{"object":"list","data":[{"id":"databricks/databricks-gemini-3-7-flash","object":"model","created":1790140226,"owned_by":"databricks","model_name":"databricks-gemini-3-7-flash","context_length":1048576,"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_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":7.4999995e-7,"output_cost_per_token":3.74999975e-6,"cache_read_input_token_cost":7.4999995e-8},"list_pricing":{"input_cost_per_token":7.4999995e-7,"output_cost_per_token":3.74999975e-6,"cache_read_input_token_cost":7.4999995e-8},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"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,"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_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":7.4999995e-7,"output_cost_per_token":3.74999975e-6,"cache_read_input_token_cost":7.4999995e-8},"list_pricing":{"input_cost_per_token":7.4999995e-7,"output_cost_per_token":3.74999975e-6,"cache_read_input_token_cost":7.4999995e-8},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"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,"description":"Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5. It is particularly strong at multi-step changes in large codebases, code...","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":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,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"tonomia/kimi-k3","object":"model","created":1790070582,"owned_by":"tonomia","model_name":"kimi-k3","context_length":null,"description":"","source":null,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":2.8e-6,"output_cost_per_token":0.0000125,"cache_read_input_token_cost":2e-7},"list_pricing":{"input_cost_per_token":2.8e-6,"output_cost_per_token":0.0000125,"cache_read_input_token_cost":2e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"databricks/databricks-gpt-6-astra","object":"model","created":1789744452,"owned_by":"databricks","model_name":"databricks-gpt-6-astra","context_length":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_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":9.9999998e-6,"output_cost_per_token":0.0000499999997,"cache_read_input_token_cost":9.9999998e-7},"list_pricing":{"input_cost_per_token":9.9999998e-6,"output_cost_per_token":0.0000499999997,"cache_read_input_token_cost":9.9999998e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"ovhcloud/Qwen3.8-27B","object":"model","created":1789657955,"owned_by":"ovhcloud","model_name":"Qwen3.8-27B","context_length":262144,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":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":4.7e-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,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"amazon/writer.palmyra-vision-7b","object":"model","created":1789621775,"owned_by":"amazon","model_name":"writer.palmyra-vision-7b","context_length":4096,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":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},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"mistral/zai-glm-5","object":"model","created":1789621775,"owned_by":"mistral","model_name":"zai-glm-5","context_length":1048576,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_tool_choice":true,"supports_computer_use":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,"regions":[{"code":"eu","name":"Europe"}],"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,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_tool_choice":true,"supports_computer_use":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,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"mistral/zai-glm-latest","object":"model","created":1789621775,"owned_by":"mistral","model_name":"zai-glm-latest","context_length":1048576,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_tool_choice":true,"supports_computer_use":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,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"scaleway/qwen3.8-27b","object":"model","created":1789565546,"owned_by":"scaleway","model_name":"qwen3.8-27b","context_length":256000,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":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":6.877799837683923e-7,"output_cost_per_token":3.7827899107261584e-6,"cache_read_input_token_cost":1.375559967536785e-7},"list_pricing":{"input_cost_per_token":6.877799837683923e-7,"output_cost_per_token":3.7827899107261584e-6,"cache_read_input_token_cost":1.375559967536785e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"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,"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_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,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"compactifai/carina-60b","object":"model","created":1788457256,"owned_by":"compactifai","model_name":"carina-60b","context_length":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":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":2e-7},"list_pricing":{"input_cost_per_token":5e-8,"output_cost_per_token":2e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"compactifai/quasar-438b","object":"model","created":1788457256,"owned_by":"compactifai","model_name":"quasar-438b","context_length":1000000,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":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":1.8e-6},"list_pricing":{"input_cost_per_token":6e-7,"output_cost_per_token":1.8e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"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,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":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},"list_pricing":{"input_cost_per_token":4e-7,"output_cost_per_token":2e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"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,"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_tool_choice":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":0.014},"list_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":0.014},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"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,"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_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,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"ionos/Qwen/Qwen3.8-27B","object":"model","created":1788215842,"owned_by":"ionos","model_name":"Qwen/Qwen3.8-27B","context_length":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":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":4.5851998917892826e-7,"output_cost_per_token":3.0950099269577662e-6},"list_pricing":{"input_cost_per_token":4.5851998917892826e-7,"output_cost_per_token":3.0950099269577662e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"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,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":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,"regions":[{"code":"eu","name":"Europe"}],"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,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":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":9e-7,"cache_read_input_token_cost":3e-8},"list_pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":9e-7,"cache_read_input_token_cost":3e-8},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"mistral/mistral-code-latest","object":"model","created":1788066615,"owned_by":"mistral","model_name":"mistral-code-latest","context_length":256000,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":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":9e-7,"cache_read_input_token_cost":3e-8},"list_pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":9e-7,"cache_read_input_token_cost":3e-8},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"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,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":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":1.5e-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,"regions":[{"code":"eu","name":"Europe"}],"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,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":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":1.5e-6,"output_cost_per_token":7.5e-6,"cache_read_input_token_cost":1.5e-7},"list_pricing":{"input_cost_per_token":1.5e-6,"output_cost_per_token":7.5e-6,"cache_read_input_token_cost":1.5e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"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,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":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":1.5e-6,"output_cost_per_token":7.5e-6,"cache_read_input_token_cost":1.5e-7},"list_pricing":{"input_cost_per_token":1.5e-6,"output_cost_per_token":7.5e-6,"cache_read_input_token_cost":1.5e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"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,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":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,"regions":[{"code":"eu","name":"Europe"}],"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,"description":"Served by TensorX at fp8 quantization.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":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,"regions":[{"code":"eu","name":"Europe"}],"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,"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_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,"regions":[{"code":"eu","name":"Europe"}],"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,"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_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,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"mistral/ministral-14b-latest","object":"model","created":1787893793,"owned_by":"mistral","model_name":"ministral-14b-latest","context_length":262144,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":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":2e-7,"output_cost_per_token":2e-7,"cache_read_input_token_cost":2e-8},"list_pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":2e-7,"cache_read_input_token_cost":2e-8},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"mistral/ministral-3b-latest","object":"model","created":1787893793,"owned_by":"mistral","model_name":"ministral-3b-latest","context_length":131072,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":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":1e-7,"output_cost_per_token":1e-7,"cache_read_input_token_cost":1e-8},"list_pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":1e-7,"cache_read_input_token_cost":1e-8},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"mistral/voxtral-small-2507","object":"model","created":1787893793,"owned_by":"mistral","model_name":"voxtral-small-2507","context_length":32768,"description":null,"source":null,"capabilities":{"input_modalities":["text","audio"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":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,"input_cost_per_second":0.00006666666666666667,"output_cost_per_token":4e-7,"cache_read_input_token_cost":1e-8},"list_pricing":{"input_cost_per_token":1e-7,"input_cost_per_second":0.00006666666666666667,"output_cost_per_token":4e-7,"cache_read_input_token_cost":1e-8},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"mistral/voxtral-small-latest","object":"model","created":1787893793,"owned_by":"mistral","model_name":"voxtral-small-latest","context_length":32768,"description":null,"source":null,"capabilities":{"input_modalities":["text","audio"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":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,"input_cost_per_second":0.00006666666666666667,"output_cost_per_token":4e-7,"cache_read_input_token_cost":1e-8},"list_pricing":{"input_cost_per_token":1e-7,"input_cost_per_second":0.00006666666666666667,"output_cost_per_token":4e-7,"cache_read_input_token_cost":1e-8},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"tensorx/deepseek/deepseek-r1-0528","object":"model","created":1787003349,"owned_by":"tensorx","model_name":"deepseek/deepseek-r1-0528","context_length":164000,"description":"Served by TensorX at fp8 quantization.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":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,"regions":[{"code":"eu","name":"Europe"}],"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,"description":"Served by TensorX at fp8 quantization.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":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,"regions":[{"code":"eu","name":"Europe"}],"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,"description":"Served by TensorX at fp4 quantization.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":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,"regions":[{"code":"eu","name":"Europe"}],"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,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":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,"regions":[{"code":"eu","name":"Europe"}],"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,"description":"Served by TensorX at fp8 quantization.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":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,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"tensorx/minimax/minimax-m3","object":"model","created":1787003349,"owned_by":"tensorx","model_name":"minimax/minimax-m3","context_length":1048576,"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_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,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"tensorx/moonshotai/kimi-k2.5","object":"model","created":1787003349,"owned_by":"tensorx","model_name":"moonshotai/kimi-k2.5","context_length":262144,"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_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":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,"regions":[{"code":"eu","name":"Europe"}],"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,"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_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":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,"regions":[{"code":"eu","name":"Europe"}],"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,"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_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,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"tensorx/moonshotai/kimi-k3","object":"model","created":1787003349,"owned_by":"tensorx","model_name":"moonshotai/kimi-k3","context_length":1048576,"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_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,"regions":[{"code":"eu","name":"Europe"}],"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,"description":"Served by TensorX at fp8 quantization.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":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,"regions":[{"code":"eu","name":"Europe"}],"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,"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_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":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,"regions":[{"code":"eu","name":"Europe"}],"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,"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_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":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,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"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,"description":"Served by TensorX at nvfp4 quantization.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":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,"regions":[{"code":"eu","name":"Europe"}],"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,"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_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,"regions":[{"code":"eu","name":"Europe"}],"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,"description":"Served by TensorX at fp8 quantization.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":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,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"tensorx/z-ai/glm-5.1","object":"model","created":1787003349,"owned_by":"tensorx","model_name":"z-ai/glm-5.1","context_length":202752,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":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,"regions":[{"code":"eu","name":"Europe"}],"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,"description":"Served by TensorX at fp8 quantization.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":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,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"tensorx/z-ai/glm-5-turbo","object":"model","created":1787003349,"owned_by":"tensorx","model_name":"z-ai/glm-5-turbo","context_length":202752,"description":"Served by TensorX at fp8 quantization.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":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,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"tensorx/z-ai/glm-5v-turbo","object":"model","created":1787003349,"owned_by":"tensorx","model_name":"z-ai/glm-5v-turbo","context_length":202752,"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_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":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,"regions":[{"code":"eu","name":"Europe"}],"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":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":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":7.450949824157585e-7,"output_cost_per_token":7.450949824157585e-7},"list_pricing":{"input_cost_per_token":7.450949824157585e-7,"output_cost_per_token":7.450949824157585e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"ionos/meta-llama/Meta-Llama-3.1-405B-Instruct-FP8","object":"model","created":1786647205,"owned_by":"ionos","model_name":"meta-llama/Meta-Llama-3.1-405B-Instruct-FP8","context_length":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":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":2.0193255221975797e-6,"output_cost_per_token":2.0193255221975797e-6},"list_pricing":{"input_cost_per_token":2.0193255221975797e-6,"output_cost_per_token":2.0193255221975797e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"ionos/meta-llama/Meta-Llama-3.1-8B-Instruct","object":"model","created":1786647205,"owned_by":"ionos","model_name":"meta-llama/Meta-Llama-3.1-8B-Instruct","context_length":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":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":1.7194499594209808e-7,"output_cost_per_token":1.7194499594209808e-7},"list_pricing":{"input_cost_per_token":1.7194499594209808e-7,"output_cost_per_token":1.7194499594209808e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"ionos/mistralai/Mistral-Nemo-Instruct-2407","object":"model","created":1786647205,"owned_by":"ionos","model_name":"mistralai/Mistral-Nemo-Instruct-2407","context_length":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":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":1.7194499594209808e-7,"output_cost_per_token":1.7194499594209808e-7},"list_pricing":{"input_cost_per_token":1.7194499594209808e-7,"output_cost_per_token":1.7194499594209808e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"ionos/mistralai/Mistral-Small-24B-Instruct","object":"model","created":1786647205,"owned_by":"ionos","model_name":"mistralai/Mistral-Small-24B-Instruct","context_length":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":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":1.1462999729473207e-7,"output_cost_per_token":3.4388999188419616e-7},"list_pricing":{"input_cost_per_token":1.1462999729473207e-7,"output_cost_per_token":3.4388999188419616e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"ionos/openai/gpt-oss-120b","object":"model","created":1786647205,"owned_by":"ionos","model_name":"openai/gpt-oss-120b","context_length":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":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":1.7194499594209808e-7,"output_cost_per_token":7.450949824157585e-7},"list_pricing":{"input_cost_per_token":1.7194499594209808e-7,"output_cost_per_token":7.450949824157585e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"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":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":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":6.877799837683923e-7,"output_cost_per_token":4.126679902610355e-6},"list_pricing":{"input_cost_per_token":6.877799837683923e-7,"output_cost_per_token":4.126679902610355e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"ionos/Qwen/Qwen3.5-9B","object":"model","created":1786647205,"owned_by":"ionos","model_name":"Qwen/Qwen3.5-9B","context_length":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":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":1.1462999729473207e-7,"output_cost_per_token":1.7194499594209808e-7},"list_pricing":{"input_cost_per_token":1.1462999729473207e-7,"output_cost_per_token":1.7194499594209808e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"ionos/Qwen/Qwen3-Coder-Next","object":"model","created":1786647205,"owned_by":"ionos","model_name":"Qwen/Qwen3-Coder-Next","context_length":null,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":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":1.7194499594209808e-7,"output_cost_per_token":9.170399783578565e-7},"list_pricing":{"input_cost_per_token":1.7194499594209808e-7,"output_cost_per_token":9.170399783578565e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"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,"description":"Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step...","source":null,"capabilities":{"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":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":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":0.014},"list_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":0.014},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"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,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":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":3.438899918841962e-7,"output_cost_per_token":4.585199891789283e-7},"list_pricing":{"input_cost_per_token":3.438899918841962e-7,"output_cost_per_token":4.585199891789283e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"azure/deepseek-v4-flash","object":"model","created":1786613111,"owned_by":"azure","model_name":"deepseek-v4-flash","context_length":1000000,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":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,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"azure/gpt-4.1","object":"model","created":1786613111,"owned_by":"azure","model_name":"gpt-4.1","context_length":1047576,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_tool_choice":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},"list_pricing":{"input_cost_per_token":2.2e-6,"output_cost_per_token":8.8e-6,"cache_read_input_token_cost":5.5e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"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,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_tool_choice":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},"list_pricing":{"input_cost_per_token":4.4e-7,"output_cost_per_token":1.76e-6,"cache_read_input_token_cost":1.1e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"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,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":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":4.585199891789283e-7,"output_cost_per_token":9.170399783578566e-7,"cache_read_input_token_cost":9.170399783578566e-8},"list_pricing":{"input_cost_per_token":4.585199891789283e-7,"output_cost_per_token":9.170399783578566e-7,"cache_read_input_token_cost":9.170399783578566e-8},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"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,"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_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,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":4.99999997e-6,"output_cost_per_token":0.00002499999999,"input_dbu_cost_per_token":0.000071429,"output_dbu_cost_per_token":0.000357143,"cache_read_input_token_cost":4.99999997e-7,"cache_creation_input_token_cost":6.25002e-6},"list_pricing":{"input_cost_per_token":4.99999997e-6,"output_cost_per_token":0.00002499999999,"input_dbu_cost_per_token":0.000071429,"output_dbu_cost_per_token":0.000357143,"cache_read_input_token_cost":4.99999997e-7,"cache_creation_input_token_cost":6.25002e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"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,"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_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,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":1.999998e-6,"output_cost_per_token":9.99999e-6,"input_dbu_cost_per_token":0.000042857,"output_dbu_cost_per_token":0.000214286,"cache_read_input_token_cost":1.999998e-7,"cache_creation_input_token_cost":3.74997e-6},"list_pricing":{"input_cost_per_token":1.999998e-6,"output_cost_per_token":9.99999e-6,"input_dbu_cost_per_token":0.000042857,"output_dbu_cost_per_token":0.000214286,"cache_read_input_token_cost":1.999998e-7,"cache_creation_input_token_cost":3.74997e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"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,"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_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,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":2.4997e-7,"output_cost_per_token":1.50003e-6,"input_dbu_cost_per_token":4.464e-6,"output_dbu_cost_per_token":0.000026786,"cache_read_input_token_cost":2.4997e-8,"cache_creation_input_token_cost":3.1248e-7},"list_pricing":{"input_cost_per_token":2.4997e-7,"output_cost_per_token":1.50003e-6,"input_dbu_cost_per_token":4.464e-6,"output_dbu_cost_per_token":0.000026786,"cache_read_input_token_cost":2.4997e-8,"cache_creation_input_token_cost":3.1248e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"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,"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_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,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":1.499995e-6,"output_cost_per_token":8.99997e-6,"input_dbu_cost_per_token":0.000026786,"output_dbu_cost_per_token":0.000160714,"cache_read_input_token_cost":1.499995e-7,"cache_creation_input_token_cost":1.87502e-6},"list_pricing":{"input_cost_per_token":1.499995e-6,"output_cost_per_token":8.99997e-6,"input_dbu_cost_per_token":0.000026786,"output_dbu_cost_per_token":0.000160714,"cache_read_input_token_cost":1.499995e-7,"cache_creation_input_token_cost":1.87502e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"databricks/databricks-gpt-5-2","object":"model","created":1785417770,"owned_by":"databricks","model_name":"databricks-gpt-5-2","context_length":272000,"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_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,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"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,"cache_creation_input_token_cost":1.75e-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,"cache_creation_input_token_cost":1.75e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"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":922000,"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_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,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":0.00002999997,"output_cost_per_token":0.0001799994,"input_dbu_cost_per_token":0.000428571,"output_dbu_cost_per_token":0.002571429,"cache_read_input_token_cost":2.999997e-6,"cache_creation_input_token_cost":0.00002999997},"list_pricing":{"input_cost_per_token":0.00002999997,"output_cost_per_token":0.0001799994,"input_dbu_cost_per_token":0.000428571,"output_dbu_cost_per_token":0.002571429,"cache_read_input_token_cost":2.999997e-6,"cache_creation_input_token_cost":0.00002999997},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"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,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":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,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":2.199995e-7,"output_cost_per_token":2.199995e-6,"input_dbu_cost_per_token":3.143e-6,"output_dbu_cost_per_token":0.000031429,"cache_read_input_token_cost":2.199995e-8,"cache_creation_input_token_cost":2.2001e-7},"list_pricing":{"input_cost_per_token":2.199995e-7,"output_cost_per_token":2.199995e-6,"input_dbu_cost_per_token":3.143e-6,"output_dbu_cost_per_token":0.000031429,"cache_read_input_token_cost":2.199995e-8,"cache_creation_input_token_cost":2.2001e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"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,"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_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,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":1.5001e-7,"output_cost_per_token":1.20001e-6,"input_dbu_cost_per_token":2.143e-6,"output_dbu_cost_per_token":0.000017143,"cache_read_input_token_cost":1.5001e-8,"cache_creation_input_token_cost":1.5001e-7},"list_pricing":{"input_cost_per_token":1.5001e-7,"output_cost_per_token":1.20001e-6,"input_dbu_cost_per_token":2.143e-6,"output_dbu_cost_per_token":0.000017143,"cache_read_input_token_cost":1.5001e-8,"cache_creation_input_token_cost":1.5001e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"qwen/qwen3.5-flash","object":"model","created":1785412138,"owned_by":"qwen","model_name":"qwen3.5-flash","context_length":1000000,"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":true,"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,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"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,"regions":[{"code":"eu","name":"Europe"}],"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,"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":true,"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,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"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,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"qwen/qwen3-vl-flash","object":"model","created":1785412138,"owned_by":"qwen","model_name":"qwen3-vl-flash","context_length":262144,"description":"The Qwen3 series of small-scale visual understanding models effectively integrates thinking and non-thinking modes, delivering superior performance compared to the open-source Qwen3-VL-30B-A3B while maintaining fast response speeds. It features a comprehensive upgrade in image/video understanding, supporting ultra-long contexts such as extended videos and documents, spatial awareness, and object recognition across various domains. Equipped with 2D/3D visual localization capabilities, it is well-suited for tackling complex real-world tasks.","source":null,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":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,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"tiered_pricing":[{"range":[0,32000],"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":4.0625e-8},{"range":[32000,128000],"input_cost_per_token":4.8749999999999996e-8,"output_cost_per_token":3.8999999999999997e-7,"cache_read_input_token_cost":9.75e-9,"cache_creation_input_token_cost":6.09375e-8},{"range":[128000,256000],"input_cost_per_token":7.8e-8,"output_cost_per_token":6.24e-7,"cache_read_input_token_cost":1.56e-8,"cache_creation_input_token_cost":9.749999999999999e-8}],"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":4.0625e-8},"list_pricing":{"tiered_pricing":[{"range":[0,32000],"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":6.25e-8},{"range":[32000,128000],"input_cost_per_token":7.5e-8,"output_cost_per_token":6e-7,"cache_read_input_token_cost":1.5e-8,"cache_creation_input_token_cost":9.375e-8},{"range":[128000,256000],"input_cost_per_token":1.2e-7,"output_cost_per_token":9.6e-7,"cache_read_input_token_cost":2.4e-8,"cache_creation_input_token_cost":1.5e-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":6.25e-8},"discount":0.35,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"qwen/qwen3-vl-flash-2025-10-15","object":"model","created":1785412138,"owned_by":"qwen","model_name":"qwen3-vl-flash-2025-10-15","context_length":262144,"description":"The Qwen3 series of small-scale visual understanding models effectively integrates thinking and non-thinking modes, delivering superior performance compared to the open-source Qwen3-VL-30B-A3B while maintaining fast response speeds. It features a comprehensive upgrade in image/video understanding, supporting ultra-long contexts such as extended videos and documents, spatial awareness, and object recognition across various domains. Equipped with 2D/3D visual localization capabilities, it is well-suited for tackling complex real-world tasks.This version is a snapshot as of October 15, 2025.","source":null,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":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,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"tiered_pricing":[{"range":[0,32000],"input_cost_per_token":3.2500000000000006e-8,"output_cost_per_token":2.6000000000000005e-7},{"range":[32000,128000],"input_cost_per_token":4.8749999999999996e-8,"output_cost_per_token":3.8999999999999997e-7},{"range":[128000,256000],"input_cost_per_token":7.8e-8,"output_cost_per_token":6.24e-7}],"input_cost_per_token":3.2500000000000006e-8,"output_cost_per_token":2.6000000000000005e-7},"list_pricing":{"tiered_pricing":[{"range":[0,32000],"input_cost_per_token":5.0000000000000004e-8,"output_cost_per_token":4.0000000000000003e-7},{"range":[32000,128000],"input_cost_per_token":7.5e-8,"output_cost_per_token":6e-7},{"range":[128000,256000],"input_cost_per_token":1.2e-7,"output_cost_per_token":9.6e-7}],"input_cost_per_token":5.0000000000000004e-8,"output_cost_per_token":4.0000000000000003e-7},"discount":0.35,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"qwen/qwen3-vl-flash-2026-01-22","object":"model","created":1785412138,"owned_by":"qwen","model_name":"qwen3-vl-flash-2026-01-22","context_length":262144,"description":"The Qwen3 series of small-sized visual understanding models effectively integrates thinking and non-thinking modes. Compared with the snapshot taken on October 15, 2025, the overall performance of the model has improved significantly: it delivers enhanced capabilities in general visual recognition and reasoning, and shows marked improvements in recognition accuracy across various business scenarios such as security, in-store inspections, equipment monitoring, and photo-based problem solving. This version is a snapshot as of January 22, 2026.","source":null,"capabilities":{"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":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,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"tiered_pricing":[{"range":[0,32000],"input_cost_per_token":3.2500000000000006e-8,"output_cost_per_token":2.6000000000000005e-7},{"range":[32000,128000],"input_cost_per_token":4.8749999999999996e-8,"output_cost_per_token":3.8999999999999997e-7},{"range":[128000,256000],"input_cost_per_token":7.8e-8,"output_cost_per_token":6.24e-7}],"input_cost_per_token":3.2500000000000006e-8,"output_cost_per_token":2.6000000000000005e-7},"list_pricing":{"tiered_pricing":[{"range":[0,32000],"input_cost_per_token":5.0000000000000004e-8,"output_cost_per_token":4.0000000000000003e-7},{"range":[32000,128000],"input_cost_per_token":7.5e-8,"output_cost_per_token":6e-7},{"range":[128000,256000],"input_cost_per_token":1.2e-7,"output_cost_per_token":9.6e-7}],"input_cost_per_token":5.0000000000000004e-8,"output_cost_per_token":4.0000000000000003e-7},"discount":0.35,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"qwen/qwen3-vl-plus","object":"model","created":1785412138,"owned_by":"qwen","model_name":"qwen3-vl-plus","context_length":262144,"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_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,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"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,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"azure/gpt-5.5","object":"model","created":1785276709,"owned_by":"azure","model_name":"gpt-5.5","context_length":1050000,"description":null,"source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":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,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":5.500000000000001e-6,"output_cost_per_token":0.000033,"cache_read_input_token_cost":5.500000000000001e-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,"input_cost_per_token_above_272k_tokens":0.000011000000000000001,"output_cost_per_token_above_272k_tokens":0.000049500000000000004,"cache_read_input_token_cost_above_272k_tokens":1.1000000000000003e-6,"cache_creation_input_token_cost_above_272k_tokens":0.000013750000000000002},"list_pricing":{"input_cost_per_token":5.500000000000001e-6,"output_cost_per_token":0.000033,"cache_read_input_token_cost":5.500000000000001e-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,"input_cost_per_token_above_272k_tokens":0.000011000000000000001,"output_cost_per_token_above_272k_tokens":0.000049500000000000004,"cache_read_input_token_cost_above_272k_tokens":1.1000000000000003e-6,"cache_creation_input_token_cost_above_272k_tokens":0.000013750000000000002},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"azure/gpt-4o","object":"model","created":1784916453,"owned_by":"azure","model_name":"gpt-4o","context_length":128000,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_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,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"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,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"azure/gpt-4o-mini","object":"model","created":1784916453,"owned_by":"azure","model_name":"gpt-4o-mini","context_length":128000,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_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,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":1.8150000000000003e-7,"output_cost_per_token":7.260000000000001e-7,"cache_read_input_token_cost":8.25e-8},"list_pricing":{"input_cost_per_token":1.8150000000000003e-7,"output_cost_per_token":7.260000000000001e-7,"cache_read_input_token_cost":8.25e-8},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"azure/o3","object":"model","created":1784916453,"owned_by":"azure","model_name":"o3","context_length":200000,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":2.2e-6,"output_cost_per_token":8.8e-6,"cache_read_input_token_cost":5.5e-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},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"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,"description":"Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis...","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":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,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"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,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"vertex/claude-opus-5","object":"model","created":1784912544,"owned_by":"vertex","model_name":"claude-opus-5","context_length":1000000,"description":"Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis...","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":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,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"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,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"azure/gpt-5.4","object":"model","created":1784832896,"owned_by":"azure","model_name":"gpt-5.4","context_length":1050000,"description":null,"source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":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,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":2.7500000000000004e-6,"output_cost_per_token":0.0000165,"cache_read_input_token_cost":2.75e-7,"input_cost_per_token_above_272k_tokens":5.500000000000001e-6,"output_cost_per_token_above_272k_tokens":0.000024750000000000002,"cache_read_input_token_cost_above_272k_tokens":5.5e-7},"list_pricing":{"input_cost_per_token":2.7500000000000004e-6,"output_cost_per_token":0.0000165,"cache_read_input_token_cost":2.75e-7,"input_cost_per_token_above_272k_tokens":5.500000000000001e-6,"output_cost_per_token_above_272k_tokens":0.000024750000000000002,"cache_read_input_token_cost_above_272k_tokens":5.5e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"azure/gpt-5.4-mini","object":"model","created":1784832896,"owned_by":"azure","model_name":"gpt-5.4-mini","context_length":272000,"description":null,"source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":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,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":8.25e-7,"output_cost_per_token":4.950000000000001e-6,"cache_read_input_token_cost":8.25e-8,"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":8.25e-7,"output_cost_per_token":4.950000000000001e-6,"cache_read_input_token_cost":8.25e-8,"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,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"azure/gpt-5.6-luna","object":"model","created":1784804086,"owned_by":"azure","model_name":"gpt-5.6-luna","context_length":922000,"description":null,"source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":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,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":2.2000000000000004e-7,"output_cost_per_token":1.32e-6,"cache_read_input_token_cost":2.2000000000000005e-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":2.7500000000000007e-7,"input_cost_per_token_above_272k_tokens":4.400000000000001e-7,"output_cost_per_token_above_272k_tokens":1.98e-6,"cache_read_input_token_cost_above_272k_tokens":4.400000000000001e-8,"cache_creation_input_token_cost_above_272k_tokens":5.500000000000001e-7},"list_pricing":{"input_cost_per_token":2.2000000000000004e-7,"output_cost_per_token":1.32e-6,"cache_read_input_token_cost":2.2000000000000005e-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":2.7500000000000007e-7,"input_cost_per_token_above_272k_tokens":4.400000000000001e-7,"output_cost_per_token_above_272k_tokens":1.98e-6,"cache_read_input_token_cost_above_272k_tokens":4.400000000000001e-8,"cache_creation_input_token_cost_above_272k_tokens":5.500000000000001e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"azure/gpt-5.6-sol","object":"model","created":1784804086,"owned_by":"azure","model_name":"gpt-5.6-sol","context_length":922000,"description":null,"source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":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,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":5.500000000000001e-6,"output_cost_per_token":0.000033,"cache_read_input_token_cost":5.500000000000001e-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,"input_cost_per_token_above_272k_tokens":0.000011000000000000001,"output_cost_per_token_above_272k_tokens":0.000049500000000000004,"cache_read_input_token_cost_above_272k_tokens":1.1000000000000003e-6,"cache_creation_input_token_cost_above_272k_tokens":0.000013750000000000002},"list_pricing":{"input_cost_per_token":5.500000000000001e-6,"output_cost_per_token":0.000033,"cache_read_input_token_cost":5.500000000000001e-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,"input_cost_per_token_above_272k_tokens":0.000011000000000000001,"output_cost_per_token_above_272k_tokens":0.000049500000000000004,"cache_read_input_token_cost_above_272k_tokens":1.1000000000000003e-6,"cache_creation_input_token_cost_above_272k_tokens":0.000013750000000000002},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"azure/gpt-5.6-terra","object":"model","created":1784804086,"owned_by":"azure","model_name":"gpt-5.6-terra","context_length":922000,"description":null,"source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":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,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":2.2e-6,"output_cost_per_token":0.0000132,"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":2.75e-6,"input_cost_per_token_above_272k_tokens":4.4e-6,"output_cost_per_token_above_272k_tokens":0.000019800000000000004,"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,"search_context_cost_per_query":{"search_context_size_low":0.01,"search_context_size_high":0.01,"search_context_size_medium":0.01},"cache_creation_input_token_cost":2.75e-6,"input_cost_per_token_above_272k_tokens":4.4e-6,"output_cost_per_token_above_272k_tokens":0.000019800000000000004,"cache_read_input_token_cost_above_272k_tokens":4.4e-7,"cache_creation_input_token_cost_above_272k_tokens":5.5e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"azure/gpt-5","object":"model","created":1784721580,"owned_by":"azure","model_name":"gpt-5","context_length":272000,"description":null,"source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_tool_choice":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,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":1.3750000000000002e-6,"output_cost_per_token":0.000011000000000000001,"cache_read_input_token_cost":1.375e-7},"list_pricing":{"input_cost_per_token":1.3750000000000002e-6,"output_cost_per_token":0.000011000000000000001,"cache_read_input_token_cost":1.375e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"azure/gpt-5.1","object":"model","created":1784721580,"owned_by":"azure","model_name":"gpt-5.1","context_length":272000,"description":null,"source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_tool_choice":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,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":1.3750000000000002e-6,"output_cost_per_token":0.000011000000000000001,"cache_read_input_token_cost":1.375e-7},"list_pricing":{"input_cost_per_token":1.3750000000000002e-6,"output_cost_per_token":0.000011000000000000001,"cache_read_input_token_cost":1.375e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"azure/gpt-5-mini","object":"model","created":1784721580,"owned_by":"azure","model_name":"gpt-5-mini","context_length":272000,"description":null,"source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_tool_choice":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,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":2.75e-7,"output_cost_per_token":2.2e-6,"cache_read_input_token_cost":2.75e-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},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"azure/gpt-5-nano","object":"model","created":1784721580,"owned_by":"azure","model_name":"gpt-5-nano","context_length":272000,"description":null,"source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_tool_choice":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,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":5.5e-8,"output_cost_per_token":4.4e-7,"cache_read_input_token_cost":5.5000000000000004e-9},"list_pricing":{"input_cost_per_token":5.5e-8,"output_cost_per_token":4.4e-7,"cache_read_input_token_cost":5.5000000000000004e-9},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"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,"description":"Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development. It is designed to produce polished outputs with fewer unnecessary edits and...","source":null,"capabilities":{"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":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,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"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":0.014},"list_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":0.014},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"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,"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_tool_choice":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,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":2.5e-6,"input_cost_per_audio_token":3e-7,"input_cost_per_image_token":3e-7,"cache_read_input_token_cost":3e-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":8.33333333333333e-8,"output_cost_per_reasoning_token":2.5e-6,"cache_read_input_audio_token_cost":3e-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_audio_token":3e-7,"input_cost_per_image_token":3e-7,"cache_read_input_token_cost":3e-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":8.33333333333333e-8,"output_cost_per_reasoning_token":2.5e-6,"cache_read_input_audio_token_cost":3e-8,"google_maps_grounding_cost_per_query":0.014},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"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":922000,"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_tool_choice":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,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":1.9999e-7,"output_cost_per_token":1.20001e-6,"input_dbu_cost_per_token":0.000014286,"output_dbu_cost_per_token":0.000085714,"cache_read_input_token_cost":1.9999e-8,"cache_creation_input_token_cost":1.24999e-6},"list_pricing":{"input_cost_per_token":1.9999e-7,"output_cost_per_token":1.20001e-6,"input_dbu_cost_per_token":0.000014286,"output_dbu_cost_per_token":0.000085714,"cache_read_input_token_cost":1.9999e-8,"cache_creation_input_token_cost":1.24999e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"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":922000,"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_tool_choice":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,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":1.99997e-6,"output_cost_per_token":0.00001200003,"input_dbu_cost_per_token":0.000035714,"output_dbu_cost_per_token":0.000214286,"cache_read_input_token_cost":1.99997e-7,"cache_creation_input_token_cost":3.12501e-6},"list_pricing":{"input_cost_per_token":1.99997e-6,"output_cost_per_token":0.00001200003,"input_dbu_cost_per_token":0.000035714,"output_dbu_cost_per_token":0.000214286,"cache_read_input_token_cost":1.99997e-7,"cache_creation_input_token_cost":3.12501e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"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":922000,"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_tool_choice":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,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":3.9999995e-6,"output_cost_per_token":0.0000199999996,"input_dbu_cost_per_token":0.000057143,"output_dbu_cost_per_token":0.000285714,"cache_read_input_token_cost":3.9999995e-7,"cache_creation_input_token_cost":5.00003e-6},"list_pricing":{"input_cost_per_token":3.9999995e-6,"output_cost_per_token":0.0000199999996,"input_dbu_cost_per_token":0.000057143,"output_dbu_cost_per_token":0.000285714,"cache_read_input_token_cost":3.9999995e-7,"cache_creation_input_token_cost":5.00003e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"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,"description":"Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max,...","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":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,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"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,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"vertex/claude-sonnet-5","object":"model","created":1782843083,"owned_by":"vertex","model_name":"claude-sonnet-5","context_length":1000000,"description":"Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max,...","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":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,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"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,"regions":[{"code":"eu","name":"Europe"}],"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,"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. It delivers text-to-image generation...","source":null,"capabilities":{"input_modalities":["image","text"],"output_modalities":["image","text"],"supports_reasoning":true,"supports_web_search":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,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"mistral/mistral-medium-2508","object":"model","created":1782745560,"owned_by":"mistral","model_name":"mistral-medium-2508","context_length":131072,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":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,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"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,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"mistral/mistral-medium-2604","object":"model","created":1782745560,"owned_by":"mistral","model_name":"mistral-medium-2604","context_length":262144,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":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,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":1.5e-6,"output_cost_per_token":7.5e-6,"cache_read_input_token_cost":1.5e-7},"list_pricing":{"input_cost_per_token":1.5e-6,"output_cost_per_token":7.5e-6,"cache_read_input_token_cost":1.5e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"scaleway/glm-5.2","object":"model","created":1782376549,"owned_by":"scaleway","model_name":"glm-5.2","context_length":256000,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":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,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":2.063339951305177e-6,"output_cost_per_token":6.3046498512102635e-6},"list_pricing":{"input_cost_per_token":2.063339951305177e-6,"output_cost_per_token":6.3046498512102635e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"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,"description":null,"source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":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,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"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,"regions":[{"code":"eu","name":"Europe"}],"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,"description":null,"source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":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,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"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,"regions":[{"code":"eu","name":"Europe"}],"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,"description":null,"source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":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,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"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,"regions":[{"code":"eu","name":"Europe"}],"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,"description":null,"source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":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,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"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,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"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,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":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,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"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,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"vertex/gemini-3.1-flash-image","object":"model","created":1781754065,"owned_by":"vertex","model_name":"gemini-3.1-flash-image","context_length":131072,"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. It combines advanced...","source":null,"capabilities":{"input_modalities":["image","text"],"output_modalities":["image","text"],"supports_reasoning":true,"supports_web_search":true,"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,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"vertex/gemini-3-pro-image","object":"model","created":1781754054,"owned_by":"vertex","model_name":"gemini-3-pro-image","context_length":65536,"description":"Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and...","source":null,"capabilities":{"input_modalities":["image","text"],"output_modalities":["image","text"],"supports_reasoning":true,"supports_web_search":true,"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,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"mistral/glm-5-2","object":"model","created":1781631930,"owned_by":"mistral","model_name":"glm-5-2","context_length":1048576,"description":"GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering,...","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_tool_choice":true,"supports_computer_use":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,"regions":[{"code":"eu","name":"Europe"}],"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":272000,"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_tool_choice":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,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":1.9999e-7,"output_cost_per_token":1.24999e-6,"input_dbu_cost_per_token":2.857e-6,"output_dbu_cost_per_token":0.000017857,"cache_read_input_token_cost":1.9999e-8,"cache_creation_input_token_cost":1.9999e-7},"list_pricing":{"input_cost_per_token":1.9999e-7,"output_cost_per_token":1.24999e-6,"input_dbu_cost_per_token":2.857e-6,"output_dbu_cost_per_token":0.000017857,"cache_read_input_token_cost":1.9999e-8,"cache_creation_input_token_cost":1.9999e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"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":272000,"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_tool_choice":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,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":7.4998e-7,"output_cost_per_token":4.50002e-6,"input_dbu_cost_per_token":0.000010714,"output_dbu_cost_per_token":0.000064286,"cache_read_input_token_cost":7.4998e-8,"cache_creation_input_token_cost":7.4998e-7},"list_pricing":{"input_cost_per_token":7.4998e-7,"output_cost_per_token":4.50002e-6,"input_dbu_cost_per_token":0.000010714,"output_dbu_cost_per_token":0.000064286,"cache_read_input_token_cost":7.4998e-8,"cache_creation_input_token_cost":7.4998e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"databricks/databricks-gpt-5-4","object":"model","created":1781107711,"owned_by":"databricks","model_name":"databricks-gpt-5-4","context_length":922000,"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_tool_choice":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,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":2.49998e-6,"output_cost_per_token":0.00001500002,"input_dbu_cost_per_token":0.000035714,"output_dbu_cost_per_token":0.000214286,"cache_read_input_token_cost":2.49998e-7,"cache_creation_input_token_cost":2.49998e-6},"list_pricing":{"input_cost_per_token":2.49998e-6,"output_cost_per_token":0.00001500002,"input_dbu_cost_per_token":0.000035714,"output_dbu_cost_per_token":0.000214286,"cache_read_input_token_cost":2.49998e-7,"cache_creation_input_token_cost":2.49998e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"databricks/databricks-gpt-5-5","object":"model","created":1781107530,"owned_by":"databricks","model_name":"databricks-gpt-5-5","context_length":922000,"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_tool_choice":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,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":5.00003e-6,"output_cost_per_token":0.00002999997,"input_dbu_cost_per_token":0.000071429,"output_dbu_cost_per_token":0.000428571,"cache_read_input_token_cost":5.00003e-7,"cache_creation_input_token_cost":5.00003e-6},"list_pricing":{"input_cost_per_token":5.00003e-6,"output_cost_per_token":0.00002999997,"input_dbu_cost_per_token":0.000071429,"output_dbu_cost_per_token":0.000428571,"cache_read_input_token_cost":5.00003e-7,"cache_creation_input_token_cost":5.00003e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"vertex/claude-fable-5","object":"model","created":1781007515,"owned_by":"vertex","model_name":"claude-fable-5","context_length":1000000,"description":"Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and...","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":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,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"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,"regions":[{"code":"eu","name":"Europe"}],"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,"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_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,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":2.99999e-6,"output_cost_per_token":0.00001500002,"input_dbu_cost_per_token":0.000042857,"output_dbu_cost_per_token":0.000214286,"cache_read_input_token_cost":2.99999e-7,"cache_creation_input_token_cost":3.74997e-6},"list_pricing":{"input_cost_per_token":2.99999e-6,"output_cost_per_token":0.00001500002,"input_dbu_cost_per_token":0.000042857,"output_dbu_cost_per_token":0.000214286,"cache_read_input_token_cost":2.99999e-7,"cache_creation_input_token_cost":3.74997e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"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,"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_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,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":5.00003e-6,"output_cost_per_token":0.00002500001,"input_dbu_cost_per_token":0.000071429,"output_dbu_cost_per_token":0.000357143,"cache_read_input_token_cost":5.00003e-7,"cache_creation_input_token_cost":6.25002e-6},"list_pricing":{"input_cost_per_token":5.00003e-6,"output_cost_per_token":0.00002500001,"input_dbu_cost_per_token":0.000071429,"output_dbu_cost_per_token":0.000357143,"cache_read_input_token_cost":5.00003e-7,"cache_creation_input_token_cost":6.25002e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"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,"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_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,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":5.00003e-6,"output_cost_per_token":0.00002500001,"input_dbu_cost_per_token":0.000071429,"output_dbu_cost_per_token":0.000357143,"cache_read_input_token_cost":5.00003e-7,"cache_creation_input_token_cost":6.25002e-6},"list_pricing":{"input_cost_per_token":5.00003e-6,"output_cost_per_token":0.00002500001,"input_dbu_cost_per_token":0.000071429,"output_dbu_cost_per_token":0.000357143,"cache_read_input_token_cost":5.00003e-7,"cache_creation_input_token_cost":6.25002e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"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,"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_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,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":5.00003e-6,"output_cost_per_token":0.00002500001,"input_dbu_cost_per_token":0.000071429,"output_dbu_cost_per_token":0.000357143,"cache_read_input_token_cost":5.00003e-7,"cache_creation_input_token_cost":6.25002e-6},"list_pricing":{"input_cost_per_token":5.00003e-6,"output_cost_per_token":0.00002500001,"input_dbu_cost_per_token":0.000071429,"output_dbu_cost_per_token":0.000357143,"cache_read_input_token_cost":5.00003e-7,"cache_creation_input_token_cost":6.25002e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"mistral/codestral-latest","object":"model","created":1780673223,"owned_by":"mistral","model_name":"codestral-latest","context_length":256000,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":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,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":9e-7,"cache_read_input_token_cost":3e-8},"list_pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":9e-7,"cache_read_input_token_cost":3e-8},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"mistral/mistral-tiny-latest","object":"model","created":1780673223,"owned_by":"mistral","model_name":"mistral-tiny-latest","context_length":131072,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":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,"regions":[{"code":"eu","name":"Europe"}],"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,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":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":7.1e-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,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"ovhcloud/Qwen3.5-9B","object":"model","created":1780673223,"owned_by":"ovhcloud","model_name":"Qwen3.5-9B","context_length":262144,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":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":1.2e-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,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"ovhcloud/Qwen3.6-27B","object":"model","created":1780673223,"owned_by":"ovhcloud","model_name":"Qwen3.6-27B","context_length":262144,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":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":4.7e-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,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"ovhcloud/Qwen3-Coder-30B-A3B-Instruct","object":"model","created":1780673223,"owned_by":"ovhcloud","model_name":"Qwen3-Coder-30B-A3B-Instruct","context_length":262144,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":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":7e-8,"output_cost_per_token":2.6e-7},"list_pricing":{"input_cost_per_token":7e-8,"output_cost_per_token":2.6e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"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,"description":"Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token...","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":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,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"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,"regions":[{"code":"eu","name":"Europe"}],"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,"description":"Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token...","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":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,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"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,"regions":[{"code":"eu","name":"Europe"}],"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,"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. It is highly optimized for coding proficiency and parallel agentic execution...","source":null,"capabilities":{"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":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,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":1.5e-6,"output_cost_per_token":9e-6,"input_cost_per_audio_token":3e-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":0.014,"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":9e-6,"cache_read_input_audio_token_cost":3e-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_audio_token":3e-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":0.014,"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":9e-6,"cache_read_input_audio_token_cost":3e-7,"google_maps_grounding_cost_per_query":0.014},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"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,"description":"Gemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads. It supports text, image, video, audio, and PDF inputs, and is designed for lightweight agentic...","source":null,"capabilities":{"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":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":1.5e-6,"input_cost_per_audio_token":5e-7,"input_cost_per_image_token":2.5e-7,"cache_read_input_token_cost":2.5e-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":8.33333333333333e-8,"output_cost_per_reasoning_token":1.5e-6,"cache_read_input_audio_token_cost":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_audio_token":5e-7,"input_cost_per_image_token":2.5e-7,"cache_read_input_token_cost":2.5e-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":8.33333333333333e-8,"output_cost_per_reasoning_token":1.5e-6,"cache_read_input_audio_token_cost":5e-8,"google_maps_grounding_cost_per_query":0.014},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"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,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":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,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":1.719449959420981e-6,"output_cost_per_token":8.597249797104904e-6},"list_pricing":{"input_cost_per_token":1.719449959420981e-6,"output_cost_per_token":8.597249797104904e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"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,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":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,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":2.8657499323683016e-7,"output_cost_per_token":1.719449959420981e-6},"list_pricing":{"input_cost_per_token":2.8657499323683016e-7,"output_cost_per_token":1.719449959420981e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"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,"description":"Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex...","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":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,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":1.5e-6,"output_cost_per_token":7.5e-6,"cache_read_input_token_cost":1.5e-7},"list_pricing":{"input_cost_per_token":1.5e-6,"output_cost_per_token":7.5e-6,"cache_read_input_token_cost":1.5e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"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,"description":"Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex...","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":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,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":1.5e-6,"output_cost_per_token":7.5e-6,"cache_read_input_token_cost":1.5e-7},"list_pricing":{"input_cost_per_token":1.5e-6,"output_cost_per_token":7.5e-6,"cache_read_input_token_cost":1.5e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"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,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":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,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":2.8657499323683016e-7,"output_cost_per_token":5.731499864736603e-7},"list_pricing":{"input_cost_per_token":2.8657499323683016e-7,"output_cost_per_token":5.731499864736603e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"mistral/codestral-2405","object":"model","created":1777389105,"owned_by":"mistral","model_name":"codestral-2405","context_length":32000,"description":"","source":"https://docs.mistral.ai/capabilities/code_generation/","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":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,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"mistral/mistral-large-2402","object":"model","created":1777389105,"owned_by":"mistral","model_name":"mistral-large-2402","context_length":32000,"description":"","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":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,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"mistral/mistral-medium-2312","object":"model","created":1777389105,"owned_by":"mistral","model_name":"mistral-medium-2312","context_length":32000,"description":"","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":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,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"mistral/mistral-small","object":"model","created":1777389105,"owned_by":"mistral","model_name":"mistral-small","context_length":32000,"description":"","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":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,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"mistral/mistral-tiny","object":"model","created":1777389105,"owned_by":"mistral","model_name":"mistral-tiny","context_length":32000,"description":"","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":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,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"mistral/open-mistral-7b","object":"model","created":1777389105,"owned_by":"mistral","model_name":"open-mistral-7b","context_length":32000,"description":"","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":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,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"mistral/open-mixtral-8x22b","object":"model","created":1777389105,"owned_by":"mistral","model_name":"open-mixtral-8x22b","context_length":65336,"description":"","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":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,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"mistral/open-mixtral-8x7b","object":"model","created":1777389105,"owned_by":"mistral","model_name":"open-mixtral-8x7b","context_length":32000,"description":"","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":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,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"mistral/pixtral-12b-2409","object":"model","created":1777389105,"owned_by":"mistral","model_name":"pixtral-12b-2409","context_length":128000,"description":"","source":null,"capabilities":{"input_modalities":["image","text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":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,"regions":[{"code":"eu","name":"Europe"}],"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,"description":"Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents. Building on the coding and agentic strengths of Opus 4.6, it delivers stronger performance on...","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":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,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"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,"regions":[{"code":"eu","name":"Europe"}],"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,"description":"Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents. Building on the coding and agentic strengths of Opus 4.6, it delivers stronger performance on...","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":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,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"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,"regions":[{"code":"eu","name":"Europe"}],"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,"description":"Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...","source":null,"capabilities":{"input_modalities":["image","text","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":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,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":1.65e-7,"output_cost_per_token":6.6e-7},"list_pricing":{"input_cost_per_token":1.65e-7,"output_cost_per_token":6.6e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"amazon/minimax.minimax-m2.5","object":"model","created":1775193119,"owned_by":"amazon","model_name":"minimax.minimax-m2.5","context_length":1000000,"description":null,"source":"https://aws.amazon.com/bedrock/pricing/","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":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,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":3.6e-7,"output_cost_per_token":1.44e-6},"list_pricing":{"input_cost_per_token":3.6e-7,"output_cost_per_token":1.44e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"amazon/nvidia.nemotron-super-3-120b","object":"model","created":1775193119,"owned_by":"amazon","model_name":"nvidia.nemotron-super-3-120b","context_length":256000,"description":null,"source":"https://aws.amazon.com/bedrock/pricing/","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":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,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":2.3e-7,"output_cost_per_token":1.01e-6},"list_pricing":{"input_cost_per_token":2.3e-7,"output_cost_per_token":1.01e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"amazon/zai.glm-5","object":"model","created":1775193119,"owned_by":"amazon","model_name":"zai.glm-5","context_length":200000,"description":null,"source":"https://aws.amazon.com/bedrock/pricing/","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":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,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":3.2e-6},"list_pricing":{"input_cost_per_token":1e-6,"output_cost_per_token":3.2e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"mistral/mistral-small-2603","object":"model","created":1773695685,"owned_by":"mistral","model_name":"mistral-small-2603","context_length":262144,"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. It combines strong reasoning from...","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_tool_choice":true,"supports_computer_use":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,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"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,"regions":[{"code":"eu","name":"Europe"}],"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,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":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,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":6.877799837683923e-7,"output_cost_per_token":4.126679902610354e-6},"list_pricing":{"input_cost_per_token":6.877799837683923e-7,"output_cost_per_token":4.126679902610354e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"amazon/mistral.devstral-2-123b","object":"model","created":1772697599,"owned_by":"amazon","model_name":"mistral.devstral-2-123b","context_length":256000,"description":null,"source":"https://aws.amazon.com/bedrock/pricing/","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":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,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"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,"regions":[{"code":"eu","name":"Europe"}],"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,"description":null,"source":"https://aws.amazon.com/bedrock/pricing/","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":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,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":7e-8,"output_cost_per_token":4e-7},"list_pricing":{"input_cost_per_token":7e-8,"output_cost_per_token":4e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"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,"description":"","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":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,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"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,"description":"","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":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,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"amazon/anthropic.claude-3-haiku-20240307-v1:0","object":"model","created":1772632546,"owned_by":"amazon","model_name":"anthropic.claude-3-haiku-20240307-v1:0","context_length":200000,"description":null,"source":null,"capabilities":{"input_modalities":["file","image","text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":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,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":2.5e-7,"output_cost_per_token":1.25e-6,"cache_read_input_token_cost":2.5e-8,"cache_creation_input_token_cost":3.125e-7},"list_pricing":{"input_cost_per_token":2.5e-7,"output_cost_per_token":1.25e-6,"cache_read_input_token_cost":2.5e-8,"cache_creation_input_token_cost":3.125e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"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,"description":"","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":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,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"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,"description":"","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":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,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"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,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":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,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"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,"regions":[{"code":"eu","name":"Europe"}],"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,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":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,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"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,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"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,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":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,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"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,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"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,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":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,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"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,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"mistral/devstral-latest","object":"model","created":1771588786,"owned_by":"mistral","model_name":"devstral-latest","context_length":262144,"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_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,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"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,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"mistral/devstral-medium-latest","object":"model","created":1771588786,"owned_by":"mistral","model_name":"devstral-medium-latest","context_length":262144,"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_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,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"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,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"mistral/devstral-small-latest","object":"model","created":1771588786,"owned_by":"mistral","model_name":"devstral-small-latest","context_length":256000,"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_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,"regions":[{"code":"eu","name":"Europe"}],"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,"description":"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...","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":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,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"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,"regions":[{"code":"eu","name":"Europe"}],"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,"description":"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...","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":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,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"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,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"amazon/minimax.minimax-m2.1","object":"model","created":1770991619,"owned_by":"amazon","model_name":"minimax.minimax-m2.1","context_length":196000,"description":null,"source":"https://aws.amazon.com/bedrock/pricing/","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":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,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":3.6e-7,"output_cost_per_token":1.44e-6},"list_pricing":{"input_cost_per_token":3.6e-7,"output_cost_per_token":1.44e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"amazon/nvidia.nemotron-nano-3-30b","object":"model","created":1770991619,"owned_by":"amazon","model_name":"nvidia.nemotron-nano-3-30b","context_length":256000,"description":null,"source":"https://aws.amazon.com/bedrock/pricing/","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":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,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":6e-8,"output_cost_per_token":2.4e-7},"list_pricing":{"input_cost_per_token":6e-8,"output_cost_per_token":2.4e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"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,"description":null,"source":"https://aws.amazon.com/bedrock/pricing/","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":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,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":6e-7,"output_cost_per_token":1.44e-6},"list_pricing":{"input_cost_per_token":6e-7,"output_cost_per_token":1.44e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"amazon/zai.glm-4.7","object":"model","created":1770991619,"owned_by":"amazon","model_name":"zai.glm-4.7","context_length":203000,"description":null,"source":"https://aws.amazon.com/bedrock/pricing/","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":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,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":6e-7,"output_cost_per_token":2.2e-6},"list_pricing":{"input_cost_per_token":6e-7,"output_cost_per_token":2.2e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"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,"description":"Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts, making it especially effective...","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":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,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"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,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"qwen/qwen3-coder-next","object":"model","created":1770164101,"owned_by":"qwen","model_name":"qwen3-coder-next","context_length":262144,"description":"The new-generation code generation model in the Qwen3 series delivers performance close to that of Qwen3-Coder-Plus while offering even better capabilities. The model has been optimized with a focus on repository-level understanding, supports multi-turn tool interactions, and enhances its compatibility with agentic coding tools.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":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,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"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}],"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}],"input_cost_per_token":3e-7,"output_cost_per_token":1.5e-6},"discount":0.35,"regions":[{"code":"eu","name":"Europe"}],"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,"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_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,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":1.00002e-6,"output_cost_per_token":5.00003e-6,"input_dbu_cost_per_token":0.000014286,"output_dbu_cost_per_token":0.000071429,"cache_read_input_token_cost":1.00002e-7,"cache_creation_input_token_cost":1.24999e-6},"list_pricing":{"input_cost_per_token":1.00002e-6,"output_cost_per_token":5.00003e-6,"input_dbu_cost_per_token":0.000014286,"output_dbu_cost_per_token":0.000071429,"cache_read_input_token_cost":1.00002e-7,"cache_creation_input_token_cost":1.24999e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"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,"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_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,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]},"supports_output_config":true},"pricing":{"input_cost_per_token":5.00003e-6,"output_cost_per_token":0.00002500001,"input_dbu_cost_per_token":0.000071429,"output_dbu_cost_per_token":0.000357143,"cache_read_input_token_cost":5.00003e-7,"cache_creation_input_token_cost":6.25002e-6},"list_pricing":{"input_cost_per_token":5.00003e-6,"output_cost_per_token":0.00002500001,"input_dbu_cost_per_token":0.000071429,"output_dbu_cost_per_token":0.000357143,"cache_read_input_token_cost":5.00003e-7,"cache_creation_input_token_cost":6.25002e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"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,"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_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,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":2.99999e-6,"output_cost_per_token":0.00001500002,"input_dbu_cost_per_token":0.000042857,"output_dbu_cost_per_token":0.000214286,"cache_read_input_token_cost":2.99999e-7,"cache_creation_input_token_cost":3.74997e-6},"list_pricing":{"input_cost_per_token":2.99999e-6,"output_cost_per_token":0.00001500002,"input_dbu_cost_per_token":0.000042857,"output_dbu_cost_per_token":0.000214286,"cache_read_input_token_cost":2.99999e-7,"cache_creation_input_token_cost":3.74997e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"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,"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_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,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":1.5001e-7,"output_cost_per_token":5.0001e-7,"input_dbu_cost_per_token":2.1429999999999996e-6,"output_dbu_cost_per_token":7.143e-6,"cache_read_input_token_cost":1.5001e-8,"cache_creation_input_token_cost":1.5001e-7},"list_pricing":{"input_cost_per_token":1.5001e-7,"output_cost_per_token":5.0001e-7,"input_dbu_cost_per_token":2.1429999999999996e-6,"output_dbu_cost_per_token":7.143e-6,"cache_read_input_token_cost":1.5001e-8,"cache_creation_input_token_cost":1.5001e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"databricks/databricks-gpt-5","object":"model","created":1769507058,"owned_by":"databricks","model_name":"databricks-gpt-5","context_length":272000,"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_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,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":1.24999e-6,"output_cost_per_token":9.99999e-6,"input_dbu_cost_per_token":0.000017857,"output_dbu_cost_per_token":0.000142857,"cache_read_input_token_cost":1.24999e-7,"cache_creation_input_token_cost":1.24999e-6},"list_pricing":{"input_cost_per_token":1.24999e-6,"output_cost_per_token":9.99999e-6,"input_dbu_cost_per_token":0.000017857,"output_dbu_cost_per_token":0.000142857,"cache_read_input_token_cost":1.24999e-7,"cache_creation_input_token_cost":1.24999e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"databricks/databricks-gpt-5-1","object":"model","created":1769507058,"owned_by":"databricks","model_name":"databricks-gpt-5-1","context_length":272000,"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_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,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":1.24999e-6,"output_cost_per_token":9.99999e-6,"input_dbu_cost_per_token":0.000017857,"output_dbu_cost_per_token":0.000142857,"cache_read_input_token_cost":1.24999e-7,"cache_creation_input_token_cost":1.24999e-6},"list_pricing":{"input_cost_per_token":1.24999e-6,"output_cost_per_token":9.99999e-6,"input_dbu_cost_per_token":0.000017857,"output_dbu_cost_per_token":0.000142857,"cache_read_input_token_cost":1.24999e-7,"cache_creation_input_token_cost":1.24999e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"databricks/databricks-gpt-5-mini","object":"model","created":1769507058,"owned_by":"databricks","model_name":"databricks-gpt-5-mini","context_length":272000,"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_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,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":2.4997e-7,"output_cost_per_token":1.99997e-6,"input_dbu_cost_per_token":3.571e-6,"output_dbu_cost_per_token":0.000028571,"cache_read_input_token_cost":2.4997e-8,"cache_creation_input_token_cost":2.4997e-7},"list_pricing":{"input_cost_per_token":2.4997e-7,"output_cost_per_token":1.99997e-6,"input_dbu_cost_per_token":3.571e-6,"output_dbu_cost_per_token":0.000028571,"cache_read_input_token_cost":2.4997e-8,"cache_creation_input_token_cost":2.4997e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"databricks/databricks-gpt-5-nano","object":"model","created":1769507058,"owned_by":"databricks","model_name":"databricks-gpt-5-nano","context_length":272000,"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_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,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":4.998e-8,"output_cost_per_token":3.9998e-7,"input_dbu_cost_per_token":7.14e-7,"output_dbu_cost_per_token":5.714000000000001e-6,"cache_read_input_token_cost":4.998e-9,"cache_creation_input_token_cost":4.998e-8},"list_pricing":{"input_cost_per_token":4.998e-8,"output_cost_per_token":3.9998e-7,"input_dbu_cost_per_token":7.14e-7,"output_dbu_cost_per_token":5.714000000000001e-6,"cache_read_input_token_cost":4.998e-9,"cache_creation_input_token_cost":4.998e-8},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"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,"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_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,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":1.5001e-7,"output_cost_per_token":5.9997e-7,"input_dbu_cost_per_token":2.1429999999999996e-6,"output_dbu_cost_per_token":8.571e-6,"cache_read_input_token_cost":1.5001e-8,"cache_creation_input_token_cost":1.5001e-7},"list_pricing":{"input_cost_per_token":1.5001e-7,"output_cost_per_token":5.9997e-7,"input_dbu_cost_per_token":2.1429999999999996e-6,"output_dbu_cost_per_token":8.571e-6,"cache_read_input_token_cost":1.5001e-8,"cache_creation_input_token_cost":1.5001e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"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,"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_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,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":7e-8,"output_cost_per_token":3.0002e-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":3.0002e-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,"regions":[{"code":"eu","name":"Europe"}],"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,"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_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,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":5.0001e-7,"output_cost_per_token":1.50003e-6,"input_dbu_cost_per_token":7.143e-6,"output_dbu_cost_per_token":0.000021429,"cache_read_input_token_cost":5.0001e-8,"cache_creation_input_token_cost":5.0001e-7},"list_pricing":{"input_cost_per_token":5.0001e-7,"output_cost_per_token":1.50003e-6,"input_dbu_cost_per_token":7.143e-6,"output_dbu_cost_per_token":0.000021429,"cache_read_input_token_cost":5.0001e-8,"cache_creation_input_token_cost":5.0001e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"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,"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_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,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":5.0001e-7,"output_cost_per_token":1.50003e-6,"input_dbu_cost_per_token":7.143e-6,"output_dbu_cost_per_token":0.000021429,"cache_read_input_token_cost":5.0001e-8,"cache_creation_input_token_cost":5.0001e-7},"list_pricing":{"input_cost_per_token":5.0001e-7,"output_cost_per_token":1.50003e-6,"input_dbu_cost_per_token":7.143e-6,"output_dbu_cost_per_token":0.000021429,"cache_read_input_token_cost":5.0001e-8,"cache_creation_input_token_cost":5.0001e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"ovhcloud/gpt-oss-120b","object":"model","created":1769507058,"owned_by":"ovhcloud","model_name":"gpt-oss-120b","context_length":131072,"description":null,"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_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,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"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,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"ovhcloud/gpt-oss-20b","object":"model","created":1769507058,"owned_by":"ovhcloud","model_name":"gpt-oss-20b","context_length":131072,"description":null,"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_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,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"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,"regions":[{"code":"eu","name":"Europe"}],"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,"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_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,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"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,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"ovhcloud/Mistral-7B-Instruct-v0.3","object":"model","created":1769507058,"owned_by":"ovhcloud","model_name":"Mistral-7B-Instruct-v0.3","context_length":65536,"description":null,"source":"https://endpoints.ai.cloud.ovh.net/models/mistral-7b-instruct-v0-3","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":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,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":1.1e-7,"output_cost_per_token":1.1e-7},"list_pricing":{"input_cost_per_token":1.1e-7,"output_cost_per_token":1.1e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"ovhcloud/Mistral-Nemo-Instruct-2407","object":"model","created":1769507058,"owned_by":"ovhcloud","model_name":"Mistral-Nemo-Instruct-2407","context_length":65536,"description":null,"source":"https://endpoints.ai.cloud.ovh.net/models/mistral-nemo-instruct-2407","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":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,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":1.4e-7,"output_cost_per_token":1.4e-7},"list_pricing":{"input_cost_per_token":1.4e-7,"output_cost_per_token":1.4e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"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,"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_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,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"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,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"ovhcloud/Qwen2.5-VL-72B-Instruct","object":"model","created":1769507058,"owned_by":"ovhcloud","model_name":"Qwen2.5-VL-72B-Instruct","context_length":32768,"description":null,"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_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,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"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,"regions":[{"code":"eu","name":"Europe"}],"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,"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":"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_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,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"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,"regions":[{"code":"eu","name":"Europe"}],"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,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":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,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":9e-8,"output_cost_per_token":2.9e-7},"list_pricing":{"input_cost_per_token":9e-8,"output_cost_per_token":2.9e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"amazon/google.gemma-3-27b-it","object":"model","created":1767692616,"owned_by":"amazon","model_name":"google.gemma-3-27b-it","context_length":128000,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":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,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":2.3e-7,"output_cost_per_token":3.8e-7},"list_pricing":{"input_cost_per_token":2.3e-7,"output_cost_per_token":3.8e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"amazon/google.gemma-3-4b-it","object":"model","created":1767692616,"owned_by":"amazon","model_name":"google.gemma-3-4b-it","context_length":128000,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":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,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":4e-8,"output_cost_per_token":8e-8},"list_pricing":{"input_cost_per_token":4e-8,"output_cost_per_token":8e-8},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"amazon/minimax.minimax-m2","object":"model","created":1767692616,"owned_by":"amazon","model_name":"minimax.minimax-m2","context_length":1000000,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":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,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"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,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"amazon/mistral.magistral-small-2509","object":"model","created":1767692616,"owned_by":"amazon","model_name":"mistral.magistral-small-2509","context_length":128000,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":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,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"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,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"amazon/mistral.ministral-3-14b-instruct","object":"model","created":1767692616,"owned_by":"amazon","model_name":"mistral.ministral-3-14b-instruct","context_length":128000,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":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,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":2e-7},"list_pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":2e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"amazon/mistral.ministral-3-3b-instruct","object":"model","created":1767692616,"owned_by":"amazon","model_name":"mistral.ministral-3-3b-instruct","context_length":128000,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":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,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":1e-7},"list_pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":1e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"amazon/mistral.ministral-3-8b-instruct","object":"model","created":1767692616,"owned_by":"amazon","model_name":"mistral.ministral-3-8b-instruct","context_length":128000,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":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,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"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,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"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,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":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,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"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,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"amazon/mistral.voxtral-mini-3b-2507","object":"model","created":1767692616,"owned_by":"amazon","model_name":"mistral.voxtral-mini-3b-2507","context_length":128000,"description":null,"source":null,"capabilities":{"input_modalities":["text","audio"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":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,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":4e-8,"output_cost_per_token":4e-8},"list_pricing":{"input_cost_per_token":4e-8,"output_cost_per_token":4e-8},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"amazon/mistral.voxtral-small-24b-2507","object":"model","created":1767692616,"owned_by":"amazon","model_name":"mistral.voxtral-small-24b-2507","context_length":128000,"description":null,"source":null,"capabilities":{"input_modalities":["text","audio"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":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,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"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,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"amazon/moonshot.kimi-k2-thinking","object":"model","created":1767692616,"owned_by":"amazon","model_name":"moonshot.kimi-k2-thinking","context_length":256000,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":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,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":6e-7,"output_cost_per_token":2.5e-6},"list_pricing":{"input_cost_per_token":6e-7,"output_cost_per_token":2.5e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"amazon/nvidia.nemotron-nano-12b-v2","object":"model","created":1767692616,"owned_by":"amazon","model_name":"nvidia.nemotron-nano-12b-v2","context_length":128000,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":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,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"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,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"amazon/nvidia.nemotron-nano-9b-v2","object":"model","created":1767692616,"owned_by":"amazon","model_name":"nvidia.nemotron-nano-9b-v2","context_length":128000,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":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,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":6e-8,"output_cost_per_token":2.3e-7},"list_pricing":{"input_cost_per_token":6e-8,"output_cost_per_token":2.3e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"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,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":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,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"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,"regions":[{"code":"eu","name":"Europe"}],"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,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":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,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":7e-8,"output_cost_per_token":3e-7},"list_pricing":{"input_cost_per_token":7e-8,"output_cost_per_token":3e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"amazon/openai.gpt-oss-safeguard-120b","object":"model","created":1767692616,"owned_by":"amazon","model_name":"openai.gpt-oss-safeguard-120b","context_length":128000,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":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,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"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,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"amazon/openai.gpt-oss-safeguard-20b","object":"model","created":1767692616,"owned_by":"amazon","model_name":"openai.gpt-oss-safeguard-20b","context_length":128000,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":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,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":7e-8,"output_cost_per_token":2e-7},"list_pricing":{"input_cost_per_token":7e-8,"output_cost_per_token":2e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"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":131072,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":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,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"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,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"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,"description":"","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":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,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"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,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"amazon/qwen.qwen3-next-80b-a3b","object":"model","created":1767692616,"owned_by":"amazon","model_name":"qwen.qwen3-next-80b-a3b","context_length":256000,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":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,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":1.2e-6},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":1.2e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"amazon/qwen.qwen3-vl-235b-a22b","object":"model","created":1767692616,"owned_by":"amazon","model_name":"qwen.qwen3-vl-235b-a22b","context_length":256000,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":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,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":5.3e-7,"output_cost_per_token":2.66e-6},"list_pricing":{"input_cost_per_token":5.3e-7,"output_cost_per_token":2.66e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"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,"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_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,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"mistral/magistral-medium-latest","object":"model","created":1767692616,"owned_by":"mistral","model_name":"magistral-medium-latest","context_length":262144,"description":null,"source":"https://mistral.ai/news/magistral","capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":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":1.5e-6,"output_cost_per_token":7.5e-6,"cache_read_input_token_cost":1.5e-7},"list_pricing":{"input_cost_per_token":1.5e-6,"output_cost_per_token":7.5e-6,"cache_read_input_token_cost":1.5e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"mistral/magistral-small-latest","object":"model","created":1767692616,"owned_by":"mistral","model_name":"magistral-small-latest","context_length":262144,"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_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,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"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,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"mistral/mistral-medium","object":"model","created":1767692616,"owned_by":"mistral","model_name":"mistral-medium","context_length":262144,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":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,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":1.5e-6,"output_cost_per_token":7.5e-6,"cache_read_input_token_cost":1.5e-7},"list_pricing":{"input_cost_per_token":1.5e-6,"output_cost_per_token":7.5e-6,"cache_read_input_token_cost":1.5e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"mistral/mistral-medium-2505","object":"model","created":1767692616,"owned_by":"mistral","model_name":"mistral-medium-2505","context_length":131072,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":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,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"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,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"mistral/mistral-medium-latest","object":"model","created":1767692616,"owned_by":"mistral","model_name":"mistral-medium-latest","context_length":262144,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":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,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":1.5e-6,"output_cost_per_token":7.5e-6,"cache_read_input_token_cost":1.5e-7},"list_pricing":{"input_cost_per_token":1.5e-6,"output_cost_per_token":7.5e-6,"cache_read_input_token_cost":1.5e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"mistral/mistral-small-latest","object":"model","created":1767692616,"owned_by":"mistral","model_name":"mistral-small-latest","context_length":262144,"description":null,"source":"https://mistral.ai/pricing","capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":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,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"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,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"mistral/open-mistral-nemo","object":"model","created":1767692616,"owned_by":"mistral","model_name":"open-mistral-nemo","context_length":131072,"description":null,"source":"https://mistral.ai/technology/","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":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,"regions":[{"code":"eu","name":"Europe"}],"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,"description":null,"source":"https://mistral.ai/technology/","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":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,"regions":[{"code":"eu","name":"Europe"}],"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,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":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,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"vertex/zai-org/glm-4.7-maas","object":"model","created":1766378014,"owned_by":"vertex","model_name":"zai-org/glm-4.7-maas","context_length":200000,"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. It demonstrates significant improvements in executing complex agent tasks while...","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":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,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":6.6e-7,"output_cost_per_token":2.42e-6},"list_pricing":{"input_cost_per_token":6.6e-7,"output_cost_per_token":2.42e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"mistral/devstral-2512","object":"model","created":1765285419,"owned_by":"mistral","model_name":"devstral-2512","context_length":262144,"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. Devstral 2 supports exploring...","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_tool_choice":true,"supports_computer_use":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,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"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,"regions":[{"code":"eu","name":"Europe"}],"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,"description":"Nova 2 Lite is a fast, cost-effective reasoning model for everyday workloads that can process text, images, and videos to generate text. Nova 2 Lite demonstrates standout capabilities in processing...","source":null,"capabilities":{"input_modalities":["text","image","video","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":2.5e-6,"cache_read_input_token_cost":7.5e-8},"list_pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":2.5e-6,"cache_read_input_token_cost":7.5e-8},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"mistral/ministral-14b-2512","object":"model","created":1764681735,"owned_by":"mistral","model_name":"ministral-14b-2512","context_length":262144,"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. A powerful and efficient language...","source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_tool_choice":true,"supports_computer_use":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,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":2e-7,"cache_read_input_token_cost":2e-8},"list_pricing":{"input_cost_per_token":2e-7,"output_cost_per_token":2e-7,"cache_read_input_token_cost":2e-8},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"mistral/ministral-8b-2512","object":"model","created":1764681654,"owned_by":"mistral","model_name":"ministral-8b-2512","context_length":262144,"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_tool_choice":true,"supports_computer_use":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,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":1.5e-7,"cache_read_input_token_cost":1.5e-8},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":1.5e-7,"cache_read_input_token_cost":1.5e-8},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"mistral/ministral-3b-2512","object":"model","created":1764681560,"owned_by":"mistral","model_name":"ministral-3b-2512","context_length":131072,"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_tool_choice":true,"supports_computer_use":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,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":1e-7,"cache_read_input_token_cost":1e-8},"list_pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":1e-7,"cache_read_input_token_cost":1e-8},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"mistral/mistral-large-2512","object":"model","created":1764624472,"owned_by":"mistral","model_name":"mistral-large-2512","context_length":262144,"description":null,"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_tool_choice":true,"supports_computer_use":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,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":1.5e-6,"cache_read_input_token_cost":5e-8},"list_pricing":{"input_cost_per_token":5e-7,"output_cost_per_token":1.5e-6,"cache_read_input_token_cost":5e-8},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"vertex/deepseek-ai/deepseek-v3.2-maas","object":"model","created":1764594642,"owned_by":"vertex","model_name":"deepseek-ai/deepseek-v3.2-maas","context_length":163840,"description":"DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":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,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":6.160000000000001e-7,"output_cost_per_token":1.8480000000000001e-6},"list_pricing":{"input_cost_per_token":6.160000000000001e-7,"output_cost_per_token":1.8480000000000001e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"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,"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":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,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"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,"regions":[{"code":"eu","name":"Europe"}],"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,"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":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":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":true,"supports_assistant_prefill":true,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"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,"regions":[{"code":"eu","name":"Europe"}],"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,"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. It is capable of image generation,...","source":null,"capabilities":{"input_modalities":["image","text"],"output_modalities":["image","text"],"supports_reasoning":false,"supports_web_search":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,"regions":[{"code":"eu","name":"Europe"}],"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,"description":"Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with...","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":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,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"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,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"qwen/qwen3-max","object":"model","created":1758662808,"owned_by":"qwen","model_name":"qwen3-max","context_length":262144,"description":"The Qwen 3 series Max model has undergone specialized upgrades in agent programming and tool invocation compared to the preview version. The officially released model this time has achieved state-of-the-art (SOTA) performance in its field and is better suited to meet the demands of agents operating in more complex scenarios.","source":"https://www.alibabacloud.com/help/en/model-studio/models","capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":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,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"tiered_pricing":[{"range":[0,32000],"input_cost_per_token":7.799999999999999e-7,"output_cost_per_token":3.9e-6,"cache_read_input_token_cost":1.56e-7,"cache_creation_input_token_cost":9.75e-7},{"range":[32000,128000],"input_cost_per_token":1.5599999999999999e-6,"output_cost_per_token":7.8e-6,"cache_read_input_token_cost":3.12e-7,"cache_creation_input_token_cost":1.95e-6},{"range":[128000,256000],"input_cost_per_token":1.95e-6,"output_cost_per_token":9.75e-6,"cache_read_input_token_cost":3.8999999999999997e-7,"cache_creation_input_token_cost":2.4375e-6}],"input_cost_per_token":7.799999999999999e-7,"output_cost_per_token":3.9e-6,"cache_read_input_token_cost":1.56e-7,"cache_creation_input_token_cost":9.75e-7},"list_pricing":{"tiered_pricing":[{"range":[0,32000],"input_cost_per_token":1.2e-6,"output_cost_per_token":6e-6,"cache_read_input_token_cost":2.4e-7,"cache_creation_input_token_cost":1.5e-6},{"range":[32000,128000],"input_cost_per_token":2.4e-6,"output_cost_per_token":0.000012,"cache_read_input_token_cost":4.8e-7,"cache_creation_input_token_cost":3e-6},{"range":[128000,256000],"input_cost_per_token":3e-6,"output_cost_per_token":0.000015,"cache_read_input_token_cost":6e-7,"cache_creation_input_token_cost":3.75e-6}],"input_cost_per_token":1.2e-6,"output_cost_per_token":6e-6,"cache_read_input_token_cost":2.4e-7,"cache_creation_input_token_cost":1.5e-6},"discount":0.35,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"qwen/qwen3-max-2026-01-23","object":"model","created":1758662808,"owned_by":"qwen","model_name":"qwen3-max-2026-01-23","context_length":262144,"description":"Compared with the snapshot as of September 23, 2025, the Qwen-3 series Max model in this release achieves an effective integration of thinking and non-thinking modes, resulting in a comprehensive and substantial improvement in the model’s overall performance. In thinking mode, the model simultaneously supports web search, web information extraction, and a code interpreter tool, enabling it to tackle more complex and challenging problems with greater accuracy by leveraging external tools while engaging in slow, deliberative reasoning. This version is based on a snapshot taken on January 23, 2026.","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":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,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"tiered_pricing":[{"range":[0,32000],"input_cost_per_token":7.799999999999999e-7,"output_cost_per_token":3.9e-6},{"range":[32000,128000],"input_cost_per_token":1.5599999999999999e-6,"output_cost_per_token":7.8e-6},{"range":[128000,256000],"input_cost_per_token":1.95e-6,"output_cost_per_token":9.75e-6}],"input_cost_per_token":7.799999999999999e-7,"output_cost_per_token":3.9e-6},"list_pricing":{"tiered_pricing":[{"range":[0,32000],"input_cost_per_token":1.2e-6,"output_cost_per_token":6e-6},{"range":[32000,128000],"input_cost_per_token":2.4e-6,"output_cost_per_token":0.000012},{"range":[128000,256000],"input_cost_per_token":3e-6,"output_cost_per_token":0.000015}],"input_cost_per_token":1.2e-6,"output_cost_per_token":6e-6},"discount":0.35,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"vertex/qwen/qwen3-next-80b-a3b-thinking-maas","object":"model","created":1757612284,"owned_by":"vertex","model_name":"qwen/qwen3-next-80b-a3b-thinking-maas","context_length":262144,"description":"Qwen3-Next-80B-A3B-Thinking is a reasoning-first chat model in the Qwen3-Next line that outputs structured “thinking” traces by default. It’s designed for hard multi-step problems; math proofs, code synthesis/debugging, logic, and agentic...","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":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,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":1.65e-7,"output_cost_per_token":1.32e-6},"list_pricing":{"input_cost_per_token":1.65e-7,"output_cost_per_token":1.32e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"vertex/qwen/qwen3-next-80b-a3b-instruct-maas","object":"model","created":1757612213,"owned_by":"vertex","model_name":"qwen/qwen3-next-80b-a3b-instruct-maas","context_length":262144,"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. It targets complex tasks across reasoning, code generation, knowledge QA, and multilingual...","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":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,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":1.65e-7,"output_cost_per_token":1.32e-6},"list_pricing":{"input_cost_per_token":1.65e-7,"output_cost_per_token":1.32e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"qwen/qwen-plus","object":"model","created":1757347599,"owned_by":"qwen","model_name":"qwen-plus","context_length":1000000,"description":"Qwen-Plus is an enhanced version of the Qwen ultra-large language model that supports multiple input languages such as Chinese and English. Compared to previous versions, it shows significant improvements in both Chinese and English code generation, logical reasoning, and multilingual abilities. The response style has been greatly adjusted to align with human preferences, with noticeable enhancements in the level of detail and clarity of responses. Specialized improvements have been made in creative writing, adherence to JSON formatting, and role-playing 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_tool_choice":true,"supports_computer_use":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,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"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,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"qwen/qwen-plus-2025-12-01","object":"model","created":1757347599,"owned_by":"qwen","model_name":"qwen-plus-2025-12-01","context_length":1000000,"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_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"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,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"scaleway/gpt-oss-120b","object":"model","created":1755093042,"owned_by":"scaleway","model_name":"gpt-oss-120b","context_length":128000,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":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,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":1.7194499594209808e-7,"output_cost_per_token":6.877799837683923e-7},"list_pricing":{"input_cost_per_token":1.7194499594209808e-7,"output_cost_per_token":6.877799837683923e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"scaleway/holo2-30b-a3b","object":"model","created":1755006551,"owned_by":"scaleway","model_name":"holo2-30b-a3b","context_length":22000,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":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,"regions":[{"code":"eu","name":"Europe"}],"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,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":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,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":1.7194499594209808e-7,"output_cost_per_token":4.012049905315622e-7},"list_pricing":{"input_cost_per_token":1.7194499594209808e-7,"output_cost_per_token":4.012049905315622e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"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,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":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,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":2.2925999458946416e-7,"output_cost_per_token":9.170399783578566e-7},"list_pricing":{"input_cost_per_token":2.2925999458946416e-7,"output_cost_per_token":9.170399783578566e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"mistral/codestral-2508","object":"model","created":1754079630,"owned_by":"mistral","model_name":"codestral-2508","context_length":256000,"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.\n\n[Blog Post](https://mistral.ai/news/codestral-25-08)","source":"https://mistral.ai/news/codestral-25-08","capabilities":{"input_modalities":["text","file"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_tool_choice":true,"supports_computer_use":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,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":9e-7,"cache_read_input_token_cost":3e-8},"list_pricing":{"input_cost_per_token":3e-7,"output_cost_per_token":9e-7,"cache_read_input_token_cost":3e-8},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"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,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":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,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":8.597249797104905e-7,"output_cost_per_token":2.579174939131471e-6},"list_pricing":{"input_cost_per_token":8.597249797104905e-7,"output_cost_per_token":2.579174939131471e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"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,"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. It offers improved throughput, faster token generation, and better performance...","source":null,"capabilities":{"input_modalities":["text","image","file","audio","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":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":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":4e-7,"input_cost_per_audio_token":3e-7,"input_cost_per_image_token":1e-7,"cache_read_input_token_cost":1e-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":8.33333333333333e-8,"output_cost_per_reasoning_token":4e-7,"cache_read_input_audio_token_cost":3e-8,"google_maps_grounding_cost_per_query":0.025},"list_pricing":{"input_cost_per_token":1e-7,"output_cost_per_token":4e-7,"input_cost_per_audio_token":3e-7,"input_cost_per_image_token":1e-7,"cache_read_input_token_cost":1e-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":8.33333333333333e-8,"output_cost_per_reasoning_token":4e-7,"cache_read_input_audio_token_cost":3e-8,"google_maps_grounding_cost_per_query":0.025},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"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,"description":"Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in \"thinking\" capabilities, enabling it to provide responses with greater...","source":null,"capabilities":{"input_modalities":["file","image","text","audio","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":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":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":true,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"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,"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,"google_maps_grounding_cost_per_query":0.025},"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,"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,"google_maps_grounding_cost_per_query":0.025},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"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,"description":"Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...","source":null,"capabilities":{"input_modalities":["text","image","file","audio","video"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":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":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":0.00001,"input_cost_per_audio_token":1.25e-6,"input_cost_per_image_token":1.25e-6,"cache_read_input_token_cost":1.25e-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":3.75e-7,"output_cost_per_reasoning_token":0.00001,"cache_read_input_audio_token_cost":1.25e-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_audio_token_above_200k_tokens":2.5e-6,"cache_read_input_token_cost_above_200k_tokens":2.5e-7,"cache_creation_input_token_cost_above_200k_tokens":2.5e-7,"cache_read_input_audio_token_cost_above_200k_tokens":2.5e-7},"list_pricing":{"input_cost_per_token":1.25e-6,"output_cost_per_token":0.00001,"input_cost_per_audio_token":1.25e-6,"input_cost_per_image_token":1.25e-6,"cache_read_input_token_cost":1.25e-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":3.75e-7,"output_cost_per_reasoning_token":0.00001,"cache_read_input_audio_token_cost":1.25e-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_audio_token_above_200k_tokens":2.5e-6,"cache_read_input_token_cost_above_200k_tokens":2.5e-7,"cache_creation_input_token_cost_above_200k_tokens":2.5e-7,"cache_read_input_audio_token_cost_above_200k_tokens":2.5e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"mistral/mistral-medium-3","object":"model","created":1746627341,"owned_by":"mistral","model_name":"mistral-medium-3","context_length":262144,"description":"Mistral Medium 3 is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances state-of-the-art reasoning and multimodal performance with 8× lower cost...","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":true,"supports_web_search":false,"supports_tool_choice":true,"supports_computer_use":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,"reasoning":{"mandatory":true,"default_effort":null,"supported_efforts":[]}},"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,"regions":[{"code":"eu","name":"Europe"}],"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,"description":null,"source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":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,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":1.0316699756525885e-6,"output_cost_per_token":1.0316699756525885e-6},"list_pricing":{"input_cost_per_token":1.0316699756525885e-6,"output_cost_per_token":1.0316699756525885e-6},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"amazon/amazon.nova-lite-v1:0","object":"model","created":1733437363,"owned_by":"amazon","model_name":"amazon.nova-lite-v1:0","context_length":300000,"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. Amazon Nova Lite...","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"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,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"amazon/amazon.nova-micro-v1:0","object":"model","created":1733437237,"owned_by":"amazon","model_name":"amazon.nova-micro-v1:0","context_length":128000,"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. With a context length...","source":null,"capabilities":{"input_modalities":["text"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"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,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"amazon/amazon.nova-pro-v1:0","object":"model","created":1733436303,"owned_by":"amazon","model_name":"amazon.nova-pro-v1:0","context_length":300000,"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. As of December...","source":null,"capabilities":{"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_tool_choice":true,"supports_computer_use":false,"supports_prompt_caching":true,"supports_response_schema":true,"supports_system_messages":false,"supports_function_calling":true,"supports_native_streaming":false,"supports_assistant_prefill":false,"supports_embedding_image_input":false,"supports_parallel_function_calling":false,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":8e-7,"output_cost_per_token":3.2e-6,"cache_read_input_token_cost":2e-7},"list_pricing":{"input_cost_per_token":8e-7,"output_cost_per_token":3.2e-6,"cache_read_input_token_cost":2e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"mistral/mistral-large-2407","object":"model","created":1731978415,"owned_by":"mistral","model_name":"mistral-large-2407","context_length":131072,"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. Read the launch announcement [here](https://mistral.ai/news/mistral-large-2407/)....","source":null,"capabilities":{"input_modalities":["text","file"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":false,"supports_tool_choice":true,"supports_computer_use":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,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"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,"regions":[{"code":"eu","name":"Europe"}],"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,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":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,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"scaleway/pixtral-12b-2409","object":"model","created":1730385501,"owned_by":"scaleway","model_name":"pixtral-12b-2409","context_length":128000,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":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,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":2.2925999458946416e-7,"output_cost_per_token":2.2925999458946416e-7},"list_pricing":{"input_cost_per_token":2.2925999458946416e-7,"output_cost_per_token":2.2925999458946416e-7},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"mistral/ministral-8b-latest","object":"model","created":1729123200,"owned_by":"mistral","model_name":"ministral-8b-latest","context_length":262144,"description":null,"source":null,"capabilities":{"input_modalities":["text","image"],"output_modalities":["text"],"supports_reasoning":false,"supports_web_search":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,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":1.5e-7,"cache_read_input_token_cost":1.5e-8},"list_pricing":{"input_cost_per_token":1.5e-7,"output_cost_per_token":1.5e-7,"cache_read_input_token_cost":1.5e-8},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"mistral/mistral-large-latest","object":"model","created":1708905600,"owned_by":"mistral","model_name":"mistral-large-latest","context_length":262144,"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. Read the launch announcement [here](https://mistral.ai/news/mistral-large-2407/)....","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_tool_choice":true,"supports_computer_use":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,"reasoning":{"mandatory":false,"default_effort":null,"supported_efforts":[]}},"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,"regions":[{"code":"eu","name":"Europe"}],"alias_of":null},{"id":"vertex/gemini-flash-latest","object":"model","created":1788362056,"owned_by":"vertex","model_name":"gemini-3.8-flash","context_length":1048576,"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_tool_choice":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":0.014},"list_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":0.014},"discount":null,"regions":[{"code":"eu","name":"Europe"}],"alias_of":"vertex/gemini-3.8-flash"}]}