[ { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00001, "output_cost_per_token": 0.00005, "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "cache_creation_input_token_cost_above_1hr": 0.00002, "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "model_id": "azure_ai/claude-fable-5", "model_name": "Claude Fable 5", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 10, "output_cost_per_million": 50, "cache_read_cost_per_token": 0.000001, "cache_read_cost_per_million": 1, "cache_write_cost_per_token": 0.0000125, "cache_write_cost_per_million": 12.5, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000005, "max_input_tokens": 200000, "max_output_tokens": 64000, "cache_creation_input_token_cost_above_1hr": 0.000002, "max_tokens": 64000, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "azure_ai/claude-haiku-4-5", "model_name": "Claude Haiku 4 5", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1, "output_cost_per_million": 5, "cache_read_cost_per_token": 1e-7, "cache_read_cost_per_million": 0.09999999999999999, "cache_write_cost_per_token": 0.00000125, "cache_write_cost_per_million": 1.25, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000015, "output_cost_per_token": 0.000075, "max_input_tokens": 200000, "max_output_tokens": 32000, "cache_creation_input_token_cost_above_1hr": 0.00003, "max_tokens": 32000, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "azure_ai/claude-opus-4-1", "model_name": "Claude Opus 4 1", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 15, "output_cost_per_million": 75, "cache_read_cost_per_token": 0.0000015, "cache_read_cost_per_million": 1.5, "cache_write_cost_per_token": 0.00001875, "cache_write_cost_per_million": 18.75, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025, "max_input_tokens": 200000, "max_output_tokens": 64000, "cache_creation_input_token_cost_above_1hr": 0.00001, "max_tokens": 64000, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_output_config": true, "model_id": "azure_ai/claude-opus-4-5", "model_name": "Claude Opus 4 5", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 5, "output_cost_per_million": 25, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0.00000625, "cache_write_cost_per_million": 6.25, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025, "max_input_tokens": 200000, "max_output_tokens": 128000, "supports_adaptive_thinking": true, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "cache_creation_input_token_cost_above_1hr": 0.00001, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_output_config": true, "supports_max_reasoning_effort": true, "model_id": "azure_ai/claude-opus-4-6", "model_name": "Claude Opus 4 6", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 5, "output_cost_per_million": 25, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0.00000625, "cache_write_cost_per_million": 6.25, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025, "max_input_tokens": 200000, "max_output_tokens": 128000, "supports_adaptive_thinking": true, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "cache_creation_input_token_cost_above_1hr": 0.00001, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "model_id": "azure_ai/claude-opus-4-7", "model_name": "Claude Opus 4 7", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 5, "output_cost_per_million": 25, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0.00000625, "cache_write_cost_per_million": 6.25, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025, "max_input_tokens": 200000, "max_output_tokens": 128000, "supports_adaptive_thinking": true, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "cache_creation_input_token_cost_above_1hr": 0.00001, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "model_id": "azure_ai/claude-opus-4-8", "model_name": "Claude Opus 4 8", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 5, "output_cost_per_million": 25, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0.00000625, "cache_write_cost_per_million": 6.25, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 200000, "max_output_tokens": 64000, "cache_creation_input_token_cost_above_1hr": 0.000006, "max_tokens": 64000, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "azure_ai/claude-sonnet-4-5", "model_name": "Claude Sonnet 4 5", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 3, "output_cost_per_million": 15, "cache_read_cost_per_token": 3e-7, "cache_read_cost_per_million": 0.3, "cache_write_cost_per_token": 0.00000375, "cache_write_cost_per_million": 3.75, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 1000000, "max_output_tokens": 64000, "supports_adaptive_thinking": true, "cache_creation_input_token_cost_above_1hr": 0.000006, "max_tokens": 64000, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_max_reasoning_effort": true, "supports_tool_choice": true, "supports_output_config": true, "model_id": "azure_ai/claude-sonnet-4-6", "model_name": "Claude Sonnet 4 6", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 3, "output_cost_per_million": 15, "cache_read_cost_per_token": 3e-7, "cache_read_cost_per_million": 0.3, "cache_write_cost_per_token": 0.00000375, "cache_write_cost_per_million": 3.75, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.00001, "max_input_tokens": 1000000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_1hr": 0.000004, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "model_id": "azure_ai/claude-sonnet-5", "model_name": "Claude Sonnet 5", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2, "output_cost_per_million": 10, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 0.0000025, "cache_write_cost_per_million": 2.5, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "input_cost_per_token": 1e-7, "output_cost_per_token": 0, "max_input_tokens": 512, "max_tokens": 512, "output_vector_size": 1024, "source": "https://azuremarketplace.microsoft.com/en-us/marketplace/apps/cohere.cohere-embed-v3-english-offer?tab=PlansAndPrice", "supports_embedding_image_input": true, "model_id": "azure_ai/Cohere-embed-v3-english", "model_name": "Cohere Embed V3 English", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_output_tokens": 0, "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1e-7, "output_cost_per_token": 0, "max_input_tokens": 512, "max_tokens": 512, "output_vector_size": 1024, "source": "https://azuremarketplace.microsoft.com/en-us/marketplace/apps/cohere.cohere-embed-v3-english-offer?tab=PlansAndPrice", "supports_embedding_image_input": true, "model_id": "azure_ai/Cohere-embed-v3-multilingual", "model_name": "Cohere Embed V3 Multilingual", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_output_tokens": 0, "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0, "output_cost_per_token": 0, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_query": 0.002, "max_tokens": 4096, "model_id": "azure_ai/cohere-rerank-v3-english", "model_name": "Cohere Rerank V3 English", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "rerank", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0, "output_cost_per_token": 0, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_query": 0.002, "max_tokens": 4096, "model_id": "azure_ai/cohere-rerank-v3-multilingual", "model_name": "Cohere Rerank V3 Multilingual", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "rerank", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0, "output_cost_per_token": 0, "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_query": 0.002, "max_tokens": 4096, "model_id": "azure_ai/cohere-rerank-v3.5", "model_name": "Cohere Rerank V3.5", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "rerank", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0, "output_cost_per_token": 0, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_query": 0.002, "max_tokens": 32768, "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/introducing-cohere-rerank-4-0-in-microsoft-foundry/4477076", "model_id": "azure_ai/cohere-rerank-v4.0-fast", "model_name": "Cohere Rerank V4.0 Fast", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "rerank", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0, "output_cost_per_token": 0, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_query": 0.0025, "max_tokens": 32768, "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/introducing-cohere-rerank-4-0-in-microsoft-foundry/4477076", "model_id": "azure_ai/cohere-rerank-v4.0-pro", "model_name": "Cohere Rerank V4.0 Pro", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "rerank", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.00000135, "output_cost_per_token": 0.0000054, "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "source": "https://techcommunity.microsoft.com/blog/machinelearningblog/deepseek-r1-improved-performance-higher-limits-and-transparent-pricing/4386367", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "azure_ai/deepseek-r1", "model_name": "DeepSeek R1", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.35, "output_cost_per_million": 5.4, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.00000114, "output_cost_per_token": 0.00000456, "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "source": "https://techcommunity.microsoft.com/blog/machinelearningblog/announcing-deepseek-v3-on-azure-ai-foundry-and-github/4390438", "supports_tool_choice": true, "model_id": "azure_ai/deepseek-v3", "model_name": "DeepSeek V3", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.1400000000000001, "output_cost_per_million": 4.5600000000000005, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.00000114, "output_cost_per_token": 0.00000456, "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "source": "https://techcommunity.microsoft.com/blog/machinelearningblog/announcing-deepseek-v3-on-azure-ai-foundry-and-github/4390438", "supports_tool_choice": true, "model_id": "azure_ai/deepseek-v3-0324", "model_name": "Deepseek V3 0324", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.1400000000000001, "output_cost_per_million": 4.5600000000000005, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.00000123, "output_cost_per_token": 0.00000494, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/deepseek/", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "azure_ai/deepseek-v3.1", "model_name": "Deepseek V3.1", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.23, "output_cost_per_million": 4.94, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 5.8e-7, "output_cost_per_token": 0.00000168, "max_input_tokens": 163840, "max_output_tokens": 163840, "max_tokens": 163840, "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/introducing-deepseek-v3-2-and-deepseek-v3-2-speciale-in-microsoft-foundry/4477549", "supports_assistant_prefill": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "azure_ai/deepseek-v3.2", "model_name": "Deepseek V3.2", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.58, "output_cost_per_million": 1.68, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 5.8e-7, "output_cost_per_token": 0.00000168, "max_input_tokens": 163840, "max_output_tokens": 163840, "max_tokens": 163840, "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/introducing-deepseek-v3-2-and-deepseek-v3-2-speciale-in-microsoft-foundry/4477549", "supports_assistant_prefill": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "azure_ai/deepseek-v3.2-speciale", "model_name": "Deepseek V3.2 Speciale", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.58, "output_cost_per_million": 1.68, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 1.9e-7, "output_cost_per_token": 5.1e-7, "max_input_tokens": 1000000, "max_output_tokens": 384000, "max_tokens": 384000, "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/deepseek/", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "azure_ai/deepseek-v4-flash", "model_name": "Deepseek V4 Flash", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.19, "output_cost_per_million": 0.51, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.00000174, "output_cost_per_token": 0.00000348, "max_input_tokens": 1000000, "max_output_tokens": 384000, "max_tokens": 384000, "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/deepseek/", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "azure_ai/deepseek-v4-pro", "model_name": "Deepseek V4 Pro", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.74, "output_cost_per_million": 3.48, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "ocr_cost_per_page": 0.01, "supported_endpoints": [ "/v1/ocr" ], "source": "https://azure.microsoft.com/en-us/pricing/details/ai-document-intelligence/", "model_id": "azure_ai/doc-intelligence/prebuilt-document", "model_name": "Prebuilt Document", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "ocr", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "ocr_cost_per_page": 0.01, "supported_endpoints": [ "/v1/ocr" ], "source": "https://azure.microsoft.com/en-us/pricing/details/ai-document-intelligence/", "model_id": "azure_ai/doc-intelligence/prebuilt-layout", "model_name": "Prebuilt Layout", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "ocr", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "ocr_cost_per_page": 0.0015, "supported_endpoints": [ "/v1/ocr" ], "source": "https://azure.microsoft.com/en-us/pricing/details/ai-document-intelligence/", "model_id": "azure_ai/doc-intelligence/prebuilt-read", "model_name": "Prebuilt Read", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "ocr", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1.2e-7, "output_cost_per_token": 0, "max_input_tokens": 128000, "max_tokens": 128000, "output_vector_size": 3072, "source": "https://azuremarketplace.microsoft.com/pt-br/marketplace/apps/cohere.cohere-embed-4-offer?tab=PlansAndPrice", "supported_endpoints": [ "/v1/embeddings" ], "supported_modalities": [ "text", "image" ], "supports_embedding_image_input": true, "model_id": "azure_ai/embed-v-4-0", "model_name": "Embed V 4 0", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_output_tokens": 0, "input_cost_per_million": 0.12, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "output_cost_per_image": 0.04, "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/black-forest-labs-flux-1-kontext-pro-and-flux1-1-pro-now-available-in-azure-ai-f/4434659", "supported_endpoints": [ "/v1/images/generations" ], "model_id": "azure_ai/FLUX-1.1-pro", "model_name": "FLUX 1.1 Pro", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "image", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "output_cost_per_image": 0.04, "source": "https://azuremarketplace.microsoft.com/pt-br/marketplace/apps/cohere.cohere-embed-4-offer?tab=PlansAndPrice", "supported_endpoints": [ "/v1/images/generations" ], "model_id": "azure_ai/FLUX.1-Kontext-pro", "model_name": "FLUX.1 Kontext Pro", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "image", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "output_cost_per_image": 0.04, "source": "https://ai.azure.com/explore/models/flux.2-pro/version/1/registry/azureml-blackforestlabs", "supported_endpoints": [ "/v1/images/generations" ], "model_id": "azure_ai/flux.2-pro", "model_name": "Flux.2 Pro", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "image", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": false, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://devblogs.microsoft.com/foundry/announcing-grok-3-and-grok-3-mini-on-azure-ai-foundry/", "supports_tool_choice": true, "supports_web_search": true, "model_id": "azure_ai/global/grok-3", "model_name": "Grok 3", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 3, "output_cost_per_million": 15, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": false, "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.00000127, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://devblogs.microsoft.com/foundry/announcing-grok-3-and-grok-3-mini-on-azure-ai-foundry/", "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "azure_ai/global/grok-3-mini", "model_name": "Grok 3 Mini", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.25, "output_cost_per_million": 1.27, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.000015, "max_input_tokens": 1050000, "max_output_tokens": 128000, "cache_read_input_token_cost_above_272k_tokens": 5e-7, "cache_read_input_token_cost_priority": 5e-7, "cache_read_input_token_cost_above_272k_tokens_priority": 0.000001, "input_cost_per_token_above_272k_tokens": 0.000005, "input_cost_per_token_priority": 0.000005, "input_cost_per_token_above_272k_tokens_priority": 0.00001, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.0000225, "output_cost_per_token_priority": 0.00003, "output_cost_per_token_above_272k_tokens_priority": 0.000045, "source": "https://ai.azure.com/catalog/models/gpt-5.4", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true, "model_id": "azure_ai/gpt-5.4", "model_name": "GPT-5.4", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2.5, "output_cost_per_million": 15, "cache_read_cost_per_token": 2.5e-7, "cache_read_cost_per_million": 0.25, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.000015, "max_input_tokens": 1050000, "max_output_tokens": 128000, "cache_read_input_token_cost_above_272k_tokens": 5e-7, "cache_read_input_token_cost_priority": 5e-7, "cache_read_input_token_cost_above_272k_tokens_priority": 0.000001, "input_cost_per_token_above_272k_tokens": 0.000005, "input_cost_per_token_priority": 0.000005, "input_cost_per_token_above_272k_tokens_priority": 0.00001, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.0000225, "output_cost_per_token_priority": 0.00003, "output_cost_per_token_above_272k_tokens_priority": 0.000045, "source": "https://ai.azure.com/catalog/models/gpt-5.4", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true, "model_id": "azure_ai/gpt-5.4-2026-03-05", "model_name": "GPT-5.4 (Mar 2026)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2.5, "output_cost_per_million": 15, "cache_read_cost_per_token": 2.5e-7, "cache_read_cost_per_million": 0.25, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 7.5e-7, "output_cost_per_token": 0.0000045, "max_input_tokens": 400000, "max_output_tokens": 128000, "cache_read_input_token_cost_above_272k_tokens": 1.5e-7, "cache_read_input_token_cost_priority": 1.5e-7, "cache_read_input_token_cost_above_272k_tokens_priority": 3e-7, "input_cost_per_token_above_272k_tokens": 0.0000015, "input_cost_per_token_priority": 0.0000015, "input_cost_per_token_above_272k_tokens_priority": 0.000003, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.00000675, "output_cost_per_token_priority": 0.000009, "output_cost_per_token_above_272k_tokens_priority": 0.0000135, "source": "https://ai.azure.com/catalog/models/gpt-5.4-mini", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "model_id": "azure_ai/gpt-5.4-mini", "model_name": "GPT-5.4 Mini", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.75, "output_cost_per_million": 4.5, "cache_read_cost_per_token": 7.5e-8, "cache_read_cost_per_million": 0.075, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 7.5e-7, "output_cost_per_token": 0.0000045, "max_input_tokens": 400000, "max_output_tokens": 128000, "cache_read_input_token_cost_above_272k_tokens": 1.5e-7, "cache_read_input_token_cost_priority": 1.5e-7, "cache_read_input_token_cost_above_272k_tokens_priority": 3e-7, "input_cost_per_token_above_272k_tokens": 0.0000015, "input_cost_per_token_priority": 0.0000015, "input_cost_per_token_above_272k_tokens_priority": 0.000003, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.00000675, "output_cost_per_token_priority": 0.000009, "output_cost_per_token_above_272k_tokens_priority": 0.0000135, "source": "https://ai.azure.com/catalog/models/gpt-5.4-mini", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "model_id": "azure_ai/gpt-5.4-mini-2026-03-17", "model_name": "GPT-5.4 Mini (Mar 2026)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.75, "output_cost_per_million": 4.5, "cache_read_cost_per_token": 7.5e-8, "cache_read_cost_per_million": 0.075, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2e-7, "output_cost_per_token": 0.00000125, "max_input_tokens": 400000, "max_output_tokens": 128000, "cache_read_input_token_cost_above_272k_tokens": 4e-8, "cache_read_input_token_cost_priority": 4e-8, "cache_read_input_token_cost_above_272k_tokens_priority": 8e-8, "input_cost_per_token_above_272k_tokens": 4e-7, "input_cost_per_token_priority": 4e-7, "input_cost_per_token_above_272k_tokens_priority": 8e-7, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.000001875, "output_cost_per_token_priority": 0.0000025, "output_cost_per_token_above_272k_tokens_priority": 0.00000375, "source": "https://ai.azure.com/catalog/models/gpt-5.4-nano", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "model_id": "azure_ai/gpt-5.4-nano", "model_name": "GPT-5.4 Nano", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.19999999999999998, "output_cost_per_million": 1.25, "cache_read_cost_per_token": 2e-8, "cache_read_cost_per_million": 0.02, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2e-7, "output_cost_per_token": 0.00000125, "max_input_tokens": 400000, "max_output_tokens": 128000, "cache_read_input_token_cost_above_272k_tokens": 4e-8, "cache_read_input_token_cost_priority": 4e-8, "cache_read_input_token_cost_above_272k_tokens_priority": 8e-8, "input_cost_per_token_above_272k_tokens": 4e-7, "input_cost_per_token_priority": 4e-7, "input_cost_per_token_above_272k_tokens_priority": 8e-7, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.000001875, "output_cost_per_token_priority": 0.0000025, "output_cost_per_token_above_272k_tokens_priority": 0.00000375, "source": "https://ai.azure.com/catalog/models/gpt-5.4-nano", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "model_id": "azure_ai/gpt-5.4-nano-2026-03-17", "model_name": "GPT-5.4 Nano (Mar 2026)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.19999999999999998, "output_cost_per_million": 1.25, "cache_read_cost_per_token": 2e-8, "cache_read_cost_per_million": 0.02, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": false, "input_cost_per_token": 0.00003, "output_cost_per_token": 0.00018, "max_input_tokens": 1050000, "max_output_tokens": 128000, "cache_read_input_token_cost_above_272k_tokens": 0.000006, "cache_read_input_token_cost_priority": 0.000006, "cache_read_input_token_cost_above_272k_tokens_priority": 0.000012, "input_cost_per_token_above_272k_tokens": 0.00006, "input_cost_per_token_priority": 0.00006, "input_cost_per_token_above_272k_tokens_priority": 0.00012, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.00027, "output_cost_per_token_priority": 0.00036, "output_cost_per_token_above_272k_tokens_priority": 0.00054, "source": "https://ai.azure.com/catalog/models/gpt-5.4-pro", "supported_endpoints": [ "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true, "model_id": "azure_ai/gpt-5.4-pro", "model_name": "GPT-5.4 Pro", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 30, "output_cost_per_million": 180, "cache_read_cost_per_token": 0.000003, "cache_read_cost_per_million": 3, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": false, "input_cost_per_token": 0.00003, "output_cost_per_token": 0.00018, "max_input_tokens": 1050000, "max_output_tokens": 128000, "cache_read_input_token_cost_above_272k_tokens": 0.000006, "cache_read_input_token_cost_priority": 0.000006, "cache_read_input_token_cost_above_272k_tokens_priority": 0.000012, "input_cost_per_token_above_272k_tokens": 0.00006, "input_cost_per_token_priority": 0.00006, "input_cost_per_token_above_272k_tokens_priority": 0.00012, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.00027, "output_cost_per_token_priority": 0.00036, "output_cost_per_token_above_272k_tokens_priority": 0.00054, "source": "https://ai.azure.com/catalog/models/gpt-5.4-pro", "supported_endpoints": [ "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": true, "model_id": "azure_ai/gpt-5.4-pro-2026-03-05", "model_name": "GPT-5.4 Pro (Mar 2026)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 30, "output_cost_per_million": 180, "cache_read_cost_per_token": 0.000003, "cache_read_cost_per_million": 3, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.00003, "max_input_tokens": 1050000, "max_output_tokens": 128000, "cache_read_input_token_cost_above_272k_tokens": 0.000001, "cache_read_input_token_cost_priority": 0.000001, "cache_read_input_token_cost_above_272k_tokens_priority": 0.000002, "input_cost_per_token_above_272k_tokens": 0.00001, "input_cost_per_token_priority": 0.00001, "input_cost_per_token_above_272k_tokens_priority": 0.00002, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.000045, "output_cost_per_token_priority": 0.00006, "output_cost_per_token_above_272k_tokens_priority": 0.00009, "source": "https://ai.azure.com/catalog/models/gpt-5.5", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "model_id": "azure_ai/gpt-5.5", "model_name": "GPT-5.5", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 5, "output_cost_per_million": 30, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.00003, "max_input_tokens": 1050000, "max_output_tokens": 128000, "cache_read_input_token_cost_above_272k_tokens": 0.000001, "cache_read_input_token_cost_priority": 0.000001, "cache_read_input_token_cost_above_272k_tokens_priority": 0.000002, "input_cost_per_token_above_272k_tokens": 0.00001, "input_cost_per_token_priority": 0.00001, "input_cost_per_token_above_272k_tokens_priority": 0.00002, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.000045, "output_cost_per_token_priority": 0.00006, "output_cost_per_token_above_272k_tokens_priority": 0.00009, "source": "https://ai.azure.com/catalog/models/gpt-5.5", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "model_id": "azure_ai/gpt-5.5-2026-04-23", "model_name": "GPT-5.5 (Apr 2026)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 5, "output_cost_per_million": 30, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 1.5e-7, "output_cost_per_token": 6e-7, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", "supports_tool_choice": true, "model_id": "azure_ai/gpt-oss-120b", "model_name": "GPT Oss 120B", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.15, "output_cost_per_million": 0.6, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true, "supports_vision": false }, { "supports_function_calling": true, "supports_response_schema": false, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/grok/", "supports_tool_choice": true, "supports_web_search": true, "model_id": "azure_ai/grok-3", "model_name": "Grok 3", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 3, "output_cost_per_million": 15, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": false, "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.00000127, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/grok/", "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "azure_ai/grok-3-mini", "model_name": "Grok 3 Mini", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.25, "output_cost_per_million": 1.27, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/grok/", "supports_tool_choice": true, "supports_web_search": true, "model_id": "azure_ai/grok-4", "model_name": "Grok 4", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 3, "output_cost_per_million": 15, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 2e-7, "output_cost_per_token": 5e-7, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://techcommunity.microsoft.com/t5/Azure-AI-Foundry-Blog/Grok-4-0-Goes-GA-in-Microsoft-Foundry-and-Grok-4-1-Fast-Arrives/ba-p/4497964", "supports_tool_choice": true, "supports_web_search": true, "model_id": "azure_ai/grok-4-1-fast-non-reasoning", "model_name": "Grok 4 1 Fast Non Reasoning", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.19999999999999998, "output_cost_per_million": 0.5, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 2e-7, "output_cost_per_token": 5e-7, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://techcommunity.microsoft.com/t5/Azure-AI-Foundry-Blog/Grok-4-0-Goes-GA-in-Microsoft-Foundry-and-Grok-4-1-Fast-Arrives/ba-p/4497964", "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "azure_ai/grok-4-1-fast-reasoning", "model_name": "Grok 4 1 Fast Reasoning", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.19999999999999998, "output_cost_per_million": 0.5, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 2e-7, "output_cost_per_token": 5e-7, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "supports_tool_choice": true, "supports_web_search": true, "model_id": "azure_ai/grok-4-fast-non-reasoning", "model_name": "Grok 4 Fast Non Reasoning", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.19999999999999998, "output_cost_per_million": 0.5, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 2e-7, "output_cost_per_token": 5e-7, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/grok/", "supports_tool_choice": true, "supports_web_search": true, "model_id": "azure_ai/grok-4-fast-reasoning", "model_name": "Grok 4 Fast Reasoning", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.19999999999999998, "output_cost_per_million": 0.5, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 2e-7, "output_cost_per_token": 0.0000015, "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/grok/", "supports_tool_choice": true, "supports_web_search": true, "model_id": "azure_ai/grok-code-fast-1", "model_name": "Grok Code Fast 1", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.19999999999999998, "output_cost_per_million": 1.5, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_vision": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.0032, "output_cost_per_token": 0.00971, "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, "source": "https://azure.microsoft.com/en-us/products/ai-services/ai-foundry/models/jais-30b-chat", "model_id": "azure_ai/jais-30b-chat", "model_name": "Jais 30B Chat", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 3200, "output_cost_per_million": 9710, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 5e-7, "output_cost_per_token": 7e-7, "max_input_tokens": 70000, "max_output_tokens": 4096, "max_tokens": 4096, "supports_tool_choice": true, "model_id": "azure_ai/jamba-instruct", "model_name": "Jamba Instruct", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.5, "output_cost_per_million": 0.7, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.000003, "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/kimi-k2-5-now-in-microsoft-foundry/4492321", "supports_tool_choice": true, "supports_video_input": true, "model_id": "azure_ai/kimi-k2.5", "model_name": "Kimi K2.5", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.6, "output_cost_per_million": 3, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 9.5e-7, "output_cost_per_token": 0.000004, "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/introducing-kimi-k2-6-in-microsoft-foundry/4513125", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_reasoning": true, "supports_tool_choice": true, "model_id": "azure_ai/kimi-k2.6", "model_name": "Kimi K2.6", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.95, "output_cost_per_million": 4, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 3.7e-7, "output_cost_per_token": 3.7e-7, "max_input_tokens": 128000, "max_output_tokens": 2048, "max_tokens": 2048, "source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/metagenai.meta-llama-3-2-11b-vision-instruct-offer?tab=Overview", "supports_tool_choice": true, "model_id": "azure_ai/Llama-3.2-11B-Vision-Instruct", "model_name": "Llama 3.2 11B Vision Instruct", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.37, "output_cost_per_million": 0.37, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 0.00000204, "output_cost_per_token": 0.00000204, "max_input_tokens": 128000, "max_output_tokens": 2048, "max_tokens": 2048, "source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/metagenai.meta-llama-3-2-90b-vision-instruct-offer?tab=Overview", "supports_tool_choice": true, "model_id": "azure_ai/Llama-3.2-90B-Vision-Instruct", "model_name": "Llama 3.2 90B Vision Instruct", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2.04, "output_cost_per_million": 2.04, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 7.1e-7, "output_cost_per_token": 7.1e-7, "max_input_tokens": 128000, "max_output_tokens": 2048, "max_tokens": 2048, "source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/metagenai.llama-3-3-70b-instruct-offer?tab=Overview", "supports_tool_choice": true, "model_id": "azure_ai/Llama-3.3-70B-Instruct", "model_name": "Llama 3.3 70B Instruct", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.71, "output_cost_per_million": 0.71, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 0.00000141, "output_cost_per_token": 3.5e-7, "max_input_tokens": 1000000, "max_output_tokens": 16384, "max_tokens": 16384, "source": "https://azure.microsoft.com/en-us/blog/introducing-the-llama-4-herd-in-azure-ai-foundry-and-azure-databricks/", "supports_tool_choice": true, "model_id": "azure_ai/Llama-4-Maverick-17B-128E-Instruct-FP8", "model_name": "Llama 4 Maverick 17B 128E Instruct FP8", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.4100000000000001, "output_cost_per_million": 0.35, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 2e-7, "output_cost_per_token": 7.8e-7, "max_input_tokens": 10000000, "max_output_tokens": 16384, "max_tokens": 16384, "source": "https://azure.microsoft.com/en-us/blog/introducing-the-llama-4-herd-in-azure-ai-foundry-and-azure-databricks/", "supports_tool_choice": true, "model_id": "azure_ai/Llama-4-Scout-17B-16E-Instruct", "model_name": "Llama 4 Scout 17B 16E Instruct", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.19999999999999998, "output_cost_per_million": 0.78, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.00000135, "output_cost_per_token": 0.0000054, "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/microsoft/", "supports_reasoning": true, "supports_tool_choice": true, "model_id": "azure_ai/MAI-DS-R1", "model_name": "MAI DS R1", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.35, "output_cost_per_million": 5.4, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.000005, "input_cost_per_image_token": 0.000008, "output_cost_per_image": 0.05, "output_cost_per_image_token": 0.000047, "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/new-mai-models-in-microsoft-foundry-across-text-image-voice-and-speech/4524632", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "model_id": "azure_ai/MAI-Image-2.5", "model_name": "MAI Image 2.5", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 5, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "image", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.00000175, "input_cost_per_image_token": 0.00000175, "output_cost_per_image": 0.0338, "output_cost_per_image_token": 0.000033, "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/new-mai-models-in-microsoft-foundry-across-text-image-voice-and-speech/4524632", "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "model_id": "azure_ai/MAI-Image-2.5-Flash", "model_name": "MAI Image 2.5 Flash", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 1.75, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "image", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.000005, "output_cost_per_image": 0.02, "output_cost_per_image_token": 0.0000195, "source": "https://aka.ms/mai-image-2e-foundryblog", "supported_endpoints": [ "/v1/images/generations" ], "model_id": "azure_ai/MAI-Image-2e", "model_name": "MAI Image 2e", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 5, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "image", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.0000011, "output_cost_per_token": 3.7e-7, "max_input_tokens": 8192, "max_output_tokens": 2048, "max_tokens": 2048, "supports_tool_choice": true, "model_id": "azure_ai/Meta-Llama-3-70B-Instruct", "model_name": "Meta Llama 3 70B Instruct", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.1, "output_cost_per_million": 0.37, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.00000533, "output_cost_per_token": 0.000016, "max_input_tokens": 128000, "max_output_tokens": 2048, "max_tokens": 2048, "source": "https://azuremarketplace.microsoft.com/en-us/marketplace/apps/metagenai.meta-llama-3-1-405b-instruct-offer?tab=PlansAndPrice", "supports_tool_choice": true, "model_id": "azure_ai/Meta-Llama-3.1-405B-Instruct", "model_name": "Meta Llama 3.1 405B Instruct", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 5.33, "output_cost_per_million": 16, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.00000268, "output_cost_per_token": 0.00000354, "max_input_tokens": 128000, "max_output_tokens": 2048, "max_tokens": 2048, "source": "https://azuremarketplace.microsoft.com/en-us/marketplace/apps/metagenai.meta-llama-3-1-70b-instruct-offer?tab=PlansAndPrice", "supports_tool_choice": true, "model_id": "azure_ai/Meta-Llama-3.1-70B-Instruct", "model_name": "Meta Llama 3.1 70B Instruct", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2.68, "output_cost_per_million": 3.54, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 3e-7, "output_cost_per_token": 6.1e-7, "max_input_tokens": 128000, "max_output_tokens": 2048, "max_tokens": 2048, "source": "https://azuremarketplace.microsoft.com/en-us/marketplace/apps/metagenai.meta-llama-3-1-8b-instruct-offer?tab=PlansAndPrice", "supports_tool_choice": true, "model_id": "azure_ai/Meta-Llama-3.1-8B-Instruct", "model_name": "Meta Llama 3.1 8B Instruct", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.3, "output_cost_per_million": 0.61, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 4e-8, "output_cost_per_token": 4e-8, "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/000-000.ministral-3b-2410-offer?tab=Overview", "supports_tool_choice": true, "model_id": "azure_ai/ministral-3b", "model_name": "Ministral 3B", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.04, "output_cost_per_million": 0.04, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "ocr_cost_per_page": 0.003, "supported_endpoints": [ "/v1/ocr" ], "source": "https://devblogs.microsoft.com/foundry/whats-new-in-azure-ai-foundry-august-2025/#mistral-document-ai-(ocr)-%E2%80%94-serverless-in-foundry", "model_id": "azure_ai/mistral-document-ai-2505", "model_name": "Mistral Document AI (May 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "ocr", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "ocr_cost_per_page": 0.003, "supported_endpoints": [ "/v1/ocr" ], "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/", "model_id": "azure_ai/mistral-document-ai-2512", "model_name": "Mistral Document AI (Dec 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "ocr", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.000004, "output_cost_per_token": 0.000012, "max_input_tokens": 32000, "max_output_tokens": 8191, "max_tokens": 8191, "supports_tool_choice": true, "model_id": "azure_ai/mistral-large", "model_name": "Mistral Large", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 4, "output_cost_per_million": 12, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000006, "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/000-000.mistral-ai-large-2407-offer?tab=Overview", "supports_tool_choice": true, "model_id": "azure_ai/mistral-large-2407", "model_name": "Mistral Large (Jul 2024)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2, "output_cost_per_million": 6, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 5e-7, "output_cost_per_token": 0.0000015, "max_input_tokens": 256000, "max_output_tokens": 8191, "max_tokens": 8191, "source": "https://azure.microsoft.com/en-us/blog/introducing-mistral-large-3-in-microsoft-foundry-open-capable-and-ready-for-production-workloads/", "supports_tool_choice": true, "model_id": "azure_ai/mistral-large-3", "model_name": "Mistral Large 3", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.5, "output_cost_per_million": 1.5, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000006, "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/000-000.mistral-ai-large-2407-offer?tab=Overview", "supports_tool_choice": true, "model_id": "azure_ai/mistral-large-latest", "model_name": "Mistral Large", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2, "output_cost_per_million": 6, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 4e-7, "output_cost_per_token": 0.000002, "max_input_tokens": 131072, "max_output_tokens": 8191, "max_tokens": 8191, "supports_assistant_prefill": true, "supports_tool_choice": true, "model_id": "azure_ai/mistral-medium-2505", "model_name": "Mistral Medium (May 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.39999999999999997, "output_cost_per_million": 2, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 1.5e-7, "output_cost_per_token": 1.5e-7, "max_input_tokens": 131072, "max_output_tokens": 4096, "max_tokens": 4096, "source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/000-000.mistral-nemo-12b-2407?tab=PlansAndPrice", "model_id": "azure_ai/mistral-nemo", "model_name": "Mistral Nemo", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.15, "output_cost_per_million": 0.15, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000003, "max_input_tokens": 32000, "max_output_tokens": 8191, "max_tokens": 8191, "supports_tool_choice": true, "model_id": "azure_ai/mistral-small", "model_name": "Mistral Small", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1, "output_cost_per_million": 3, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 1e-7, "output_cost_per_token": 3e-7, "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "supports_tool_choice": true, "model_id": "azure_ai/mistral-small-2503", "model_name": "Mistral Small (Mar 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0.3, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1.4e-7, "output_cost_per_token": 0, "source": "https://azure.microsoft.com/en-us/pricing/details/ai-services/", "comment": "Flat cost of $0.14 per M input tokens for Azure AI Foundry Model Router infrastructure. Use pattern: azure_ai/model_router/ where deployment-name is your Azure deployment (e.g., azure-model-router)", "model_id": "azure_ai/model_router", "model_name": "Model_router", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 0.14, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_vision": false, "input_cost_per_token": 1.7e-7, "output_cost_per_token": 6.8e-7, "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", "supports_tool_choice": true, "model_id": "azure_ai/Phi-3-medium-128k-instruct", "model_name": "Phi 3 Medium 128k Instruct", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.16999999999999998, "output_cost_per_million": 0.6799999999999999, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_vision": false, "input_cost_per_token": 1.7e-7, "output_cost_per_token": 6.8e-7, "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", "supports_tool_choice": true, "model_id": "azure_ai/Phi-3-medium-4k-instruct", "model_name": "Phi 3 Medium 4k Instruct", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.16999999999999998, "output_cost_per_million": 0.6799999999999999, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_vision": false, "input_cost_per_token": 1.3e-7, "output_cost_per_token": 5.2e-7, "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", "supports_tool_choice": true, "model_id": "azure_ai/Phi-3-mini-128k-instruct", "model_name": "Phi 3 Mini 128k Instruct", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.13, "output_cost_per_million": 0.52, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_vision": false, "input_cost_per_token": 1.3e-7, "output_cost_per_token": 5.2e-7, "max_input_tokens": 4096, "max_output_tokens": 4096, "max_tokens": 4096, "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", "supports_tool_choice": true, "model_id": "azure_ai/Phi-3-mini-4k-instruct", "model_name": "Phi 3 Mini 4k Instruct", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.13, "output_cost_per_million": 0.52, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_vision": false, "input_cost_per_token": 1.5e-7, "output_cost_per_token": 6e-7, "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", "supports_tool_choice": true, "model_id": "azure_ai/Phi-3-small-128k-instruct", "model_name": "Phi 3 Small 128k Instruct", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.15, "output_cost_per_million": 0.6, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_vision": false, "input_cost_per_token": 1.5e-7, "output_cost_per_token": 6e-7, "max_input_tokens": 8192, "max_output_tokens": 4096, "max_tokens": 4096, "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", "supports_tool_choice": true, "model_id": "azure_ai/Phi-3-small-8k-instruct", "model_name": "Phi 3 Small 8k Instruct", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.15, "output_cost_per_million": 0.6, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_vision": false, "input_cost_per_token": 1.3e-7, "output_cost_per_token": 5.2e-7, "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", "supports_tool_choice": true, "model_id": "azure_ai/Phi-3.5-mini-instruct", "model_name": "Phi 3.5 Mini Instruct", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.13, "output_cost_per_million": 0.52, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_vision": false, "input_cost_per_token": 1.6e-7, "output_cost_per_token": 6.4e-7, "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", "supports_tool_choice": true, "model_id": "azure_ai/Phi-3.5-MoE-instruct", "model_name": "Phi 3.5 MoE Instruct", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.16, "output_cost_per_million": 0.64, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_vision": true, "input_cost_per_token": 1.3e-7, "output_cost_per_token": 5.2e-7, "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", "supports_tool_choice": true, "model_id": "azure_ai/Phi-3.5-vision-instruct", "model_name": "Phi 3.5 Vision Instruct", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.13, "output_cost_per_million": 0.52, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": false, "input_cost_per_token": 1.25e-7, "output_cost_per_token": 5e-7, "max_input_tokens": 16384, "max_output_tokens": 16384, "max_tokens": 16384, "source": "https://techcommunity.microsoft.com/blog/machinelearningblog/affordable-innovation-unveiling-the-pricing-of-phi-3-slms-on-models-as-a-service/4156495", "supports_tool_choice": true, "model_id": "azure_ai/Phi-4", "model_name": "Phi 4", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.125, "output_cost_per_million": 0.5, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 7.5e-8, "output_cost_per_token": 3e-7, "max_input_tokens": 131072, "max_output_tokens": 4096, "max_tokens": 4096, "source": "https://techcommunity.microsoft.com/blog/Azure-AI-Services-blog/announcing-new-phi-pricing-empowering-your-business-with-small-language-models/4395112", "model_id": "azure_ai/Phi-4-mini-instruct", "model_name": "Phi 4 Mini Instruct", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.075, "output_cost_per_million": 0.3, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 8e-8, "output_cost_per_token": 3.2e-7, "max_input_tokens": 131072, "max_output_tokens": 4096, "max_tokens": 4096, "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/microsoft/", "model_id": "azure_ai/Phi-4-mini-reasoning", "model_name": "Phi 4 Mini Reasoning", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.08, "output_cost_per_million": 0.32, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 8e-8, "output_cost_per_token": 3.2e-7, "max_input_tokens": 131072, "max_output_tokens": 4096, "input_cost_per_audio_token": 0.000004, "max_tokens": 4096, "source": "https://techcommunity.microsoft.com/blog/Azure-AI-Services-blog/announcing-new-phi-pricing-empowering-your-business-with-small-language-models/4395112", "supports_audio_input": true, "model_id": "azure_ai/Phi-4-multimodal-instruct", "model_name": "Phi 4 Multimodal Instruct", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.08, "output_cost_per_million": 0.32, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 1.25e-7, "output_cost_per_token": 5e-7, "max_input_tokens": 32768, "max_output_tokens": 4096, "max_tokens": 4096, "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/microsoft/", "supports_tool_choice": true, "supports_reasoning": true, "model_id": "azure_ai/Phi-4-reasoning", "model_name": "Phi 4 Reasoning", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.125, "output_cost_per_million": 0.5, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1e-7, "output_cost_per_token": 0, "max_input_tokens": 8191, "max_tokens": 8191, "model_id": "azure/ada", "model_name": "Ada", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_output_tokens": 0, "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000015, "output_cost_per_token": 0.000006, "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/codex-mini", "model_name": "Codex Mini", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.5, "output_cost_per_million": 6, "cache_read_cost_per_token": 3.75e-7, "cache_read_cost_per_million": 0.375, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "model_id": "azure/command-r-plus", "model_name": "Command R+", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 3, "output_cost_per_million": 15, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000012, "max_input_tokens": 8192, "max_output_tokens": 1024, "max_tokens": 1024, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_prompt_caching": false, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/computer-use-preview", "model_name": "Computer Use Preview", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 3, "output_cost_per_million": 12, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "code_interpreter_cost_per_session": 0.03, "model_id": "azure/container", "model_name": "Container", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000275, "output_cost_per_token": 0.000011, "max_input_tokens": 128000, "max_output_tokens": 16384, "deprecation_date": "2026-02-27", "max_tokens": 16384, "supports_prompt_caching": true, "supports_tool_choice": true, "model_id": "azure/eu/gpt-4o-2024-08-06", "model_name": "GPT-4o (Aug 2024)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2.75, "output_cost_per_million": 11, "cache_read_cost_per_token": 0.000001375, "cache_read_cost_per_million": 1.375, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000275, "output_cost_per_token": 0.000011, "max_input_tokens": 128000, "max_output_tokens": 16384, "deprecation_date": "2026-03-01", "max_tokens": 16384, "supports_tool_choice": true, "model_id": "azure/eu/gpt-4o-2024-11-20", "model_name": "GPT-4o (Nov 2024)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2.75, "output_cost_per_million": 11, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0.00000138, "cache_write_cost_per_million": 1.38, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 1.65e-7, "output_cost_per_token": 6.6e-7, "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "supports_prompt_caching": true, "supports_tool_choice": true, "model_id": "azure/eu/gpt-4o-mini-2024-07-18", "model_name": "GPT-4o mini (Jul 2024)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.165, "output_cost_per_million": 0.66, "cache_read_cost_per_token": 8.3e-8, "cache_read_cost_per_million": 0.083, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 6.6e-7, "output_cost_per_token": 0.00000264, "max_input_tokens": 128000, "max_output_tokens": 4096, "cache_creation_input_audio_token_cost": 3.3e-7, "input_cost_per_audio_token": 0.000011, "max_tokens": 4096, "output_cost_per_audio_token": 0.000022, "supports_audio_input": true, "supports_audio_output": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/eu/gpt-4o-mini-realtime-preview-2024-12-17", "model_name": "GPT-4o Mini Realtime Preview (Dec 2024)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.66, "output_cost_per_million": 2.64, "cache_read_cost_per_token": 3.3e-7, "cache_read_cost_per_million": 0.33, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 0.0000055, "output_cost_per_token": 0.000022, "max_input_tokens": 128000, "max_output_tokens": 4096, "cache_creation_input_audio_token_cost": 0.000022, "input_cost_per_audio_token": 0.00011, "max_tokens": 4096, "output_cost_per_audio_token": 0.00022, "supports_audio_input": true, "supports_audio_output": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/eu/gpt-4o-realtime-preview-2024-10-01", "model_name": "GPT-4o Realtime Preview (Oct 2024)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 5.5, "output_cost_per_million": 22, "cache_read_cost_per_token": 0.00000275, "cache_read_cost_per_million": 2.75, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 0.0000055, "output_cost_per_token": 0.000022, "max_input_tokens": 128000, "max_output_tokens": 4096, "cache_read_input_audio_token_cost": 0.0000025, "input_cost_per_audio_token": 0.000044, "max_tokens": 4096, "output_cost_per_audio_token": 0.00008, "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/eu/gpt-4o-realtime-preview-2024-12-17", "model_name": "GPT-4o Realtime Preview (Dec 2024)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 5.5, "output_cost_per_million": 22, "cache_read_cost_per_token": 0.00000275, "cache_read_cost_per_million": 2.75, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000001375, "output_cost_per_token": 0.000011, "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/eu/gpt-5-2025-08-07", "model_name": "GPT-5 (Aug 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.375, "output_cost_per_million": 11, "cache_read_cost_per_token": 1.375e-7, "cache_read_cost_per_million": 0.1375, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2.75e-7, "output_cost_per_token": 0.0000022, "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/eu/gpt-5-mini-2025-08-07", "model_name": "GPT-5 Mini (Aug 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.275, "output_cost_per_million": 2.2, "cache_read_cost_per_token": 2.75e-8, "cache_read_cost_per_million": 0.0275, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 5.5e-8, "output_cost_per_token": 4.4e-7, "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/eu/gpt-5-nano-2025-08-07", "model_name": "GPT-5 Nano (Aug 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.055, "output_cost_per_million": 0.44, "cache_read_cost_per_token": 5.5e-9, "cache_read_cost_per_million": 0.0055, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000138, "output_cost_per_token": 0.000011, "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_none_reasoning_effort": true, "model_id": "azure/eu/gpt-5.1", "model_name": "GPT-5.1", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.38, "output_cost_per_million": 11, "cache_read_cost_per_token": 1.4e-7, "cache_read_cost_per_million": 0.14, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000138, "output_cost_per_token": 0.000011, "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_none_reasoning_effort": true, "model_id": "azure/eu/gpt-5.1-chat", "model_name": "GPT-5.1 Chat", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.38, "output_cost_per_million": 11, "cache_read_cost_per_token": 1.4e-7, "cache_read_cost_per_million": 0.14, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000138, "output_cost_per_token": 0.000011, "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": false, "supports_tool_choice": true, "model_id": "azure/eu/gpt-5.1-codex", "model_name": "GPT-5.1 Codex", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.38, "output_cost_per_million": 11, "cache_read_cost_per_token": 1.4e-7, "cache_read_cost_per_million": 0.14, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2.75e-7, "output_cost_per_token": 0.0000022, "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": false, "supports_tool_choice": true, "model_id": "azure/eu/gpt-5.1-codex-mini", "model_name": "GPT-5.1 Codex Mini", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.275, "output_cost_per_million": 2.2, "cache_read_cost_per_token": 2.8e-8, "cache_read_cost_per_million": 0.028, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000275, "output_cost_per_token": 0.0000165, "max_input_tokens": 1050000, "max_output_tokens": 128000, "cache_read_input_token_cost_priority": 5.5e-7, "input_cost_per_token_priority": 0.0000055, "output_cost_per_token_priority": 0.000033, "max_tokens": 128000, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/eu/gpt-5.4", "model_name": "GPT-5.4", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2.75, "output_cost_per_million": 16.5, "cache_read_cost_per_token": 2.8e-7, "cache_read_cost_per_million": 0.28, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000275, "output_cost_per_token": 0.0000165, "max_input_tokens": 1050000, "max_output_tokens": 128000, "cache_read_input_token_cost_priority": 5.5e-7, "input_cost_per_token_priority": 0.0000055, "output_cost_per_token_priority": 0.000033, "max_tokens": 128000, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/eu/gpt-5.4-2026-03-05", "model_name": "GPT-5.4 (Mar 2026)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2.75, "output_cost_per_million": 16.5, "cache_read_cost_per_token": 2.8e-7, "cache_read_cost_per_million": 0.28, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000055, "output_cost_per_token": 0.000033, "max_input_tokens": 1050000, "max_output_tokens": 128000, "cache_read_input_token_cost_above_272k_tokens": 0.0000011, "cache_read_input_token_cost_priority": 0.00000138, "input_cost_per_token_above_272k_tokens": 0.000011, "input_cost_per_token_priority": 0.00001375, "output_cost_per_token_above_272k_tokens": 0.0000495, "output_cost_per_token_priority": 0.0000825, "max_tokens": 128000, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "model_id": "azure/eu/gpt-5.5", "model_name": "GPT-5.5", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 5.5, "output_cost_per_million": 33, "cache_read_cost_per_token": 5.5e-7, "cache_read_cost_per_million": 0.55, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000055, "output_cost_per_token": 0.000033, "max_input_tokens": 1050000, "max_output_tokens": 128000, "cache_read_input_token_cost_above_272k_tokens": 0.0000011, "cache_read_input_token_cost_priority": 0.00000138, "input_cost_per_token_above_272k_tokens": 0.000011, "input_cost_per_token_priority": 0.00001375, "output_cost_per_token_above_272k_tokens": 0.0000495, "output_cost_per_token_priority": 0.0000825, "max_tokens": 128000, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "azure/eu/gpt-5.5-2026-04-23", "model_name": "GPT-5.5 (Apr 2026)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 5.5, "output_cost_per_million": 33, "cache_read_cost_per_token": 5.5e-7, "cache_read_cost_per_million": 0.55, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "input_cost_per_token": 0.0000165, "output_cost_per_token": 0.000066, "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "supports_prompt_caching": true, "supports_tool_choice": true, "model_id": "azure/eu/o1-2024-12-17", "model_name": "o1 (Dec 2024)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 16.5, "output_cost_per_million": 66, "cache_read_cost_per_token": 0.00000825, "cache_read_cost_per_million": 8.25, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": false, "input_cost_per_token": 0.00000121, "output_cost_per_token": 0.00000484, "max_input_tokens": 128000, "max_output_tokens": 65536, "input_cost_per_token_batches": 6.05e-7, "max_tokens": 65536, "output_cost_per_token_batches": 0.00000242, "supports_prompt_caching": true, "model_id": "azure/eu/o1-mini-2024-09-12", "model_name": "o1 mini (Sep 2024)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.21, "output_cost_per_million": 4.84, "cache_read_cost_per_token": 6.05e-7, "cache_read_cost_per_million": 0.605, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": false, "input_cost_per_token": 0.0000165, "output_cost_per_token": 0.000066, "max_input_tokens": 128000, "max_output_tokens": 32768, "max_tokens": 32768, "supports_prompt_caching": true, "model_id": "azure/eu/o1-preview-2024-09-12", "model_name": "o1 Preview (Sep 2024)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 16.5, "output_cost_per_million": 66, "cache_read_cost_per_token": 0.00000825, "cache_read_cost_per_million": 8.25, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_json_mode": false }, { "supports_vision": false, "input_cost_per_token": 0.00000121, "output_cost_per_token": 0.00000484, "max_input_tokens": 200000, "max_output_tokens": 100000, "input_cost_per_token_batches": 6.05e-7, "max_tokens": 100000, "output_cost_per_token_batches": 0.00000242, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "azure/eu/o3-mini-2025-01-31", "model_name": "o3 mini (Jan 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.21, "output_cost_per_million": 4.84, "cache_read_cost_per_token": 6.05e-7, "cache_read_cost_per_million": 0.605, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.00001, "max_input_tokens": 128000, "max_output_tokens": 16384, "deprecation_date": "2026-02-27", "max_tokens": 16384, "supports_prompt_caching": true, "supports_tool_choice": true, "model_id": "azure/global-standard/gpt-4o-2024-08-06", "model_name": "GPT-4o (Aug 2024)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2.5, "output_cost_per_million": 10, "cache_read_cost_per_token": 0.00000125, "cache_read_cost_per_million": 1.25, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.00001, "max_input_tokens": 128000, "max_output_tokens": 16384, "deprecation_date": "2026-03-01", "max_tokens": 16384, "supports_tool_choice": true, "model_id": "azure/global-standard/gpt-4o-2024-11-20", "model_name": "GPT-4o (Nov 2024)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2.5, "output_cost_per_million": 10, "cache_read_cost_per_token": 0.00000125, "cache_read_cost_per_million": 1.25, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 1.5e-7, "output_cost_per_token": 6e-7, "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "supports_tool_choice": true, "model_id": "azure/global-standard/gpt-4o-mini", "model_name": "GPT-4o mini", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.15, "output_cost_per_million": 0.6, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.00001, "max_input_tokens": 128000, "max_output_tokens": 16384, "deprecation_date": "2026-02-27", "max_tokens": 16384, "supports_prompt_caching": true, "supports_tool_choice": true, "model_id": "azure/global/gpt-4o-2024-08-06", "model_name": "GPT-4o (Aug 2024)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2.5, "output_cost_per_million": 10, "cache_read_cost_per_token": 0.00000125, "cache_read_cost_per_million": 1.25, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.00001, "max_input_tokens": 128000, "max_output_tokens": 16384, "deprecation_date": "2026-03-01", "max_tokens": 16384, "supports_prompt_caching": true, "supports_tool_choice": true, "model_id": "azure/global/gpt-4o-2024-11-20", "model_name": "GPT-4o (Nov 2024)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2.5, "output_cost_per_million": 10, "cache_read_cost_per_token": 0.00000125, "cache_read_cost_per_million": 1.25, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_none_reasoning_effort": true, "model_id": "azure/global/gpt-5.1", "model_name": "GPT-5.1", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.25, "output_cost_per_million": 10, "cache_read_cost_per_token": 1.25e-7, "cache_read_cost_per_million": 0.125, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_none_reasoning_effort": true, "model_id": "azure/global/gpt-5.1-chat", "model_name": "GPT-5.1 Chat", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.25, "output_cost_per_million": 10, "cache_read_cost_per_token": 1.25e-7, "cache_read_cost_per_million": 0.125, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": false, "supports_tool_choice": true, "model_id": "azure/global/gpt-5.1-codex", "model_name": "GPT-5.1 Codex", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.25, "output_cost_per_million": 10, "cache_read_cost_per_token": 1.25e-7, "cache_read_cost_per_million": 0.125, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.000002, "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": false, "supports_tool_choice": true, "model_id": "azure/global/gpt-5.1-codex-mini", "model_name": "GPT-5.1 Codex Mini", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.25, "output_cost_per_million": 2, "cache_read_cost_per_token": 2.5e-8, "cache_read_cost_per_million": 0.024999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "input_cost_per_token": 5e-7, "output_cost_per_token": 0.0000015, "max_input_tokens": 4097, "max_output_tokens": 4096, "max_tokens": 4096, "supports_tool_choice": true, "model_id": "azure/gpt-3.5-turbo", "model_name": "GPT 3.5T", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.5, "output_cost_per_million": 1.5, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 5e-7, "output_cost_per_token": 0.0000015, "max_input_tokens": 16384, "max_output_tokens": 4096, "deprecation_date": "2025-03-31", "max_tokens": 4096, "supports_tool_choice": true, "model_id": "azure/gpt-3.5-turbo-0125", "model_name": "GPT-3.5 Turbo 0125", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.5, "output_cost_per_million": 1.5, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "input_cost_per_token": 0.0000015, "output_cost_per_token": 0.000002, "max_input_tokens": 4097, "max_tokens": 4097, "model_id": "azure/gpt-3.5-turbo-instruct-0914", "model_name": "GPT-3.5 Turbo Instruct 0914", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_output_tokens": 0, "input_cost_per_million": 1.5, "output_cost_per_million": 2, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "completion", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 5e-7, "output_cost_per_token": 0.0000015, "max_input_tokens": 4097, "max_output_tokens": 4096, "max_tokens": 4096, "supports_tool_choice": true, "model_id": "azure/gpt-35-turbo", "model_name": "GPT-35 Turbo", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.5, "output_cost_per_million": 1.5, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 5e-7, "output_cost_per_token": 0.0000015, "max_input_tokens": 16384, "max_output_tokens": 4096, "deprecation_date": "2025-05-31", "max_tokens": 4096, "supports_tool_choice": true, "model_id": "azure/gpt-35-turbo-0125", "model_name": "GPT-35 Turbo 0125", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.5, "output_cost_per_million": 1.5, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000002, "max_input_tokens": 16384, "max_output_tokens": 4096, "deprecation_date": "2025-03-31", "max_tokens": 4096, "supports_tool_choice": true, "model_id": "azure/gpt-35-turbo-1106", "model_name": "GPT-35 Turbo (Jun 2011)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1, "output_cost_per_million": 2, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000004, "max_input_tokens": 16385, "max_output_tokens": 4096, "max_tokens": 4096, "supports_tool_choice": true, "model_id": "azure/gpt-35-turbo-16k", "model_name": "GPT-35 Turbo 16k", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 3, "output_cost_per_million": 4, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000004, "max_input_tokens": 16385, "max_output_tokens": 4096, "max_tokens": 4096, "supports_tool_choice": true, "model_id": "azure/gpt-35-turbo-16k-0613", "model_name": "GPT-35 Turbo 16k 0613", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 3, "output_cost_per_million": 4, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.0000015, "output_cost_per_token": 0.000002, "max_input_tokens": 4097, "max_tokens": 4097, "model_id": "azure/gpt-35-turbo-instruct", "model_name": "GPT-35 Turbo Instruct", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_output_tokens": 0, "input_cost_per_million": 1.5, "output_cost_per_million": 2, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "completion", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.0000015, "output_cost_per_token": 0.000002, "max_input_tokens": 4097, "max_tokens": 4097, "model_id": "azure/gpt-35-turbo-instruct-0914", "model_name": "GPT-35 Turbo Instruct 0914", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_output_tokens": 0, "input_cost_per_million": 1.5, "output_cost_per_million": 2, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "completion", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.00003, "output_cost_per_token": 0.00006, "max_input_tokens": 8192, "max_output_tokens": 4096, "max_tokens": 4096, "supports_tool_choice": true, "model_id": "azure/gpt-4", "model_name": "GPT-4", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 30, "output_cost_per_million": 60, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 0.00001, "output_cost_per_token": 0.00003, "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "supports_tool_choice": true, "model_id": "azure/gpt-4-0125-preview", "model_name": "GPT-4 0125 Preview", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 10, "output_cost_per_million": 30, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "input_cost_per_token": 0.00003, "output_cost_per_token": 0.00006, "max_input_tokens": 8192, "max_output_tokens": 4096, "max_tokens": 4096, "supports_tool_choice": true, "model_id": "azure/gpt-4-0613", "model_name": "GPT-4 0613", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 30, "output_cost_per_million": 60, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 0.00001, "output_cost_per_token": 0.00003, "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "supports_tool_choice": true, "model_id": "azure/gpt-4-1106-preview", "model_name": "GPT-4 1106 Preview", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 10, "output_cost_per_million": 30, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "input_cost_per_token": 0.00006, "output_cost_per_token": 0.00012, "max_input_tokens": 32768, "max_output_tokens": 4096, "max_tokens": 4096, "supports_tool_choice": true, "model_id": "azure/gpt-4-32k", "model_name": "GPT-4 32k", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 60, "output_cost_per_million": 120, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.00006, "output_cost_per_token": 0.00012, "max_input_tokens": 32768, "max_output_tokens": 4096, "max_tokens": 4096, "supports_tool_choice": true, "model_id": "azure/gpt-4-32k-0613", "model_name": "GPT-4 32k 0613", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 60, "output_cost_per_million": 120, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 0.00001, "output_cost_per_token": 0.00003, "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "supports_tool_choice": true, "model_id": "azure/gpt-4-turbo", "model_name": "GPT-4 Turbo", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 10, "output_cost_per_million": 30, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "input_cost_per_token": 0.00001, "output_cost_per_token": 0.00003, "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "supports_tool_choice": true, "model_id": "azure/gpt-4-turbo-2024-04-09", "model_name": "GPT-4 Turbo (Apr 2024)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 10, "output_cost_per_million": 30, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_json_mode": false }, { "supports_vision": true, "input_cost_per_token": 0.00001, "output_cost_per_token": 0.00003, "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "supports_tool_choice": true, "model_id": "azure/gpt-4-turbo-vision-preview", "model_name": "GPT-4 Turbo Vision Preview", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 10, "output_cost_per_million": 30, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000008, "max_input_tokens": 1047576, "max_output_tokens": 32768, "input_cost_per_token_batches": 0.000001, "max_tokens": 32768, "output_cost_per_token_batches": 0.000004, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": false, "model_id": "azure/gpt-4.1", "model_name": "GPT-4.1", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2, "output_cost_per_million": 8, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000008, "max_input_tokens": 1047576, "max_output_tokens": 32768, "deprecation_date": "2026-11-04", "input_cost_per_token_batches": 0.000001, "max_tokens": 32768, "output_cost_per_token_batches": 0.000004, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": false, "model_id": "azure/gpt-4.1-2025-04-14", "model_name": "GPT-4.1 (Apr 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2, "output_cost_per_million": 8, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 4e-7, "output_cost_per_token": 0.0000016, "max_input_tokens": 1047576, "max_output_tokens": 32768, "input_cost_per_token_batches": 2e-7, "max_tokens": 32768, "output_cost_per_token_batches": 8e-7, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": false, "model_id": "azure/gpt-4.1-mini", "model_name": "GPT-4.1 mini", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.39999999999999997, "output_cost_per_million": 1.5999999999999999, "cache_read_cost_per_token": 1e-7, "cache_read_cost_per_million": 0.09999999999999999, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 4e-7, "output_cost_per_token": 0.0000016, "max_input_tokens": 1047576, "max_output_tokens": 32768, "deprecation_date": "2026-11-04", "input_cost_per_token_batches": 2e-7, "max_tokens": 32768, "output_cost_per_token_batches": 8e-7, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": false, "model_id": "azure/gpt-4.1-mini-2025-04-14", "model_name": "GPT-4.1 mini (Apr 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.39999999999999997, "output_cost_per_million": 1.5999999999999999, "cache_read_cost_per_token": 1e-7, "cache_read_cost_per_million": 0.09999999999999999, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 1e-7, "output_cost_per_token": 4e-7, "max_input_tokens": 1047576, "max_output_tokens": 32768, "input_cost_per_token_batches": 5e-8, "max_tokens": 32768, "output_cost_per_token_batches": 2e-7, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/gpt-4.1-nano", "model_name": "GPT-4.1 nano", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0.39999999999999997, "cache_read_cost_per_token": 2.5e-8, "cache_read_cost_per_million": 0.024999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 1e-7, "output_cost_per_token": 4e-7, "max_input_tokens": 1047576, "max_output_tokens": 32768, "deprecation_date": "2026-11-04", "input_cost_per_token_batches": 5e-8, "max_tokens": 32768, "output_cost_per_token_batches": 2e-7, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/gpt-4.1-nano-2025-04-14", "model_name": "GPT-4.1 nano (Apr 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0.39999999999999997, "cache_read_cost_per_token": 2.5e-8, "cache_read_cost_per_million": 0.024999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000075, "output_cost_per_token": 0.00015, "max_input_tokens": 128000, "max_output_tokens": 16384, "input_cost_per_token_batches": 0.0000375, "max_tokens": 16384, "output_cost_per_token_batches": 0.000075, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/gpt-4.5-preview", "model_name": "GPT-4.5 Preview", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 75, "output_cost_per_million": 150, "cache_read_cost_per_token": 0.0000375, "cache_read_cost_per_million": 37.5, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.00001, "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "supports_prompt_caching": true, "supports_tool_choice": true, "model_id": "azure/gpt-4o", "model_name": "GPT-4o", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2.5, "output_cost_per_million": 10, "cache_read_cost_per_token": 0.00000125, "cache_read_cost_per_million": 1.25, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000015, "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "supports_prompt_caching": true, "supports_tool_choice": true, "model_id": "azure/gpt-4o-2024-05-13", "model_name": "GPT-4o (May 2024)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 5, "output_cost_per_million": 15, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.00001, "max_input_tokens": 128000, "max_output_tokens": 16384, "deprecation_date": "2026-02-27", "max_tokens": 16384, "supports_prompt_caching": true, "supports_tool_choice": true, "model_id": "azure/gpt-4o-2024-08-06", "model_name": "GPT-4o (Aug 2024)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2.5, "output_cost_per_million": 10, "cache_read_cost_per_token": 0.00000125, "cache_read_cost_per_million": 1.25, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000275, "output_cost_per_token": 0.000011, "max_input_tokens": 128000, "max_output_tokens": 16384, "deprecation_date": "2026-03-01", "max_tokens": 16384, "supports_prompt_caching": true, "supports_tool_choice": true, "model_id": "azure/gpt-4o-2024-11-20", "model_name": "GPT-4o (Nov 2024)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2.75, "output_cost_per_million": 11, "cache_read_cost_per_token": 0.00000125, "cache_read_cost_per_million": 1.25, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": false, "supports_response_schema": false, "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.00001, "max_input_tokens": 128000, "max_output_tokens": 16384, "input_cost_per_audio_token": 0.00004, "max_tokens": 16384, "output_cost_per_audio_token": 0.00008, "supported_endpoints": [ "/v1/chat/completions" ], "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_native_streaming": true, "supports_prompt_caching": false, "supports_reasoning": false, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/gpt-4o-audio-preview-2024-12-17", "model_name": "GPT-4o Audio Preview (Dec 2024)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2.5, "output_cost_per_million": 10, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 1.65e-7, "output_cost_per_token": 6.6e-7, "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "supports_prompt_caching": true, "supports_tool_choice": true, "model_id": "azure/gpt-4o-mini", "model_name": "GPT-4o mini", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.165, "output_cost_per_million": 0.66, "cache_read_cost_per_token": 7.5e-8, "cache_read_cost_per_million": 0.075, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 1.65e-7, "output_cost_per_token": 6.6e-7, "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "supports_prompt_caching": true, "supports_tool_choice": true, "model_id": "azure/gpt-4o-mini-2024-07-18", "model_name": "GPT-4o mini (Jul 2024)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.165, "output_cost_per_million": 0.66, "cache_read_cost_per_token": 7.5e-8, "cache_read_cost_per_million": 0.075, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": false, "supports_response_schema": false, "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.00001, "max_input_tokens": 128000, "max_output_tokens": 16384, "input_cost_per_audio_token": 0.00004, "max_tokens": 16384, "output_cost_per_audio_token": 0.00008, "supported_endpoints": [ "/v1/chat/completions" ], "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_native_streaming": true, "supports_prompt_caching": false, "supports_reasoning": false, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/gpt-4o-mini-audio-preview-2024-12-17", "model_name": "GPT-4o Mini Audio Preview (Dec 2024)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2.5, "output_cost_per_million": 10, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000024, "max_input_tokens": 128000, "max_output_tokens": 4096, "cache_creation_input_audio_token_cost": 3e-7, "input_cost_per_audio_token": 0.00001, "max_tokens": 4096, "output_cost_per_audio_token": 0.00002, "supports_audio_input": true, "supports_audio_output": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/gpt-4o-mini-realtime-preview-2024-12-17", "model_name": "GPT-4o Mini Realtime Preview (Dec 2024)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.6, "output_cost_per_million": 2.4, "cache_read_cost_per_token": 3e-7, "cache_read_cost_per_million": 0.3, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.000005, "max_input_tokens": 16000, "max_output_tokens": 2000, "input_cost_per_audio_token": 0.00000125, "supported_endpoints": [ "/v1/audio/transcriptions" ], "model_id": "azure/gpt-4o-mini-transcribe", "model_name": "GPT-4o Mini Transcribe", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.25, "output_cost_per_million": 5, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.00001, "output_cost_per_audio_token": 0.000012, "output_cost_per_second": 0.00025, "supported_endpoints": [ "/v1/audio/speech" ], "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "audio" ], "model_id": "azure/gpt-4o-mini-tts", "model_name": "GPT-4o Mini TTS", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 2.5, "output_cost_per_million": 10, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.00002, "max_input_tokens": 128000, "max_output_tokens": 4096, "cache_creation_input_audio_token_cost": 0.00002, "input_cost_per_audio_token": 0.0001, "max_tokens": 4096, "output_cost_per_audio_token": 0.0002, "supports_audio_input": true, "supports_audio_output": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/gpt-4o-realtime-preview-2024-10-01", "model_name": "GPT-4o Realtime Preview (Oct 2024)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 5, "output_cost_per_million": 20, "cache_read_cost_per_token": 0.0000025, "cache_read_cost_per_million": 2.5, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.00002, "max_input_tokens": 128000, "max_output_tokens": 4096, "input_cost_per_audio_token": 0.00004, "max_tokens": 4096, "output_cost_per_audio_token": 0.00008, "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/gpt-4o-realtime-preview-2024-12-17", "model_name": "GPT-4o Realtime Preview (Dec 2024)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 5, "output_cost_per_million": 20, "cache_read_cost_per_token": 0.0000025, "cache_read_cost_per_million": 2.5, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.00001, "max_input_tokens": 16000, "max_output_tokens": 2000, "input_cost_per_audio_token": 0.0000025, "supported_endpoints": [ "/v1/audio/transcriptions" ], "model_id": "azure/gpt-4o-transcribe", "model_name": "GPT-4o Transcribe", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2.5, "output_cost_per_million": 10, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.00001, "max_input_tokens": 16000, "max_output_tokens": 2000, "input_cost_per_audio_token": 0.0000025, "supported_endpoints": [ "/v1/audio/transcriptions" ], "model_id": "azure/gpt-4o-transcribe-diarize", "model_name": "GPT-4o Transcribe Diarize", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2.5, "output_cost_per_million": 10, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/gpt-5", "model_name": "GPT-5", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.25, "output_cost_per_million": 10, "cache_read_cost_per_token": 1.25e-7, "cache_read_cost_per_million": 0.125, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/gpt-5-2025-08-07", "model_name": "GPT-5 (Aug 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.25, "output_cost_per_million": 10, "cache_read_cost_per_token": 1.25e-7, "cache_read_cost_per_million": 0.125, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "source": "https://azure.microsoft.com/en-us/blog/gpt-5-in-azure-ai-foundry-the-future-of-ai-apps-and-agents-starts-here/", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/gpt-5-chat", "model_name": "GPT-5 Chat", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.25, "output_cost_per_million": 10, "cache_read_cost_per_token": 1.25e-7, "cache_read_cost_per_million": 0.125, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/gpt-5-chat-latest", "model_name": "GPT-5 Chat Latest", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.25, "output_cost_per_million": 10, "cache_read_cost_per_token": 1.25e-7, "cache_read_cost_per_million": 0.125, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/gpt-5-codex", "model_name": "GPT-5 Codex", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.25, "output_cost_per_million": 10, "cache_read_cost_per_token": 1.25e-7, "cache_read_cost_per_million": 0.125, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.000002, "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/gpt-5-mini", "model_name": "GPT-5 Mini", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.25, "output_cost_per_million": 2, "cache_read_cost_per_token": 2.5e-8, "cache_read_cost_per_million": 0.024999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.000002, "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/gpt-5-mini-2025-08-07", "model_name": "GPT-5 Mini (Aug 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.25, "output_cost_per_million": 2, "cache_read_cost_per_token": 2.5e-8, "cache_read_cost_per_million": 0.024999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 5e-8, "output_cost_per_token": 4e-7, "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/gpt-5-nano", "model_name": "GPT-5 Nano", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.049999999999999996, "output_cost_per_million": 0.39999999999999997, "cache_read_cost_per_token": 5e-9, "cache_read_cost_per_million": 0.005, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 5e-8, "output_cost_per_token": 4e-7, "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/gpt-5-nano-2025-08-07", "model_name": "GPT-5 Nano (Aug 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.049999999999999996, "output_cost_per_million": 0.39999999999999997, "cache_read_cost_per_token": 5e-9, "cache_read_cost_per_million": 0.005, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000015, "output_cost_per_token": 0.00012, "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/foundry-models/concepts/models-sold-directly-by-azure?pivots=azure-openai&tabs=global-standard-aoai%2Cstandard-chat-completions%2Cglobal-standard#gpt-5", "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/gpt-5-pro", "model_name": "GPT-5 Pro", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 15, "output_cost_per_million": 120, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_none_reasoning_effort": true, "model_id": "azure/gpt-5.1", "model_name": "GPT-5.1", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.25, "output_cost_per_million": 10, "cache_read_cost_per_token": 1.25e-7, "cache_read_cost_per_million": 0.125, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 272000, "max_output_tokens": 128000, "cache_read_input_token_cost_priority": 2.5e-7, "input_cost_per_token_priority": 0.0000025, "max_tokens": 128000, "output_cost_per_token_priority": 0.00002, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_none_reasoning_effort": true, "supports_minimal_reasoning_effort": true, "model_id": "azure/gpt-5.1-2025-11-13", "model_name": "GPT-5.1 (Nov 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.25, "output_cost_per_million": 10, "cache_read_cost_per_token": 1.25e-7, "cache_read_cost_per_million": 0.125, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_none_reasoning_effort": true, "model_id": "azure/gpt-5.1-chat", "model_name": "GPT-5.1 Chat", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.25, "output_cost_per_million": 10, "cache_read_cost_per_token": 1.25e-7, "cache_read_cost_per_million": 0.125, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": false, "supports_parallel_function_calling": false, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 128000, "max_output_tokens": 16384, "cache_read_input_token_cost_priority": 2.5e-7, "input_cost_per_token_priority": 0.0000025, "max_tokens": 16384, "output_cost_per_token_priority": 0.00002, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": false, "supports_none_reasoning_effort": true, "model_id": "azure/gpt-5.1-chat-2025-11-13", "model_name": "GPT-5.1 Chat (Nov 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.25, "output_cost_per_million": 10, "cache_read_cost_per_token": 1.25e-7, "cache_read_cost_per_million": 0.125, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": false, "supports_tool_choice": true, "model_id": "azure/gpt-5.1-codex", "model_name": "GPT-5.1 Codex", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.25, "output_cost_per_million": 10, "cache_read_cost_per_token": 1.25e-7, "cache_read_cost_per_million": 0.125, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 272000, "max_output_tokens": 128000, "cache_read_input_token_cost_priority": 2.5e-7, "input_cost_per_token_priority": 0.0000025, "max_tokens": 128000, "output_cost_per_token_priority": 0.00002, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": false, "supports_tool_choice": true, "model_id": "azure/gpt-5.1-codex-2025-11-13", "model_name": "GPT-5.1 Codex (Nov 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.25, "output_cost_per_million": 10, "cache_read_cost_per_token": 1.25e-7, "cache_read_cost_per_million": 0.125, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": false, "supports_tool_choice": true, "model_id": "azure/gpt-5.1-codex-max", "model_name": "GPT-5.1 Codex Max", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.25, "output_cost_per_million": 10, "cache_read_cost_per_token": 1.25e-7, "cache_read_cost_per_million": 0.125, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.000002, "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": false, "supports_tool_choice": true, "model_id": "azure/gpt-5.1-codex-mini", "model_name": "GPT-5.1 Codex Mini", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.25, "output_cost_per_million": 2, "cache_read_cost_per_token": 2.5e-8, "cache_read_cost_per_million": 0.024999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.000002, "max_input_tokens": 272000, "max_output_tokens": 128000, "cache_read_input_token_cost_priority": 4.5e-8, "input_cost_per_token_priority": 4.5e-7, "max_tokens": 128000, "output_cost_per_token_priority": 0.0000036, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": false, "supports_tool_choice": true, "model_id": "azure/gpt-5.1-codex-mini-2025-11-13", "model_name": "GPT-5.1 Codex Mini (Nov 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.25, "output_cost_per_million": 2, "cache_read_cost_per_token": 2.5e-8, "cache_read_cost_per_million": 0.024999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000175, "output_cost_per_token": 0.000014, "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/gpt-5.2", "model_name": "GPT-5.2", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.75, "output_cost_per_million": 14, "cache_read_cost_per_token": 1.75e-7, "cache_read_cost_per_million": 0.175, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000175, "output_cost_per_token": 0.000014, "max_input_tokens": 272000, "max_output_tokens": 128000, "cache_read_input_token_cost_priority": 3.5e-7, "input_cost_per_token_priority": 0.0000035, "max_tokens": 128000, "output_cost_per_token_priority": 0.000028, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/gpt-5.2-2025-12-11", "model_name": "GPT-5.2 (Dec 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.75, "output_cost_per_million": 14, "cache_read_cost_per_token": 1.75e-7, "cache_read_cost_per_million": 0.175, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000175, "output_cost_per_token": 0.000014, "max_input_tokens": 128000, "max_output_tokens": 16384, "cache_read_input_token_cost_priority": 3.5e-7, "input_cost_per_token_priority": 0.0000035, "max_tokens": 16384, "output_cost_per_token_priority": 0.000028, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/gpt-5.2-chat", "model_name": "GPT-5.2 Chat", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.75, "output_cost_per_million": 14, "cache_read_cost_per_token": 1.75e-7, "cache_read_cost_per_million": 0.175, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000175, "output_cost_per_token": 0.000014, "max_input_tokens": 128000, "max_output_tokens": 16384, "cache_read_input_token_cost_priority": 3.5e-7, "input_cost_per_token_priority": 0.0000035, "max_tokens": 16384, "output_cost_per_token_priority": 0.000028, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/gpt-5.2-chat-2025-12-11", "model_name": "GPT-5.2 Chat (Dec 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.75, "output_cost_per_million": 14, "cache_read_cost_per_token": 1.75e-7, "cache_read_cost_per_million": 0.175, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000175, "output_cost_per_token": 0.000014, "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/gpt-5.2-codex", "model_name": "GPT-5.2 Codex", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.75, "output_cost_per_million": 14, "cache_read_cost_per_token": 1.75e-7, "cache_read_cost_per_million": 0.175, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000021, "output_cost_per_token": 0.000168, "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "supported_endpoints": [ "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "azure/gpt-5.2-pro", "model_name": "GPT-5.2 Pro", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 21, "output_cost_per_million": 168, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000021, "output_cost_per_token": 0.000168, "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "supported_endpoints": [ "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "azure/gpt-5.2-pro-2025-12-11", "model_name": "GPT-5.2 Pro (Dec 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 21, "output_cost_per_million": 168, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000175, "output_cost_per_token": 0.000014, "max_input_tokens": 128000, "max_output_tokens": 16384, "cache_read_input_token_cost_priority": 3.5e-7, "input_cost_per_token_priority": 0.0000035, "max_tokens": 16384, "output_cost_per_token_priority": 0.000028, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/gpt-5.3-chat", "model_name": "GPT-5.3 Chat", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.75, "output_cost_per_million": 14, "cache_read_cost_per_token": 1.75e-7, "cache_read_cost_per_million": 0.175, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000175, "output_cost_per_token": 0.000014, "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/gpt-5.3-codex", "model_name": "GPT-5.3 Codex", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.75, "output_cost_per_million": 14, "cache_read_cost_per_token": 1.75e-7, "cache_read_cost_per_million": 0.175, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.000015, "max_input_tokens": 1050000, "max_output_tokens": 128000, "cache_read_input_token_cost_above_272k_tokens": 5e-7, "cache_read_input_token_cost_priority": 5e-7, "cache_read_input_token_cost_above_272k_tokens_priority": 0.000001, "input_cost_per_token_above_272k_tokens": 0.000005, "input_cost_per_token_priority": 0.000005, "input_cost_per_token_above_272k_tokens_priority": 0.00001, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.0000225, "output_cost_per_token_priority": 0.00003, "output_cost_per_token_above_272k_tokens_priority": 0.000045, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/gpt-5.4", "model_name": "GPT-5.4", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2.5, "output_cost_per_million": 15, "cache_read_cost_per_token": 2.5e-7, "cache_read_cost_per_million": 0.25, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.000015, "max_input_tokens": 1050000, "max_output_tokens": 128000, "cache_read_input_token_cost_above_272k_tokens": 5e-7, "cache_read_input_token_cost_priority": 5e-7, "cache_read_input_token_cost_above_272k_tokens_priority": 0.000001, "input_cost_per_token_above_272k_tokens": 0.000005, "input_cost_per_token_priority": 0.000005, "input_cost_per_token_above_272k_tokens_priority": 0.00001, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.0000225, "output_cost_per_token_priority": 0.00003, "output_cost_per_token_above_272k_tokens_priority": 0.000045, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/gpt-5.4-2026-03-05", "model_name": "GPT-5.4 (Mar 2026)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2.5, "output_cost_per_million": 15, "cache_read_cost_per_token": 2.5e-7, "cache_read_cost_per_million": 0.25, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 7.5e-7, "output_cost_per_token": 0.0000045, "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false, "model_id": "azure/gpt-5.4-mini", "model_name": "GPT-5.4 Mini", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.75, "output_cost_per_million": 4.5, "cache_read_cost_per_token": 7.5e-8, "cache_read_cost_per_million": 0.075, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 7.5e-7, "output_cost_per_token": 0.0000045, "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false, "model_id": "azure/gpt-5.4-mini-2026-03-17", "model_name": "GPT-5.4 Mini (Mar 2026)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.75, "output_cost_per_million": 4.5, "cache_read_cost_per_token": 7.5e-8, "cache_read_cost_per_million": 0.075, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2e-7, "output_cost_per_token": 0.00000125, "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false, "model_id": "azure/gpt-5.4-nano", "model_name": "GPT-5.4 Nano", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.19999999999999998, "output_cost_per_million": 1.25, "cache_read_cost_per_token": 2e-8, "cache_read_cost_per_million": 0.02, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2e-7, "output_cost_per_token": 0.00000125, "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false, "model_id": "azure/gpt-5.4-nano-2026-03-17", "model_name": "GPT-5.4 Nano (Mar 2026)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.19999999999999998, "output_cost_per_million": 1.25, "cache_read_cost_per_token": 2e-8, "cache_read_cost_per_million": 0.02, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": false, "input_cost_per_token": 0.00003, "output_cost_per_token": 0.00018, "max_input_tokens": 1050000, "max_output_tokens": 128000, "cache_read_input_token_cost_above_272k_tokens": 0.000006, "input_cost_per_token_above_272k_tokens": 0.00006, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.00027, "supported_endpoints": [ "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "azure/gpt-5.4-pro", "model_name": "GPT-5.4 Pro", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 30, "output_cost_per_million": 180, "cache_read_cost_per_token": 0.000003, "cache_read_cost_per_million": 3, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": false, "input_cost_per_token": 0.00003, "output_cost_per_token": 0.00018, "max_input_tokens": 1050000, "max_output_tokens": 128000, "cache_read_input_token_cost_above_272k_tokens": 0.000006, "input_cost_per_token_above_272k_tokens": 0.00006, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.00027, "supported_endpoints": [ "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "azure/gpt-5.4-pro-2026-03-05", "model_name": "GPT-5.4 Pro (Mar 2026)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 30, "output_cost_per_million": 180, "cache_read_cost_per_token": 0.000003, "cache_read_cost_per_million": 3, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.00003, "max_input_tokens": 1050000, "max_output_tokens": 128000, "cache_read_input_token_cost_above_272k_tokens": 0.000001, "cache_read_input_token_cost_priority": 0.000001, "cache_read_input_token_cost_above_272k_tokens_priority": 0.000002, "input_cost_per_token_above_272k_tokens": 0.00001, "input_cost_per_token_priority": 0.00001, "input_cost_per_token_above_272k_tokens_priority": 0.00002, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.000045, "output_cost_per_token_priority": 0.00006, "output_cost_per_token_above_272k_tokens_priority": 0.00009, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "model_id": "azure/gpt-5.5", "model_name": "GPT-5.5", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 5, "output_cost_per_million": 30, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.00003, "max_input_tokens": 1050000, "max_output_tokens": 128000, "cache_read_input_token_cost_above_272k_tokens": 0.000001, "cache_read_input_token_cost_priority": 0.000001, "cache_read_input_token_cost_above_272k_tokens_priority": 0.000002, "input_cost_per_token_above_272k_tokens": 0.00001, "input_cost_per_token_priority": 0.00001, "input_cost_per_token_above_272k_tokens_priority": 0.00002, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.000045, "output_cost_per_token_priority": 0.00006, "output_cost_per_token_above_272k_tokens_priority": 0.00009, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "azure/gpt-5.5-2026-04-23", "model_name": "GPT-5.5 (Apr 2026)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 5, "output_cost_per_million": 30, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": false, "input_cost_per_token": 0.00003, "output_cost_per_token": 0.00018, "max_input_tokens": 1050000, "max_output_tokens": 128000, "cache_read_input_token_cost_above_272k_tokens": 0.000006, "input_cost_per_token_above_272k_tokens": 0.00006, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.00027, "supported_endpoints": [ "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_low_reasoning_effort": false, "model_id": "azure/gpt-5.5-pro", "model_name": "GPT-5.5 Pro", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 30, "output_cost_per_million": 180, "cache_read_cost_per_token": 0.000003, "cache_read_cost_per_million": 3, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": false, "input_cost_per_token": 0.00003, "output_cost_per_token": 0.00018, "max_input_tokens": 1050000, "max_output_tokens": 128000, "cache_read_input_token_cost_above_272k_tokens": 0.000006, "input_cost_per_token_above_272k_tokens": 0.00006, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.00027, "supported_endpoints": [ "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "azure/gpt-5.5-pro-2026-04-23", "model_name": "GPT-5.5 Pro (Apr 2026)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 30, "output_cost_per_million": 180, "cache_read_cost_per_token": 0.000003, "cache_read_cost_per_million": 3, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": false, "supports_response_schema": false, "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.00001, "max_input_tokens": 128000, "max_output_tokens": 16384, "input_cost_per_audio_token": 0.00004, "max_tokens": 16384, "output_cost_per_audio_token": 0.00008, "supported_endpoints": [ "/v1/chat/completions" ], "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_native_streaming": true, "supports_prompt_caching": false, "supports_reasoning": false, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/gpt-audio-1.5-2026-02-23", "model_name": "GPT Audio 1.5 (Feb 2026)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2.5, "output_cost_per_million": 10, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": false, "supports_response_schema": false, "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.00001, "max_input_tokens": 128000, "max_output_tokens": 16384, "input_cost_per_audio_token": 0.00004, "max_tokens": 16384, "output_cost_per_audio_token": 0.00008, "supported_endpoints": [ "/v1/chat/completions" ], "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_native_streaming": true, "supports_prompt_caching": false, "supports_reasoning": false, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/gpt-audio-2025-08-28", "model_name": "GPT Audio (Aug 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2.5, "output_cost_per_million": 10, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": false, "supports_response_schema": false, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000024, "max_input_tokens": 128000, "max_output_tokens": 16384, "input_cost_per_audio_token": 0.00001, "max_tokens": 16384, "output_cost_per_audio_token": 0.00002, "supported_endpoints": [ "/v1/chat/completions" ], "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_native_streaming": true, "supports_prompt_caching": false, "supports_reasoning": false, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/gpt-audio-mini-2025-10-06", "model_name": "GPT Audio Mini (Oct 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.6, "output_cost_per_million": 2.4, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": true }, { "input_cost_per_token": 0.000005, "input_cost_per_image_token": 0.00001, "output_cost_per_image_token": 0.00004, "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "model_id": "azure/gpt-image-1", "model_name": "GPT Image 1", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 5, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0.00000125, "cache_read_cost_per_million": 1.25, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "image", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.000002, "input_cost_per_image_token": 0.0000025, "output_cost_per_image_token": 0.000008, "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "model_id": "azure/gpt-image-1-mini", "model_name": "GPT Image 1 Mini", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 2, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "image", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.000005, "input_cost_per_image_token": 0.000008, "output_cost_per_image_token": 0.000032, "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "model_id": "azure/gpt-image-1.5", "model_name": "GPT Image 1.5", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 5, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0.00000125, "cache_read_cost_per_million": 1.25, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "image", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.000005, "input_cost_per_image_token": 0.000008, "output_cost_per_image_token": 0.000032, "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "model_id": "azure/gpt-image-1.5-2025-12-16", "model_name": "GPT Image 1.5 (Dec 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 5, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0.00000125, "cache_read_cost_per_million": 1.25, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "image", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_vision": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.00001, "input_cost_per_image_token": 0.000008, "output_cost_per_image_token": 0.00003, "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "supports_pdf_input": true, "model_id": "azure/gpt-image-2", "model_name": "GPT Image 2", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 5, "output_cost_per_million": 10, "cache_read_cost_per_token": 0.00000125, "cache_read_cost_per_million": 1.25, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "image", "deprecation_date": null, "supports_function_calling": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_vision": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.00001, "input_cost_per_image_token": 0.000008, "output_cost_per_image_token": 0.00003, "supported_endpoints": [ "/v1/images/generations", "/v1/images/edits" ], "supports_pdf_input": true, "model_id": "azure/gpt-image-2-2026-04-21", "model_name": "GPT Image 2 (Apr 2026)", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 5, "output_cost_per_million": 10, "cache_read_cost_per_token": 0.00000125, "cache_read_cost_per_million": 1.25, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "image", "deprecation_date": null, "supports_function_calling": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 0.000004, "output_cost_per_token": 0.000016, "max_input_tokens": 32000, "max_output_tokens": 4096, "cache_creation_input_audio_token_cost": 0.000004, "input_cost_per_audio_token": 0.000032, "input_cost_per_image": 0.000005, "max_tokens": 4096, "output_cost_per_audio_token": 0.000064, "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "image", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/gpt-realtime-1.5-2026-02-23", "model_name": "GPT Realtime 1.5 (Feb 2026)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 4, "output_cost_per_million": 16, "cache_read_cost_per_token": 0.000004, "cache_read_cost_per_million": 4, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 0.000004, "output_cost_per_token": 0.000016, "max_input_tokens": 32000, "max_output_tokens": 4096, "cache_creation_input_audio_token_cost": 0.000004, "input_cost_per_audio_token": 0.000032, "input_cost_per_image": 0.000005, "max_tokens": 4096, "output_cost_per_audio_token": 0.000064, "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "image", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/gpt-realtime-2025-08-28", "model_name": "GPT Realtime (Aug 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 4, "output_cost_per_million": 16, "cache_read_cost_per_token": 0.000004, "cache_read_cost_per_million": 4, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000024, "max_input_tokens": 32000, "max_output_tokens": 4096, "cache_creation_input_audio_token_cost": 3e-7, "input_cost_per_audio_token": 0.00001, "input_cost_per_image": 8e-7, "max_tokens": 4096, "output_cost_per_audio_token": 0.00002, "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "image", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/gpt-realtime-mini-2025-10-06", "model_name": "GPT Realtime Mini (Oct 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.6, "output_cost_per_million": 2.4, "cache_read_cost_per_token": 6e-8, "cache_read_cost_per_million": 0.06, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "input_cost_per_second": 0.0002833333333333333, "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/gpt-realtime-whisper", "supported_endpoints": [ "/v1/realtime", "/v1/realtime/transcription_sessions" ], "supported_modalities": [ "audio" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "model_id": "azure/gpt-realtime-whisper", "model_name": "GPT Realtime Whisper", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "output_cost_per_token": 0, "input_cost_per_pixel": 7.629e-8, "model_id": "azure/hd/1024-x-1024/dall-e-3", "model_name": "Dall E 3", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "image", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "output_cost_per_token": 0, "input_cost_per_pixel": 6.539e-8, "model_id": "azure/hd/1024-x-1792/dall-e-3", "model_name": "Dall E 3", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "image", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "output_cost_per_token": 0, "input_cost_per_pixel": 6.539e-8, "model_id": "azure/hd/1792-x-1024/dall-e-3", "model_name": "Dall E 3", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "image", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_pixel": 1.59263611e-7, "output_cost_per_pixel": 0, "supported_endpoints": [ "/v1/images/generations" ], "model_id": "azure/high/1024-x-1024/gpt-image-1", "model_name": "GPT Image 1", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "image", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_pixel": 3.173828125e-8, "output_cost_per_pixel": 0, "supported_endpoints": [ "/v1/images/generations" ], "model_id": "azure/high/1024-x-1024/gpt-image-1-mini", "model_name": "GPT Image 1 Mini", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "image", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_pixel": 1.58945719e-7, "output_cost_per_pixel": 0, "supported_endpoints": [ "/v1/images/generations" ], "model_id": "azure/high/1024-x-1536/gpt-image-1", "model_name": "GPT Image 1", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "image", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_pixel": 3.173828125e-8, "output_cost_per_pixel": 0, "supported_endpoints": [ "/v1/images/generations" ], "model_id": "azure/high/1024-x-1536/gpt-image-1-mini", "model_name": "GPT Image 1 Mini", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "image", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_pixel": 1.58945719e-7, "output_cost_per_pixel": 0, "supported_endpoints": [ "/v1/images/generations" ], "model_id": "azure/high/1536-x-1024/gpt-image-1", "model_name": "GPT Image 1", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "image", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_pixel": 3.1575520833e-8, "output_cost_per_pixel": 0, "supported_endpoints": [ "/v1/images/generations" ], "model_id": "azure/high/1536-x-1024/gpt-image-1-mini", "model_name": "GPT Image 1 Mini", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "image", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_pixel": 1.0490417e-8, "output_cost_per_pixel": 0, "supported_endpoints": [ "/v1/images/generations" ], "model_id": "azure/low/1024-x-1024/gpt-image-1", "model_name": "GPT Image 1", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "image", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_pixel": 2.0751953125e-9, "output_cost_per_pixel": 0, "supported_endpoints": [ "/v1/images/generations" ], "model_id": "azure/low/1024-x-1024/gpt-image-1-mini", "model_name": "GPT Image 1 Mini", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "image", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_pixel": 1.0172526e-8, "output_cost_per_pixel": 0, "supported_endpoints": [ "/v1/images/generations" ], "model_id": "azure/low/1024-x-1536/gpt-image-1", "model_name": "GPT Image 1", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "image", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_pixel": 2.0751953125e-9, "output_cost_per_pixel": 0, "supported_endpoints": [ "/v1/images/generations" ], "model_id": "azure/low/1024-x-1536/gpt-image-1-mini", "model_name": "GPT Image 1 Mini", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "image", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_pixel": 1.0172526e-8, "output_cost_per_pixel": 0, "supported_endpoints": [ "/v1/images/generations" ], "model_id": "azure/low/1536-x-1024/gpt-image-1", "model_name": "GPT Image 1", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "image", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_pixel": 2.0345052083e-9, "output_cost_per_pixel": 0, "supported_endpoints": [ "/v1/images/generations" ], "model_id": "azure/low/1536-x-1024/gpt-image-1-mini", "model_name": "GPT Image 1 Mini", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "image", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_pixel": 4.0054321e-8, "output_cost_per_pixel": 0, "supported_endpoints": [ "/v1/images/generations" ], "model_id": "azure/medium/1024-x-1024/gpt-image-1", "model_name": "GPT Image 1", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "image", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_pixel": 8.056640625e-9, "output_cost_per_pixel": 0, "supported_endpoints": [ "/v1/images/generations" ], "model_id": "azure/medium/1024-x-1024/gpt-image-1-mini", "model_name": "GPT Image 1 Mini", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "image", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_pixel": 4.0054321e-8, "output_cost_per_pixel": 0, "supported_endpoints": [ "/v1/images/generations" ], "model_id": "azure/medium/1024-x-1536/gpt-image-1", "model_name": "GPT Image 1", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "image", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_pixel": 8.056640625e-9, "output_cost_per_pixel": 0, "supported_endpoints": [ "/v1/images/generations" ], "model_id": "azure/medium/1024-x-1536/gpt-image-1-mini", "model_name": "GPT Image 1 Mini", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "image", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_pixel": 4.0054321e-8, "output_cost_per_pixel": 0, "supported_endpoints": [ "/v1/images/generations" ], "model_id": "azure/medium/1536-x-1024/gpt-image-1", "model_name": "GPT Image 1", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "image", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_pixel": 7.9752604167e-9, "output_cost_per_pixel": 0, "supported_endpoints": [ "/v1/images/generations" ], "model_id": "azure/medium/1536-x-1024/gpt-image-1-mini", "model_name": "GPT Image 1 Mini", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "image", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.000008, "output_cost_per_token": 0.000024, "max_input_tokens": 32000, "max_tokens": 32000, "model_id": "azure/mistral-large-2402", "model_name": "Mistral Large (Feb 2024)", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_output_tokens": 0, "input_cost_per_million": 8, "output_cost_per_million": 24, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.000008, "output_cost_per_token": 0.000024, "max_input_tokens": 32000, "max_tokens": 32000, "model_id": "azure/mistral-large-latest", "model_name": "Mistral Large", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_output_tokens": 0, "input_cost_per_million": 8, "output_cost_per_million": 24, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "input_cost_per_token": 0.000015, "output_cost_per_token": 0.00006, "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "azure/o1", "model_name": "o1", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 15, "output_cost_per_million": 60, "cache_read_cost_per_token": 0.0000075, "cache_read_cost_per_million": 7.5, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "input_cost_per_token": 0.000015, "output_cost_per_token": 0.00006, "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "azure/o1-2024-12-17", "model_name": "o1 (Dec 2024)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 15, "output_cost_per_million": 60, "cache_read_cost_per_token": 0.0000075, "cache_read_cost_per_million": 7.5, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": false, "input_cost_per_token": 0.00000121, "output_cost_per_token": 0.00000484, "max_input_tokens": 128000, "max_output_tokens": 65536, "max_tokens": 65536, "supports_prompt_caching": true, "supports_reasoning": true, "model_id": "azure/o1-mini", "model_name": "o1 mini", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.21, "output_cost_per_million": 4.84, "cache_read_cost_per_token": 6.05e-7, "cache_read_cost_per_million": 0.605, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": false, "input_cost_per_token": 0.0000011, "output_cost_per_token": 0.0000044, "max_input_tokens": 128000, "max_output_tokens": 65536, "max_tokens": 65536, "supports_prompt_caching": true, "supports_reasoning": true, "model_id": "azure/o1-mini-2024-09-12", "model_name": "o1 mini (Sep 2024)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.1, "output_cost_per_million": 4.4, "cache_read_cost_per_token": 5.5e-7, "cache_read_cost_per_million": 0.55, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": false, "input_cost_per_token": 0.000015, "output_cost_per_token": 0.00006, "max_input_tokens": 128000, "max_output_tokens": 32768, "max_tokens": 32768, "supports_prompt_caching": true, "supports_reasoning": true, "model_id": "azure/o1-preview", "model_name": "o1 Preview", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 15, "output_cost_per_million": 60, "cache_read_cost_per_token": 0.0000075, "cache_read_cost_per_million": 7.5, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": false, "input_cost_per_token": 0.000015, "output_cost_per_token": 0.00006, "max_input_tokens": 128000, "max_output_tokens": 32768, "max_tokens": 32768, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "model_id": "azure/o1-preview-2024-09-12", "model_name": "o1 Preview (Sep 2024)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 15, "output_cost_per_million": 60, "cache_read_cost_per_token": 0.0000075, "cache_read_cost_per_million": 7.5, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000008, "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "azure/o3", "model_name": "o3", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2, "output_cost_per_million": 8, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000008, "max_input_tokens": 200000, "max_output_tokens": 100000, "deprecation_date": "2026-04-16", "max_tokens": 100000, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "azure/o3-2025-04-16", "model_name": "o3 (Apr 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2, "output_cost_per_million": 8, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00001, "output_cost_per_token": 0.00004, "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "azure/o3-deep-research", "model_name": "O3 Deep Research", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 10, "output_cost_per_million": 40, "cache_read_cost_per_token": 0.0000025, "cache_read_cost_per_million": 2.5, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 0.0000011, "output_cost_per_token": 0.0000044, "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "azure/o3-mini", "model_name": "o3 mini", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.1, "output_cost_per_million": 4.4, "cache_read_cost_per_token": 5.5e-7, "cache_read_cost_per_million": 0.55, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_function_calling": false, "supports_parallel_functions": false }, { "supports_vision": false, "input_cost_per_token": 0.0000011, "output_cost_per_token": 0.0000044, "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "azure/o3-mini-2025-01-31", "model_name": "o3 mini (Jan 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.1, "output_cost_per_million": 4.4, "cache_read_cost_per_token": 5.5e-7, "cache_read_cost_per_million": 0.55, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00002, "output_cost_per_token": 0.00008, "max_input_tokens": 200000, "max_output_tokens": 100000, "input_cost_per_token_batches": 0.00001, "max_tokens": 100000, "output_cost_per_token_batches": 0.00004, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_prompt_caching": false, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "azure/o3-pro", "model_name": "o3 Pro", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 20, "output_cost_per_million": 80, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00002, "output_cost_per_token": 0.00008, "max_input_tokens": 200000, "max_output_tokens": 100000, "input_cost_per_token_batches": 0.00001, "max_tokens": 100000, "output_cost_per_token_batches": 0.00004, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_prompt_caching": false, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "azure/o3-pro-2025-06-10", "model_name": "o3 Pro (Jun 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 20, "output_cost_per_million": 80, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000011, "output_cost_per_token": 0.0000044, "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "azure/o4-mini", "model_name": "o4 mini", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.1, "output_cost_per_million": 4.4, "cache_read_cost_per_token": 2.75e-7, "cache_read_cost_per_million": 0.275, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000011, "output_cost_per_token": 0.0000044, "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "azure/o4-mini-2025-04-16", "model_name": "o4 mini (Apr 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.1, "output_cost_per_million": 4.4, "cache_read_cost_per_token": 2.75e-7, "cache_read_cost_per_million": 0.275, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "output_cost_per_video_per_second": 0.1, "source": "https://azure.microsoft.com/en-us/products/ai-services/video-generation", "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ], "model_id": "azure/sora-2", "model_name": "Sora 2", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "video_generation", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "output_cost_per_video_per_second": 0.3, "source": "https://azure.microsoft.com/en-us/products/ai-services/video-generation", "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ], "model_id": "azure/sora-2-pro", "model_name": "Sora 2 Pro", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "video_generation", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "output_cost_per_video_per_second": 0.5, "source": "https://azure.microsoft.com/en-us/products/ai-services/video-generation", "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ], "model_id": "azure/sora-2-pro-high-res", "model_name": "Sora 2 Pro High Res", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "video_generation", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "audio_transcription_config": "azure_speech", "input_cost_per_second": 0.0002777778, "output_cost_per_second": 0, "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/speech-services/", "supported_endpoints": [ "/v1/audio/transcriptions" ], "model_id": "azure/speech/azure-stt", "model_name": "Azure STT", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_character": 0.000015, "source": "https://azure.microsoft.com/en-us/pricing/calculator/", "model_id": "azure/speech/azure-tts", "model_name": "Azure TTS", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_character": 0.00003, "source": "https://azure.microsoft.com/en-us/pricing/calculator/", "model_id": "azure/speech/azure-tts-hd", "model_name": "Azure TTS HD", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "output_cost_per_token": 0, "input_cost_per_pixel": 0, "model_id": "azure/standard/1024-x-1024/dall-e-2", "model_name": "Dall E 2", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "image", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "output_cost_per_token": 0, "input_cost_per_pixel": 3.81469e-8, "model_id": "azure/standard/1024-x-1024/dall-e-3", "model_name": "Dall E 3", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "image", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "output_cost_per_token": 0, "input_cost_per_pixel": 4.359e-8, "model_id": "azure/standard/1024-x-1792/dall-e-3", "model_name": "Dall E 3", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "image", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "output_cost_per_token": 0, "input_cost_per_pixel": 4.359e-8, "model_id": "azure/standard/1792-x-1024/dall-e-3", "model_name": "Dall E 3", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "image", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1.3e-7, "output_cost_per_token": 0, "max_input_tokens": 8191, "max_tokens": 8191, "model_id": "azure/text-embedding-3-large", "model_name": "Text Embedding 3 Large", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_output_tokens": 0, "input_cost_per_million": 0.13, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 2e-8, "output_cost_per_token": 0, "max_input_tokens": 8191, "deprecation_date": "2026-04-30", "max_tokens": 8191, "model_id": "azure/text-embedding-3-small", "model_name": "Text Embedding 3 Small", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_output_tokens": 0, "input_cost_per_million": 0.02, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1e-7, "output_cost_per_token": 0, "max_input_tokens": 8191, "max_tokens": 8191, "model_id": "azure/text-embedding-ada-002", "model_name": "Text Embedding Ada 002", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_output_tokens": 0, "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_character": 0.000015, "model_id": "azure/tts-1", "model_name": "TTS 1", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_character": 0.00003, "model_id": "azure/tts-1-hd", "model_name": "TTS 1 HD", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000022, "output_cost_per_token": 0.0000088, "max_input_tokens": 1047576, "max_output_tokens": 32768, "deprecation_date": "2026-11-04", "input_cost_per_token_batches": 0.0000011, "max_tokens": 32768, "output_cost_per_token_batches": 0.0000044, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": false, "model_id": "azure/us/gpt-4.1-2025-04-14", "model_name": "GPT-4.1 (Apr 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2.2, "output_cost_per_million": 8.8, "cache_read_cost_per_token": 5.5e-7, "cache_read_cost_per_million": 0.55, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 4.4e-7, "output_cost_per_token": 0.00000176, "max_input_tokens": 1047576, "max_output_tokens": 32768, "deprecation_date": "2026-11-04", "input_cost_per_token_batches": 2.2e-7, "max_tokens": 32768, "output_cost_per_token_batches": 8.8e-7, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": false, "model_id": "azure/us/gpt-4.1-mini-2025-04-14", "model_name": "GPT-4.1 mini (Apr 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.44, "output_cost_per_million": 1.76, "cache_read_cost_per_token": 1.1e-7, "cache_read_cost_per_million": 0.11, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 1.1e-7, "output_cost_per_token": 4.4e-7, "max_input_tokens": 1047576, "max_output_tokens": 32768, "deprecation_date": "2026-11-04", "input_cost_per_token_batches": 6e-8, "max_tokens": 32768, "output_cost_per_token_batches": 2.2e-7, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/us/gpt-4.1-nano-2025-04-14", "model_name": "GPT-4.1 nano (Apr 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.11, "output_cost_per_million": 0.44, "cache_read_cost_per_token": 2.5e-8, "cache_read_cost_per_million": 0.024999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000275, "output_cost_per_token": 0.000011, "max_input_tokens": 128000, "max_output_tokens": 16384, "deprecation_date": "2026-02-27", "max_tokens": 16384, "supports_prompt_caching": true, "supports_tool_choice": true, "model_id": "azure/us/gpt-4o-2024-08-06", "model_name": "GPT-4o (Aug 2024)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2.75, "output_cost_per_million": 11, "cache_read_cost_per_token": 0.000001375, "cache_read_cost_per_million": 1.375, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000275, "output_cost_per_token": 0.000011, "max_input_tokens": 128000, "max_output_tokens": 16384, "deprecation_date": "2026-03-01", "max_tokens": 16384, "supports_tool_choice": true, "model_id": "azure/us/gpt-4o-2024-11-20", "model_name": "GPT-4o (Nov 2024)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2.75, "output_cost_per_million": 11, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0.00000138, "cache_write_cost_per_million": 1.38, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 1.65e-7, "output_cost_per_token": 6.6e-7, "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "supports_prompt_caching": true, "supports_tool_choice": true, "model_id": "azure/us/gpt-4o-mini-2024-07-18", "model_name": "GPT-4o mini (Jul 2024)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.165, "output_cost_per_million": 0.66, "cache_read_cost_per_token": 8.3e-8, "cache_read_cost_per_million": 0.083, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 6.6e-7, "output_cost_per_token": 0.00000264, "max_input_tokens": 128000, "max_output_tokens": 4096, "cache_creation_input_audio_token_cost": 3.3e-7, "input_cost_per_audio_token": 0.000011, "max_tokens": 4096, "output_cost_per_audio_token": 0.000022, "supports_audio_input": true, "supports_audio_output": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/us/gpt-4o-mini-realtime-preview-2024-12-17", "model_name": "GPT-4o Mini Realtime Preview (Dec 2024)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.66, "output_cost_per_million": 2.64, "cache_read_cost_per_token": 3.3e-7, "cache_read_cost_per_million": 0.33, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 0.0000055, "output_cost_per_token": 0.000022, "max_input_tokens": 128000, "max_output_tokens": 4096, "cache_creation_input_audio_token_cost": 0.000022, "input_cost_per_audio_token": 0.00011, "max_tokens": 4096, "output_cost_per_audio_token": 0.00022, "supports_audio_input": true, "supports_audio_output": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/us/gpt-4o-realtime-preview-2024-10-01", "model_name": "GPT-4o Realtime Preview (Oct 2024)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 5.5, "output_cost_per_million": 22, "cache_read_cost_per_token": 0.00000275, "cache_read_cost_per_million": 2.75, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 0.0000055, "output_cost_per_token": 0.000022, "max_input_tokens": 128000, "max_output_tokens": 4096, "cache_read_input_audio_token_cost": 0.0000025, "input_cost_per_audio_token": 0.000044, "max_tokens": 4096, "output_cost_per_audio_token": 0.00008, "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/us/gpt-4o-realtime-preview-2024-12-17", "model_name": "GPT-4o Realtime Preview (Dec 2024)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 5.5, "output_cost_per_million": 22, "cache_read_cost_per_token": 0.00000275, "cache_read_cost_per_million": 2.75, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000001375, "output_cost_per_token": 0.000011, "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/us/gpt-5-2025-08-07", "model_name": "GPT-5 (Aug 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.375, "output_cost_per_million": 11, "cache_read_cost_per_token": 1.375e-7, "cache_read_cost_per_million": 0.1375, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2.75e-7, "output_cost_per_token": 0.0000022, "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/us/gpt-5-mini-2025-08-07", "model_name": "GPT-5 Mini (Aug 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.275, "output_cost_per_million": 2.2, "cache_read_cost_per_token": 2.75e-8, "cache_read_cost_per_million": 0.0275, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 5.5e-8, "output_cost_per_token": 4.4e-7, "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/us/gpt-5-nano-2025-08-07", "model_name": "GPT-5 Nano (Aug 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.055, "output_cost_per_million": 0.44, "cache_read_cost_per_token": 5.5e-9, "cache_read_cost_per_million": 0.0055, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000138, "output_cost_per_token": 0.000011, "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_none_reasoning_effort": true, "model_id": "azure/us/gpt-5.1", "model_name": "GPT-5.1", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.38, "output_cost_per_million": 11, "cache_read_cost_per_token": 1.4e-7, "cache_read_cost_per_million": 0.14, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000138, "output_cost_per_token": 0.000011, "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_none_reasoning_effort": true, "model_id": "azure/us/gpt-5.1-chat", "model_name": "GPT-5.1 Chat", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.38, "output_cost_per_million": 11, "cache_read_cost_per_token": 1.4e-7, "cache_read_cost_per_million": 0.14, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000138, "output_cost_per_token": 0.000011, "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": false, "supports_tool_choice": true, "model_id": "azure/us/gpt-5.1-codex", "model_name": "GPT-5.1 Codex", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.38, "output_cost_per_million": 11, "cache_read_cost_per_token": 1.4e-7, "cache_read_cost_per_million": 0.14, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2.75e-7, "output_cost_per_token": 0.0000022, "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": false, "supports_tool_choice": true, "model_id": "azure/us/gpt-5.1-codex-mini", "model_name": "GPT-5.1 Codex Mini", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.275, "output_cost_per_million": 2.2, "cache_read_cost_per_token": 2.8e-8, "cache_read_cost_per_million": 0.028, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000275, "output_cost_per_token": 0.0000165, "max_input_tokens": 1050000, "max_output_tokens": 128000, "cache_read_input_token_cost_priority": 5.5e-7, "input_cost_per_token_priority": 0.0000055, "output_cost_per_token_priority": 0.000033, "max_tokens": 128000, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/us/gpt-5.4", "model_name": "GPT-5.4", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2.75, "output_cost_per_million": 16.5, "cache_read_cost_per_token": 2.8e-7, "cache_read_cost_per_million": 0.28, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000275, "output_cost_per_token": 0.0000165, "max_input_tokens": 1050000, "max_output_tokens": 128000, "cache_read_input_token_cost_priority": 5.5e-7, "input_cost_per_token_priority": 0.0000055, "output_cost_per_token_priority": 0.000033, "max_tokens": 128000, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/us/gpt-5.4-2026-03-05", "model_name": "GPT-5.4 (Mar 2026)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2.75, "output_cost_per_million": 16.5, "cache_read_cost_per_token": 2.8e-7, "cache_read_cost_per_million": 0.28, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000055, "output_cost_per_token": 0.000033, "max_input_tokens": 1050000, "max_output_tokens": 128000, "cache_read_input_token_cost_above_272k_tokens": 0.0000011, "cache_read_input_token_cost_priority": 0.00000138, "input_cost_per_token_above_272k_tokens": 0.000011, "input_cost_per_token_priority": 0.00001375, "output_cost_per_token_above_272k_tokens": 0.0000495, "output_cost_per_token_priority": 0.0000825, "max_tokens": 128000, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "model_id": "azure/us/gpt-5.5", "model_name": "GPT-5.5", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 5.5, "output_cost_per_million": 33, "cache_read_cost_per_token": 5.5e-7, "cache_read_cost_per_million": 0.55, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000055, "output_cost_per_token": 0.000033, "max_input_tokens": 1050000, "max_output_tokens": 128000, "cache_read_input_token_cost_above_272k_tokens": 0.0000011, "cache_read_input_token_cost_priority": 0.00000138, "input_cost_per_token_above_272k_tokens": 0.000011, "input_cost_per_token_priority": 0.00001375, "output_cost_per_token_above_272k_tokens": 0.0000495, "output_cost_per_token_priority": 0.0000825, "max_tokens": 128000, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "azure/us/gpt-5.5-2026-04-23", "model_name": "GPT-5.5 (Apr 2026)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 5.5, "output_cost_per_million": 33, "cache_read_cost_per_token": 5.5e-7, "cache_read_cost_per_million": 0.55, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "input_cost_per_token": 0.0000165, "output_cost_per_token": 0.000066, "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "supports_prompt_caching": true, "supports_tool_choice": true, "model_id": "azure/us/o1-2024-12-17", "model_name": "o1 (Dec 2024)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 16.5, "output_cost_per_million": 66, "cache_read_cost_per_token": 0.00000825, "cache_read_cost_per_million": 8.25, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": false, "input_cost_per_token": 0.00000121, "output_cost_per_token": 0.00000484, "max_input_tokens": 128000, "max_output_tokens": 65536, "input_cost_per_token_batches": 6.05e-7, "max_tokens": 65536, "output_cost_per_token_batches": 0.00000242, "supports_prompt_caching": true, "model_id": "azure/us/o1-mini-2024-09-12", "model_name": "o1 mini (Sep 2024)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.21, "output_cost_per_million": 4.84, "cache_read_cost_per_token": 6.05e-7, "cache_read_cost_per_million": 0.605, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": false, "input_cost_per_token": 0.0000165, "output_cost_per_token": 0.000066, "max_input_tokens": 128000, "max_output_tokens": 32768, "max_tokens": 32768, "supports_prompt_caching": true, "model_id": "azure/us/o1-preview-2024-09-12", "model_name": "o1 Preview (Sep 2024)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 16.5, "output_cost_per_million": 66, "cache_read_cost_per_token": 0.00000825, "cache_read_cost_per_million": 8.25, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000022, "output_cost_per_token": 0.0000088, "max_input_tokens": 200000, "max_output_tokens": 100000, "deprecation_date": "2026-04-16", "max_tokens": 100000, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "azure/us/o3-2025-04-16", "model_name": "o3 (Apr 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2.2, "output_cost_per_million": 8.8, "cache_read_cost_per_token": 5.5e-7, "cache_read_cost_per_million": 0.55, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_vision": false, "input_cost_per_token": 0.00000121, "output_cost_per_token": 0.00000484, "max_input_tokens": 200000, "max_output_tokens": 100000, "input_cost_per_token_batches": 6.05e-7, "max_tokens": 100000, "output_cost_per_token_batches": 0.00000242, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "azure/us/o3-mini-2025-01-31", "model_name": "o3 mini (Jan 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.21, "output_cost_per_million": 4.84, "cache_read_cost_per_token": 6.05e-7, "cache_read_cost_per_million": 0.605, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": false, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000121, "output_cost_per_token": 0.00000484, "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "azure/us/o4-mini-2025-04-16", "model_name": "o4 mini (Apr 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.21, "output_cost_per_million": 4.84, "cache_read_cost_per_token": 3.1e-7, "cache_read_cost_per_million": 0.31, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "input_cost_per_second": 0.0001, "output_cost_per_second": 0.0001, "model_id": "azure/whisper-1", "model_name": "Whisper 1", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000012, "max_input_tokens": 8192, "max_output_tokens": 1024, "max_tokens": 1024, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_prompt_caching": false, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "computer-use-preview", "model_name": "Computer Use Preview", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 3, "output_cost_per_million": 12, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true } ]