoint":"deepinfra/NousResearch/Hermes-3-Llama-3.1-70B","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"deepinfra/NousResearch/Hermes-3-Llama-3.1-70B","object":"model","created":1723939200,"owned_by":"deepinfra","model_name":"NousResearch/Hermes-3-Llama-3.1-70B","context_length":131072,"max_input_tokens":null,"max_output_tokens":16384,"quantization":null,"retirement_date":"2026-11-02","description":"Hermes 3 is a generalist language model with many improvements over [Hermes 2](/models/nousresearch/nous-hermes-2-mistral-7b-dpo), including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context coherence, and improvements across the...","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":false,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":false,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":7e-7,"output_cost_per_token":7e-7},"list_pricing":{"input_cost_per_token":7e-7,"output_cost_per_token":7e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"hermes-3-llama-3.1-405b","object":"model","created":1723766400,"owned_by":"nousresearch","mode":"chat","context_length":131072,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":1e-6},"pricing_endpoint":"deepinfra/NousResearch/Hermes-3-Llama-3.1-405B","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"deepinfra/NousResearch/Hermes-3-Llama-3.1-405B","object":"model","created":1723766400,"owned_by":"deepinfra","model_name":"NousResearch/Hermes-3-Llama-3.1-405B","context_length":131072,"max_input_tokens":null,"max_output_tokens":16384,"quantization":null,"retirement_date":"2026-11-02","description":"Hermes 3 is a generalist language model with many improvements over Hermes 2, including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context coherence, and improvements across the...","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":1e-6},"list_pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":1e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"gpt-4o-mini-2024-07-18","object":"model","created":1721260800,"owned_by":"openai","mode":"chat","context_length":128000,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":7.5e-8,"input_cost_per_token_batches":7.5e-8,"input_cost_per_token_priority":2.5e-7,"output_cost_per_token_batches":3e-7,"search_context_cost_per_query":{"search_context_size_low":0.025,"search_context_size_high":0.025,"search_context_size_medium":0.025},"output_cost_per_token_priority":1e-6,"cache_read_input_token_cost_priority":1.25e-7},"pricing_endpoint":"openai/gpt-4o-mini-2024-07-18","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"openai/gpt-4o-mini-2024-07-18","object":"model","created":1721260800,"owned_by":"openai","model_name":"gpt-4o-mini-2024-07-18","context_length":128000,"max_input_tokens":128000,"max_output_tokens":16384,"quantization":null,"retirement_date":null,"description":"GPT-4o mini is OpenAI's newest model after GPT-4 Omni, supporting both text and image inputs with text outputs.","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":true,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":true,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":7.5e-8,"input_cost_per_token_batches":7.5e-8,"input_cost_per_token_priority":2.5e-7,"output_cost_per_token_batches":3e-7,"search_context_cost_per_query":{"search_context_size_low":0.025,"search_context_size_high":0.025,"search_context_size_medium":0.025},"output_cost_per_token_priority":1e-6,"cache_read_input_token_cost_priority":1.25e-7},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":7.5e-8,"input_cost_per_token_batches":7.5e-8,"input_cost_per_token_priority":2.5e-7,"output_cost_per_token_batches":3e-7,"search_context_cost_per_query":{"search_context_size_low":0.025,"search_context_size_high":0.025,"search_context_size_medium":0.025},"output_cost_per_token_priority":1e-6,"cache_read_input_token_cost_priority":1.25e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":false,"alias_of":null}],"endpoint_count":1},{"id":"mistral-large-latest","object":"model","created":1708905600,"owned_by":"mistral","mode":"chat","context_length":1048576,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":6e-6,"cache_read_input_token_cost":2e-7},"pricing_endpoint":"mistral/mistral-large-latest","regions":[{"code":"eu","name":"Europe"},{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"mistral/mistral-large-latest@eu","object":"model","created":1708905600,"owned_by":"mistral","model_name":"mistral-large-latest","context_length":1048576,"max_input_tokens":262144,"max_output_tokens":102400,"quantization":null,"retirement_date":null,"description":"This is Mistral AI's flagship model, Mistral Large 2 (version mistral-large-2407). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more.","source":"https://docs.mistral.ai/models/mistral-large-3-25-12","capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2.2e-6,"output_cost_per_token":6.6e-6,"cache_read_input_token_cost":2.2e-7},"list_pricing":{"input_cost_per_token":2.2e-6,"output_cost_per_token":6.6e-6,"cache_read_input_token_cost":2.2e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"eu","name":"Europe"}],"zero_data_retention":true,"alias_of":null},{"id":"mistral/mistral-large-latest","object":"model","created":1708905600,"owned_by":"mistral","model_name":"mistral-large-latest","context_length":1048576,"max_input_tokens":262144,"max_output_tokens":102400,"quantization":null,"retirement_date":null,"description":"This is Mistral AI's flagship model, Mistral Large 2 (version mistral-large-2407). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more.","source":"https://docs.mistral.ai/models/mistral-large-3-25-12","capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":6e-6,"cache_read_input_token_cost":2e-7},"list_pricing":{"input_cost_per_token":2e-6,"output_cost_per_token":6e-6,"cache_read_input_token_cost":2e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":2},{"id":"gpt-3.5-turbo-16k","object":"model","created":1693180800,"owned_by":"openai","mode":"chat","context_length":16385,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":4e-6},"pricing_endpoint":"microsoft/gpt-35-turbo-16k","regions":[{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"microsoft/gpt-35-turbo-16k","object":"model","created":1693180800,"owned_by":"microsoft","model_name":"gpt-35-turbo-16k","context_length":16385,"max_input_tokens":null,"max_output_tokens":4096,"quantization":null,"retirement_date":null,"description":"","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":4e-6},"list_pricing":{"input_cost_per_token":3e-6,"output_cost_per_token":4e-6},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":1},{"id":"mythomax-l2-13b","object":"model","created":1688256000,"owned_by":"gryphe","mode":"chat","context_length":4096,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4e-7,"output_cost_per_token":4e-7},"pricing_endpoint":"deepinfra/Gryphe/MythoMax-L2-13b","regions":[{"code":"us","name":"United States"}],"alias_of":null,"endpoints":[{"id":"deepinfra/Gryphe/MythoMax-L2-13b","object":"model","created":1688256000,"owned_by":"deepinfra","model_name":"Gryphe/MythoMax-L2-13b","context_length":4096,"max_input_tokens":null,"max_output_tokens":null,"quantization":null,"retirement_date":null,"description":"One of the highest performing and most popular fine-tunes of Llama 2 13B, with rich descriptions and roleplay. #merge","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":4e-7,"output_cost_per_token":4e-7},"list_pricing":{"input_cost_per_token":4e-7,"output_cost_per_token":4e-7},"discount":null,"discount_ends_at":null,"regions":[{"code":"us","name":"United States"}],"zero_data_retention":true,"alias_of":null}],"endpoint_count":1},{"id":"gpt-4","object":"model","created":1685232000,"owned_by":"openai","mode":"chat","context_length":8191,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":0.00003,"output_cost_per_token":0.00006},"pricing_endpoint":"microsoft/gpt-4","regions":[{"code":"global","name":"Global"}],"alias_of":null,"endpoints":[{"id":"microsoft/gpt-4","object":"model","created":1685232000,"owned_by":"microsoft","model_name":"gpt-4","context_length":8191,"max_input_tokens":null,"max_output_tokens":4096,"quantization":null,"retirement_date":null,"description":"OpenAI's flagship model, GPT-4 is a large-scale multimodal language model capable of solving difficult problems with greater accuracy than previous models due to its broader general knowledge and advanced reasoning...","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_batch":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":false,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false},"pricing":{"input_cost_per_token":0.00003,"output_cost_per_token":0.00006},"list_pricing":{"input_cost_per_token":0.00003,"output_cost_per_token":0.00006},"discount":null,"discount_ends_at":null,"regions":[{"code":"global","name":"Global"}],"zero_data_retention":null,"alias_of":null}],"endpoint_count":1}]}