[ { "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": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "source": "https://aihubmix.com/api/v1/models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_web_search": true, "supports_adaptive_thinking": true, "prompt_cache_min_tokens": 512, "supports_sampling_params": false, "model_id": "aihubmix/claude-opus-5", "model_name": "Claude Opus 5", "provider_id": "aihubmix", "provider_name": "Aihubmix", "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, "input_cost_per_token": 4.822e-7, "output_cost_per_token": 0.000002411, "max_input_tokens": 256000, "max_output_tokens": 128000, "max_tokens": 128000, "source": "https://aihubmix.com/api/v1/models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_web_search": true, "model_id": "aihubmix/doubao-seed-2-0-code-preview", "model_name": "Doubao Seed 2 0 Code Preview", "provider_id": "aihubmix", "provider_name": "Aihubmix", "input_cost_per_million": 0.4822, "output_cost_per_million": 2.411, "cache_read_cost_per_token": 9.644e-8, "cache_read_cost_per_million": 0.09644, "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, "supports_response_schema": true, "input_cost_per_token": 9.041e-8, "output_cost_per_token": 5.4246e-7, "max_input_tokens": 256000, "max_output_tokens": 128000, "max_tokens": 128000, "source": "https://aihubmix.com/api/v1/models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_web_search": true, "model_id": "aihubmix/doubao-seed-2-0-lite-260428", "model_name": "Doubao Seed 2 0 Lite 260428", "provider_id": "aihubmix", "provider_name": "Aihubmix", "input_cost_per_million": 0.09041, "output_cost_per_million": 0.5424599999999999, "cache_read_cost_per_token": 1.8082e-8, "cache_read_cost_per_million": 0.018082, "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_vision": true, "supports_response_schema": true, "input_cost_per_token": 3.0136e-8, "output_cost_per_token": 3.0136e-7, "max_input_tokens": 256000, "max_output_tokens": 128000, "max_tokens": 128000, "source": "https://aihubmix.com/api/v1/models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_web_search": true, "model_id": "aihubmix/doubao-seed-2-0-mini", "model_name": "Doubao Seed 2 0 Mini", "provider_id": "aihubmix", "provider_name": "Aihubmix", "input_cost_per_million": 0.030136, "output_cost_per_million": 0.30136, "cache_read_cost_per_token": 6.027e-9, "cache_read_cost_per_million": 0.006027, "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_vision": true, "supports_response_schema": true, "input_cost_per_token": 4.822e-7, "output_cost_per_token": 0.000002411, "max_input_tokens": 256000, "max_output_tokens": 128000, "max_tokens": 128000, "source": "https://aihubmix.com/api/v1/models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_web_search": true, "model_id": "aihubmix/doubao-seed-2-0-pro", "model_name": "Doubao Seed 2 0 Pro", "provider_id": "aihubmix", "provider_name": "Aihubmix", "input_cost_per_million": 0.4822, "output_cost_per_million": 2.411, "cache_read_cost_per_token": 9.644e-8, "cache_read_cost_per_million": 0.09644, "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_vision": true, "supports_response_schema": true, "input_cost_per_token": 4.6475e-7, "output_cost_per_token": 0.00000232375, "max_input_tokens": 256000, "max_output_tokens": 256000, "max_tokens": 256000, "source": "https://aihubmix.com/api/v1/models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_web_search": true, "model_id": "aihubmix/doubao-seed-2-1-turbo", "model_name": "Doubao Seed 2 1 Turbo", "provider_id": "aihubmix", "provider_name": "Aihubmix", "input_cost_per_million": 0.46475, "output_cost_per_million": 2.32375, "cache_read_cost_per_token": 9.295e-8, "cache_read_cost_per_million": 0.09294999999999999, "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_vision": true, "supports_response_schema": true, "input_cost_per_token": 5e-7, "output_cost_per_token": 0.000003, "max_input_tokens": 1048576, "max_output_tokens": 65536, "max_tokens": 65536, "source": "https://aihubmix.com/api/v1/models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_web_search": true, "model_id": "aihubmix/gemini-3-flash-preview", "model_name": "Gemini 3 Flash Preview", "provider_id": "aihubmix", "provider_name": "Aihubmix", "input_cost_per_million": 0.5, "output_cost_per_million": 3, "cache_read_cost_per_token": 5e-8, "cache_read_cost_per_million": 0.049999999999999996, "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_vision": true, "supports_response_schema": true, "input_cost_per_token": 5e-7, "output_cost_per_token": 0.000003, "max_input_tokens": 1048576, "max_output_tokens": 65536, "max_tokens": 65536, "source": "https://aihubmix.com/api/v1/models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_web_search": true, "model_id": "aihubmix/gemini-3-flash-preview-search", "model_name": "Gemini 3 Flash Preview Search", "provider_id": "aihubmix", "provider_name": "Aihubmix", "input_cost_per_million": 0.5, "output_cost_per_million": 3, "cache_read_cost_per_token": 5e-8, "cache_read_cost_per_million": 0.049999999999999996, "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_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000012, "max_input_tokens": 1048576, "max_output_tokens": 65536, "max_tokens": 65536, "source": "https://aihubmix.com/api/v1/models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_web_search": true, "model_id": "aihubmix/gemini-3.1-pro-preview", "model_name": "Gemini 3.1 Pro Preview", "provider_id": "aihubmix", "provider_name": "Aihubmix", "input_cost_per_million": 2, "output_cost_per_million": 12, "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": "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": 0.000012, "max_input_tokens": 1048576, "max_output_tokens": 65536, "max_tokens": 65536, "source": "https://aihubmix.com/api/v1/models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_web_search": true, "model_id": "aihubmix/gemini-3.1-pro-preview-customtools", "model_name": "Gemini 3.1 Pro Preview Customtools", "provider_id": "aihubmix", "provider_name": "Aihubmix", "input_cost_per_million": 2, "output_cost_per_million": 12, "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": "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": 3e-7, "output_cost_per_token": 0.000002499999, "max_input_tokens": 1048576, "max_output_tokens": 65536, "max_tokens": 65536, "source": "https://aihubmix.com/api/v1/models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_web_search": true, "model_id": "aihubmix/gemini-3.5-flash-lite", "model_name": "Gemini 3.5 Flash Lite", "provider_id": "aihubmix", "provider_name": "Aihubmix", "input_cost_per_million": 0.3, "output_cost_per_million": 2.499999, "cache_read_cost_per_token": 3e-8, "cache_read_cost_per_million": 0.03, "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_vision": true, "supports_response_schema": true, "input_cost_per_token": 7.5e-7, "output_cost_per_token": 0.00000375, "max_input_tokens": 1048576, "max_output_tokens": 65536, "max_tokens": 65536, "source": "https://aihubmix.com/api/v1/models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_web_search": true, "model_id": "aihubmix/gemini-3.7-flash", "model_name": "Gemini 3.7 Flash", "provider_id": "aihubmix", "provider_name": "Aihubmix", "input_cost_per_million": 0.75, "output_cost_per_million": 3.75, "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": false }, { "supports_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, "max_tokens": 128000, "source": "https://aihubmix.com/api/v1/models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_web_search": true, "model_id": "aihubmix/gpt-5.4-high", "model_name": "GPT-5.4 High", "provider_id": "aihubmix", "provider_name": "Aihubmix", "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": false }, { "supports_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, "max_tokens": 128000, "source": "https://aihubmix.com/api/v1/models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_web_search": true, "model_id": "aihubmix/gpt-5.4-low", "model_name": "GPT-5.4 Low", "provider_id": "aihubmix", "provider_name": "Aihubmix", "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": false }, { "supports_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, "max_tokens": 128000, "source": "https://aihubmix.com/api/v1/models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_web_search": true, "model_id": "aihubmix/gpt-5.4-mini", "model_name": "GPT-5.4 Mini", "provider_id": "aihubmix", "provider_name": "Aihubmix", "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": false }, { "supports_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, "max_tokens": 128000, "source": "https://aihubmix.com/api/v1/models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_web_search": true, "model_id": "aihubmix/gpt-5.4-nano", "model_name": "GPT-5.4 Nano", "provider_id": "aihubmix", "provider_name": "Aihubmix", "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": false }, { "supports_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, "max_tokens": 128000, "source": "https://aihubmix.com/api/v1/models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_web_search": true, "model_id": "aihubmix/gpt-5.5", "model_name": "GPT-5.5", "provider_id": "aihubmix", "provider_name": "Aihubmix", "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": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00003, "output_cost_per_token": 0.00018, "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "source": "https://aihubmix.com/api/v1/models", "supports_reasoning": true, "supports_web_search": true, "model_id": "aihubmix/gpt-5.5-pro", "model_name": "GPT-5.5 Pro", "provider_id": "aihubmix", "provider_name": "Aihubmix", "input_cost_per_million": 30, "output_cost_per_million": 180, "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": false }, { "supports_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": 400000, "max_output_tokens": 128000, "max_tokens": 128000, "source": "https://aihubmix.com/api/v1/models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_web_search": true, "model_id": "aihubmix/gpt-chat-latest", "model_name": "GPT Chat Latest", "provider_id": "aihubmix", "provider_name": "Aihubmix", "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": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 1.562e-7, "output_cost_per_token": 6.248e-7, "max_input_tokens": 256000, "max_output_tokens": 128000, "max_tokens": 128000, "source": "https://aihubmix.com/api/v1/models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_web_search": true, "model_id": "aihubmix/hy3", "model_name": "Hy3", "provider_id": "aihubmix", "provider_name": "Aihubmix", "input_cost_per_million": 0.1562, "output_cost_per_million": 0.6248, "cache_read_cost_per_token": 3.905e-8, "cache_read_cost_per_million": 0.03905, "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": 8.45e-7, "output_cost_per_token": 0.000002535, "max_input_tokens": 1048576, "max_output_tokens": 64000, "max_tokens": 64000, "source": "https://aihubmix.com/api/v1/models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_web_search": true, "model_id": "aihubmix/hy4-preview", "model_name": "Hy4 Preview", "provider_id": "aihubmix", "provider_name": "Aihubmix", "input_cost_per_million": 0.845, "output_cost_per_million": 2.5349999999999997, "cache_read_cost_per_token": 4.225e-8, "cache_read_cost_per_million": 0.042249999999999996, "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_vision": true, "input_cost_per_token": 4.4e-7, "output_cost_per_token": 0.0000022, "max_input_tokens": 256000, "source": "https://aihubmix.com/api/v1/models", "supports_prompt_caching": true, "supports_web_search": true, "model_id": "aihubmix/mimo-v2-omni", "model_name": "Mimo V2 Omni", "provider_id": "aihubmix", "provider_name": "Aihubmix", "max_output_tokens": 0, "input_cost_per_million": 0.44, "output_cost_per_million": 2.2, "cache_read_cost_per_token": 8.8e-8, "cache_read_cost_per_million": 0.088, "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 }, { "input_cost_per_token": 0.0000011, "output_cost_per_token": 0.0000033, "max_input_tokens": 1000000, "source": "https://aihubmix.com/api/v1/models", "supports_prompt_caching": true, "supports_web_search": true, "model_id": "aihubmix/mimo-v2-pro", "model_name": "Mimo V2 Pro", "provider_id": "aihubmix", "provider_name": "Aihubmix", "max_output_tokens": 0, "input_cost_per_million": 1.1, "output_cost_per_million": 3.3000000000000003, "cache_read_cost_per_token": 2.2e-7, "cache_read_cost_per_million": 0.22, "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, "supports_response_schema": true, "input_cost_per_token": 1.126e-7, "output_cost_per_token": 9.008e-7, "max_input_tokens": 262144, "max_output_tokens": 65536, "max_tokens": 65536, "source": "https://aihubmix.com/api/v1/models", "supports_reasoning": true, "supports_web_search": true, "model_id": "aihubmix/qwen3.5-122b-a10b", "model_name": "Qwen3.5 122B A10B", "provider_id": "aihubmix", "provider_name": "Aihubmix", "input_cost_per_million": 0.1126, "output_cost_per_million": 0.9008, "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": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 1.644e-7, "output_cost_per_token": 9.864e-7, "max_input_tokens": 262144, "max_output_tokens": 65536, "max_tokens": 65536, "source": "https://aihubmix.com/api/v1/models", "supports_reasoning": true, "supports_web_search": true, "model_id": "aihubmix/qwen3.5-397b-a17b", "model_name": "Qwen3.5 397B A17B", "provider_id": "aihubmix", "provider_name": "Aihubmix", "input_cost_per_million": 0.1644, "output_cost_per_million": 0.9863999999999999, "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": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 4.22e-7, "output_cost_per_token": 0.000002532, "max_input_tokens": 262144, "max_output_tokens": 65536, "max_tokens": 65536, "source": "https://aihubmix.com/api/v1/models", "supports_reasoning": true, "supports_web_search": true, "model_id": "aihubmix/qwen3.6-27b", "model_name": "Qwen3.6 27B", "provider_id": "aihubmix", "provider_name": "Aihubmix", "input_cost_per_million": 0.422, "output_cost_per_million": 2.532, "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": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2.54e-7, "output_cost_per_token": 0.000001524, "max_input_tokens": 262144, "max_output_tokens": 65536, "max_tokens": 65536, "source": "https://aihubmix.com/api/v1/models", "supports_reasoning": true, "supports_web_search": true, "model_id": "aihubmix/qwen3.6-35b-a3b", "model_name": "Qwen3.6 35B A3B", "provider_id": "aihubmix", "provider_name": "Aihubmix", "input_cost_per_million": 0.254, "output_cost_per_million": 1.524, "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": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 0.000001268, "output_cost_per_token": 0.000007608, "max_input_tokens": 262144, "max_output_tokens": 65536, "max_tokens": 65536, "source": "https://aihubmix.com/api/v1/models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_web_search": true, "model_id": "aihubmix/qwen3.6-max-preview", "model_name": "Qwen3.6 Max Preview", "provider_id": "aihubmix", "provider_name": "Aihubmix", "input_cost_per_million": 1.268, "output_cost_per_million": 7.608, "cache_read_cost_per_token": 1.268e-7, "cache_read_cost_per_million": 0.1268, "cache_write_cost_per_token": 0.000001585, "cache_write_cost_per_million": 1.585, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2.82e-7, "output_cost_per_token": 0.000001128, "max_input_tokens": 1000000, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://aihubmix.com/api/v1/models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_web_search": true, "model_id": "aihubmix/qwen3.7-plus", "model_name": "Qwen3.7 Plus", "provider_id": "aihubmix", "provider_name": "Aihubmix", "input_cost_per_million": 0.28200000000000003, "output_cost_per_million": 1.1280000000000001, "cache_read_cost_per_token": 5.64e-8, "cache_read_cost_per_million": 0.0564, "cache_write_cost_per_token": 3.525e-7, "cache_write_cost_per_million": 0.35250000000000004, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000006, "max_input_tokens": 1000000, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://aihubmix.com/api/v1/models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_web_search": true, "model_id": "aihubmix/qwen3.8-2.4t-a95b", "model_name": "Qwen3.8 2.4t A95B", "provider_id": "aihubmix", "provider_name": "Aihubmix", "input_cost_per_million": 2, "output_cost_per_million": 6, "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_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 1.126e-7, "output_cost_per_token": 3.80025e-7, "max_input_tokens": 1000000, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://aihubmix.com/api/v1/models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_web_search": true, "model_id": "aihubmix/qwen3.8-flash", "model_name": "Qwen3.8 Flash", "provider_id": "aihubmix", "provider_name": "Aihubmix", "input_cost_per_million": 0.1126, "output_cost_per_million": 0.380025, "cache_read_cost_per_token": 1.4075e-8, "cache_read_cost_per_million": 0.014075, "cache_write_cost_per_token": 1.75937e-7, "cache_write_cost_per_million": 0.17593699999999998, "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": 0.00000169, "output_cost_per_token": 0.00000507, "max_input_tokens": 1000000, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://aihubmix.com/api/v1/models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_web_search": true, "model_id": "aihubmix/qwen3.8-max", "model_name": "Qwen3.8 Max", "provider_id": "aihubmix", "provider_name": "Aihubmix", "input_cost_per_million": 1.69, "output_cost_per_million": 5.069999999999999, "cache_read_cost_per_token": 1.69e-7, "cache_read_cost_per_million": 0.16899999999999998, "cache_write_cost_per_token": 0.0000021125, "cache_write_cost_per_million": 2.1125000000000003, "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, "deprecation_date": "2026-11-30", "cache_creation_input_token_cost_above_1hr": 0.000006, "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 0.000012, "input_cost_per_token_above_200k_tokens": 0.000006, "output_cost_per_token_above_200k_tokens": 0.0000225, "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_creation_input_token_cost_above_200k_tokens_batches": 0.00000375, "cache_creation_input_token_cost_batches": 0.000001875, "cache_read_input_token_cost_above_200k_tokens": 6e-7, "cache_read_input_token_cost_above_200k_tokens_batches": 3e-7, "cache_read_input_token_cost_batches": 1.5e-7, "input_cost_per_token_above_200k_tokens_batches": 0.000003, "input_cost_per_token_batches": 0.0000015, "max_tokens": 64000, "output_cost_per_token_above_200k_tokens_batches": 0.00001125, "output_cost_per_token_batches": 0.0000075, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_native_structured_output": true, "supports_tool_choice": true, "supports_web_search": true, "prompt_cache_min_tokens": 1024, "source": "https://docs.anthropic.com/en/docs/about-claude/pricing", "model_id": "claude-sonnet-4-5-20250929", "model_name": "Claude Sonnet 4 5 (Sep 2025)", "provider_id": "anthropic", "provider_name": "Anthropic", "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", "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": 0.0000025, "output_cost_per_token": 0.000015, "max_input_tokens": 922000, "max_output_tokens": 128000, "deprecation_date": "2027-09-02", "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, "default_reasoning_effort": "none", "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", "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": 922000, "max_output_tokens": 128000, "deprecation_date": "2027-09-02", "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, "default_reasoning_effort": "none", "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", "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": 272000, "max_output_tokens": 128000, "deprecation_date": "2027-09-21", "cache_read_input_token_cost_priority": 1.5e-7, "input_cost_per_token_priority": 0.0000015, "max_tokens": 128000, "output_cost_per_token_priority": 0.000009, "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, "default_reasoning_effort": "none", "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", "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": 272000, "max_output_tokens": 128000, "deprecation_date": "2027-09-21", "cache_read_input_token_cost_priority": 1.5e-7, "input_cost_per_token_priority": 0.0000015, "max_tokens": 128000, "output_cost_per_token_priority": 0.000009, "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, "default_reasoning_effort": "none", "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", "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": 272000, "max_output_tokens": 128000, "deprecation_date": "2027-09-21", "cache_read_input_token_cost_priority": 4e-8, "input_cost_per_token_priority": 4e-7, "max_tokens": 128000, "output_cost_per_token_priority": 0.0000025, "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, "default_reasoning_effort": "none", "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", "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": 272000, "max_output_tokens": 128000, "deprecation_date": "2027-09-21", "cache_read_input_token_cost_priority": 4e-8, "input_cost_per_token_priority": 4e-7, "max_tokens": 128000, "output_cost_per_token_priority": 0.0000025, "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, "default_reasoning_effort": "none", "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", "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": 922000, "max_output_tokens": 128000, "deprecation_date": "2027-09-07", "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", "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": 922000, "max_output_tokens": 128000, "deprecation_date": "2027-09-07", "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", "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": 922000, "max_output_tokens": 128000, "deprecation_date": "2027-10-26", "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", "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": 922000, "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_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.00003, "max_input_tokens": 922000, "max_output_tokens": 128000, "deprecation_date": "2027-10-26", "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://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models", "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-5.5-2026-04-24", "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", "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": 0.00001, "output_cost_per_token": 0.00005, "max_input_tokens": 922000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_272k_tokens": 0.000025, "cache_read_input_token_cost_above_272k_tokens": 0.000002, "input_cost_per_token_above_272k_tokens": 0.00002, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.000075, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://ai.azure.com/catalog/models/gpt-6-astra", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_computer_use": true, "supports_max_reasoning_effort": false, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, "supports_none_reasoning_effort": true, "supports_pdf_input": true, "supports_prompt_cache_breakpoint": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true, "model_id": "azure_ai/gpt-6-astra", "model_name": "GPT-6 Astra", "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": 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": 5e-7, "max_input_tokens": 922000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_272k_tokens": 2.5e-7, "cache_read_input_token_cost_above_272k_tokens": 2e-8, "input_cost_per_token_above_272k_tokens": 2e-7, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 7.5e-7, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_computer_use": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, "supports_none_reasoning_effort": true, "supports_pdf_input": true, "supports_prompt_cache_breakpoint": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true, "model_id": "azure_ai/gpt-6-luna", "model_name": "GPT-6 Luna", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0.5, "cache_read_cost_per_token": 1e-8, "cache_read_cost_per_million": 0.01, "cache_write_cost_per_token": 1.25e-7, "cache_write_cost_per_million": 0.125, "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": 0.00001, "max_input_tokens": 922000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_272k_tokens": 0.000005, "cache_read_input_token_cost_above_272k_tokens": 4e-7, "input_cost_per_token_above_272k_tokens": 0.000004, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.000015, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_computer_use": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, "supports_none_reasoning_effort": true, "supports_pdf_input": true, "supports_prompt_cache_breakpoint": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true, "model_id": "azure_ai/gpt-6-sol", "model_name": "GPT-6 Sol", "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": 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": 0.00001, "max_input_tokens": 922000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_272k_tokens": 0.000005, "cache_read_input_token_cost_above_272k_tokens": 2e-7, "input_cost_per_token_above_272k_tokens": 0.000004, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.000015, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_computer_use": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, "supports_none_reasoning_effort": true, "supports_pdf_input": true, "supports_prompt_cache_breakpoint": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true, "model_id": "azure_ai/gpt-6.1-sol", "model_name": "GPT-6.1 Sol", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2, "output_cost_per_million": 10, "cache_read_cost_per_token": 1e-7, "cache_read_cost_per_million": 0.09999999999999999, "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": 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": 272000, "max_output_tokens": 128000, "deprecation_date": "2026-12-02", "max_tokens": 128000, "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", "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, "supports_web_search": true, "model_id": "azure_ai/gpt-chat-latest", "model_name": "GPT Chat Latest", "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", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 262000, "max_output_tokens": 8192, "max_tokens": 8192, "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "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": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_tool_choice": true, "supports_web_search": true, "model_id": "azure_ai/grok-4-1-fast-non-reasoning", "model_name": "Grok 4 1 Fast Non Reasoning", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.19999999999999998, "output_cost_per_million": 0.5, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_vision": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 2e-7, "output_cost_per_token": 5e-7, "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "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_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.0000025, "max_input_tokens": 262000, "max_output_tokens": 8192, "deprecation_date": "2027-04-06", "max_tokens": 8192, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_prompt_caching": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "azure_ai/grok-4-20-non-reasoning", "model_name": "Grok 4 20 Non Reasoning", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.25, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 0.00000125, "cache_read_cost_per_million": 1.25, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.0000025, "max_input_tokens": 262000, "max_output_tokens": 8192, "deprecation_date": "2027-04-06", "max_tokens": 8192, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_prompt_caching": true, "supports_tool_choice": true, "supports_web_search": true, "supports_reasoning": true, "model_id": "azure_ai/grok-4-20-reasoning", "model_name": "Grok 4 20 Reasoning", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.25, "output_cost_per_million": 2.5, "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": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.0000025, "max_input_tokens": 200000, "max_output_tokens": 8192, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "input_cost_per_token_above_200k_tokens": 0.0000025, "max_tokens": 8192, "output_cost_per_token_above_200k_tokens": 0.000005, "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "azure_ai/grok-4.3", "model_name": "Grok 4.3", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 1.25, "output_cost_per_million": 2.5, "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": "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": 0.000006, "max_input_tokens": 200000, "max_output_tokens": 128000, "cache_read_input_token_cost_above_200k_tokens": 0.000001, "input_cost_per_token_above_200k_tokens": 0.000004, "max_tokens": 128000, "output_cost_per_token_above_200k_tokens": 0.000012, "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/grok/", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "azure_ai/grok-4.6", "model_name": "Grok 4.6", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2, "output_cost_per_million": 6, "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_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000006, "max_input_tokens": 500000, "max_output_tokens": 500000, "deprecation_date": "2027-10-05", "cache_read_input_token_cost_above_200k_tokens": 0.000001, "input_cost_per_token_above_200k_tokens": 0.000004, "max_tokens": 500000, "output_cost_per_token_above_200k_tokens": 0.000012, "source": "https://docs.x.ai/developers/models/grok-4.7", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "azure_ai/grok-4.7", "model_name": "Grok 4.7", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2, "output_cost_per_million": 6, "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_response_schema": true, "input_cost_per_token": 2e-7, "output_cost_per_token": 0.0000015, "max_input_tokens": 256000, "max_output_tokens": 8192, "max_tokens": 8192, "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "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 }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000024, "output_cost_per_token": 0.000012, "max_input_tokens": 922000, "max_output_tokens": 128000, "deprecation_date": "2028-03-11", "cache_creation_input_token_cost_above_272k_tokens": 0.000006, "cache_read_input_token_cost_above_272k_tokens": 2.4e-7, "input_cost_per_token_above_272k_tokens": 0.0000048, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.000018, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_computer_use": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, "supports_none_reasoning_effort": 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_xhigh_reasoning_effort": true, "model_id": "azure/apac/gpt-6.1-sol", "model_name": "GPT-6.1 Sol", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2.4, "output_cost_per_million": 12, "cache_read_cost_per_token": 1.2e-7, "cache_read_cost_per_million": 0.12, "cache_write_cost_per_token": 0.000003, "cache_write_cost_per_million": 3, "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": 0.000005, "output_cost_per_token": 0.00003, "max_input_tokens": 272000, "max_output_tokens": 128000, "deprecation_date": "2026-12-02", "max_tokens": 128000, "reasoning_effort_levels": [ "medium" ], "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", "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, "supports_web_search": true, "model_id": "azure/chat-latest", "model_name": "Chat Latest", "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", "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": 922000, "max_output_tokens": 128000, "deprecation_date": "2027-10-26", "cache_read_input_token_cost_above_272k_tokens": 0.0000011, "cache_read_input_token_cost_above_272k_tokens_batches": 5.5e-7, "cache_read_input_token_cost_batches": 2.75e-7, "cache_read_input_token_cost_priority": 0.000001375, "input_cost_per_token_above_272k_tokens": 0.000011, "input_cost_per_token_above_272k_tokens_batches": 0.0000055, "input_cost_per_token_batches": 0.00000275, "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, "output_cost_per_token_above_272k_tokens_batches": 0.00002475, "output_cost_per_token_batches": 0.0000165, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "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", "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": 922000, "max_output_tokens": 128000, "deprecation_date": "2027-10-26", "cache_read_input_token_cost_above_272k_tokens": 0.0000011, "cache_read_input_token_cost_above_272k_tokens_batches": 5.5e-7, "cache_read_input_token_cost_batches": 2.75e-7, "cache_read_input_token_cost_priority": 0.000001375, "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, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "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, "input_cost_per_token_above_272k_tokens_batches": 0.0000055, "input_cost_per_token_batches": 0.00000275, "output_cost_per_token_above_272k_tokens_batches": 0.00002475, "output_cost_per_token_batches": 0.0000165, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "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", "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": 922000, "max_output_tokens": 128000, "deprecation_date": "2027-10-26", "cache_read_input_token_cost_above_272k_tokens": 0.0000011, "cache_read_input_token_cost_priority": 0.000001375, "input_cost_per_token_batches": 0.00000275, "input_cost_per_token_above_272k_tokens": 0.000011, "input_cost_per_token_priority": 0.00001375, "output_cost_per_token_batches": 0.0000165, "output_cost_per_token_above_272k_tokens": 0.0000495, "output_cost_per_token_priority": 0.0000825, "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 }, "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, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "cache_read_input_token_cost_above_272k_tokens_batches": 5.5e-7, "cache_read_input_token_cost_batches": 2.75e-7, "input_cost_per_token_above_272k_tokens_batches": 0.0000055, "output_cost_per_token_above_272k_tokens_batches": 0.00002475, "model_id": "azure/eu/gpt-5.5-2026-04-24", "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", "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": 0.0000044, "output_cost_per_token": 0.000022, "max_input_tokens": 922000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_272k_tokens": 0.000011, "cache_creation_input_token_cost_above_272k_tokens_priority": 0.000022, "cache_creation_input_token_cost_priority": 0.000011, "cache_read_input_token_cost_above_272k_tokens": 8.8e-7, "cache_read_input_token_cost_above_272k_tokens_priority": 0.00000176, "cache_read_input_token_cost_priority": 8.8e-7, "input_cost_per_token_above_272k_tokens": 0.0000088, "input_cost_per_token_above_272k_tokens_priority": 0.0000176, "input_cost_per_token_priority": 0.0000088, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.000033, "output_cost_per_token_above_272k_tokens_priority": 0.000066, "output_cost_per_token_priority": 0.000044, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "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-5.6", "model_name": "GPT-5.6", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 4.4, "output_cost_per_million": 22, "cache_read_cost_per_token": 4.4e-7, "cache_read_cost_per_million": 0.44, "cache_write_cost_per_token": 0.0000055, "cache_write_cost_per_million": 5.5, "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": 2.2e-7, "output_cost_per_token": 0.00000132, "max_input_tokens": 922000, "max_output_tokens": 128000, "deprecation_date": "2028-01-11", "cache_creation_input_token_cost_above_272k_tokens": 5.5e-7, "cache_creation_input_token_cost_above_272k_tokens_priority": 0.0000011, "cache_creation_input_token_cost_priority": 5.5e-7, "cache_read_input_token_cost_above_272k_tokens": 4.4e-8, "cache_read_input_token_cost_above_272k_tokens_priority": 8.8e-8, "cache_read_input_token_cost_priority": 4.4e-8, "input_cost_per_token_above_272k_tokens": 4.4e-7, "input_cost_per_token_above_272k_tokens_priority": 8.8e-7, "input_cost_per_token_priority": 4.4e-7, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.00000198, "output_cost_per_token_above_272k_tokens_priority": 0.00000396, "output_cost_per_token_priority": 0.00000264, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "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-5.6-luna", "model_name": "GPT-5.6 Luna", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.22, "output_cost_per_million": 1.32, "cache_read_cost_per_token": 2.2e-8, "cache_read_cost_per_million": 0.022, "cache_write_cost_per_token": 2.75e-7, "cache_write_cost_per_million": 0.275, "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": 0.0000044, "output_cost_per_token": 0.000022, "max_input_tokens": 922000, "max_output_tokens": 128000, "deprecation_date": "2028-01-11", "cache_creation_input_token_cost_above_272k_tokens": 0.000011, "cache_creation_input_token_cost_above_272k_tokens_priority": 0.000022, "cache_creation_input_token_cost_priority": 0.000011, "cache_read_input_token_cost_above_272k_tokens": 8.8e-7, "cache_read_input_token_cost_above_272k_tokens_priority": 0.00000176, "cache_read_input_token_cost_priority": 8.8e-7, "input_cost_per_token_above_272k_tokens": 0.0000088, "input_cost_per_token_above_272k_tokens_priority": 0.0000176, "input_cost_per_token_priority": 0.0000088, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.000033, "output_cost_per_token_above_272k_tokens_priority": 0.000066, "output_cost_per_token_priority": 0.000044, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "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-5.6-sol", "model_name": "GPT-5.6 Sol", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 4.4, "output_cost_per_million": 22, "cache_read_cost_per_token": 4.4e-7, "cache_read_cost_per_million": 0.44, "cache_write_cost_per_token": 0.0000055, "cache_write_cost_per_million": 5.5, "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": 0.0000022, "output_cost_per_token": 0.0000132, "max_input_tokens": 922000, "max_output_tokens": 128000, "deprecation_date": "2028-01-11", "cache_creation_input_token_cost_above_272k_tokens": 0.0000055, "cache_creation_input_token_cost_above_272k_tokens_priority": 0.000011, "cache_creation_input_token_cost_priority": 0.0000055, "cache_read_input_token_cost_above_272k_tokens": 4.4e-7, "cache_read_input_token_cost_above_272k_tokens_priority": 8.8e-7, "cache_read_input_token_cost_priority": 4.4e-7, "input_cost_per_token_above_272k_tokens": 0.0000044, "input_cost_per_token_above_272k_tokens_priority": 0.0000088, "input_cost_per_token_priority": 0.0000044, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.0000198, "output_cost_per_token_above_272k_tokens_priority": 0.0000396, "output_cost_per_token_priority": 0.0000264, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "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-5.6-terra", "model_name": "GPT-5.6 Terra", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2.2, "output_cost_per_million": 13.200000000000001, "cache_read_cost_per_token": 2.2e-7, "cache_read_cost_per_million": 0.22, "cache_write_cost_per_token": 0.00000275, "cache_write_cost_per_million": 2.75, "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": 0.000012, "output_cost_per_token": 0.00006, "max_input_tokens": 922000, "max_output_tokens": 128000, "deprecation_date": "2028-01-11", "cache_creation_input_token_cost_above_272k_tokens": 0.00003, "cache_read_input_token_cost_above_272k_tokens": 0.0000024, "input_cost_per_token_above_272k_tokens": 0.000024, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.00009, "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_computer_use": true, "supports_max_reasoning_effort": false, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, "supports_none_reasoning_effort": 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_xhigh_reasoning_effort": true, "model_id": "azure/eu/gpt-6-astra", "model_name": "GPT-6 Astra", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 12, "output_cost_per_million": 60, "cache_read_cost_per_token": 0.0000012, "cache_read_cost_per_million": 1.2, "cache_write_cost_per_token": 0.000015, "cache_write_cost_per_million": 15, "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": 1.2e-7, "output_cost_per_token": 6e-7, "max_input_tokens": 922000, "max_output_tokens": 128000, "deprecation_date": "2028-03-11", "cache_creation_input_token_cost_above_272k_tokens": 3e-7, "cache_read_input_token_cost_above_272k_tokens": 2.4e-8, "input_cost_per_token_above_272k_tokens": 2.4e-7, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 9e-7, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_computer_use": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, "supports_none_reasoning_effort": 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_xhigh_reasoning_effort": true, "model_id": "azure/eu/gpt-6-luna", "model_name": "GPT-6 Luna", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.12, "output_cost_per_million": 0.6, "cache_read_cost_per_token": 1.2e-8, "cache_read_cost_per_million": 0.012, "cache_write_cost_per_token": 1.5e-7, "cache_write_cost_per_million": 0.15, "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": 0.0000024, "output_cost_per_token": 0.000012, "max_input_tokens": 922000, "max_output_tokens": 128000, "deprecation_date": "2028-03-11", "cache_creation_input_token_cost_above_272k_tokens": 0.000006, "cache_read_input_token_cost_above_272k_tokens": 4.8e-7, "input_cost_per_token_above_272k_tokens": 0.0000048, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.000018, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_computer_use": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, "supports_none_reasoning_effort": 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_xhigh_reasoning_effort": true, "model_id": "azure/eu/gpt-6-sol", "model_name": "GPT-6 Sol", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2.4, "output_cost_per_million": 12, "cache_read_cost_per_token": 2.4e-7, "cache_read_cost_per_million": 0.24, "cache_write_cost_per_token": 0.000003, "cache_write_cost_per_million": 3, "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": 0.0000024, "output_cost_per_token": 0.000012, "max_input_tokens": 922000, "max_output_tokens": 128000, "deprecation_date": "2028-03-11", "cache_creation_input_token_cost_above_272k_tokens": 0.000006, "cache_read_input_token_cost_above_272k_tokens": 2.4e-7, "input_cost_per_token_above_272k_tokens": 0.0000048, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.000018, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_computer_use": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, "supports_none_reasoning_effort": 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_xhigh_reasoning_effort": true, "model_id": "azure/eu/gpt-6.1-sol", "model_name": "GPT-6.1 Sol", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2.4, "output_cost_per_million": 12, "cache_read_cost_per_token": 1.2e-7, "cache_read_cost_per_million": 0.12, "cache_write_cost_per_token": 0.000003, "cache_write_cost_per_million": 3, "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": 0.000021, "output_cost_per_token": 0.000168, "max_input_tokens": 272000, "max_output_tokens": 128000, "input_cost_per_token_batches": 0.0000105, "max_tokens": 128000, "output_cost_per_token_batches": 0.000084, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "azure/gpt-5.2-pro", "model_name": "GPT-5.2 Pro", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 21, "output_cost_per_million": 168, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000021, "output_cost_per_token": 0.000168, "max_input_tokens": 272000, "max_output_tokens": 128000, "input_cost_per_token_batches": 0.0000105, "max_tokens": 128000, "output_cost_per_token_batches": 0.000084, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "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": 7.5e-7, "output_cost_per_token": 0.0000045, "max_input_tokens": 272000, "max_output_tokens": 128000, "deprecation_date": "2027-09-21", "cache_read_input_token_cost_batches": 3.75e-8, "cache_read_input_token_cost_flex": 3.75e-8, "cache_read_input_token_cost_priority": 1.5e-7, "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 }, "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, "default_reasoning_effort": "none", "input_cost_per_token_batches": 3.75e-7, "input_cost_per_token_flex": 3.75e-7, "input_cost_per_token_priority": 0.0000015, "output_cost_per_token_batches": 0.00000225, "output_cost_per_token_flex": 0.00000225, "output_cost_per_token_priority": 0.000009, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true, "model_id": "azure/gpt-5.4-mini", "model_name": "GPT-5.4 Mini", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.75, "output_cost_per_million": 4.5, "cache_read_cost_per_token": 7.5e-8, "cache_read_cost_per_million": 0.075, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 7.5e-7, "output_cost_per_token": 0.0000045, "max_input_tokens": 272000, "max_output_tokens": 128000, "deprecation_date": "2027-09-21", "cache_read_input_token_cost_flex": 3.75e-8, "cache_read_input_token_cost_priority": 1.5e-7, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", "input_cost_per_token_batches": 3.75e-7, "input_cost_per_token_flex": 3.75e-7, "input_cost_per_token_priority": 0.0000015, "output_cost_per_token_batches": 0.00000225, "output_cost_per_token_flex": 0.00000225, "output_cost_per_token_priority": 0.000009, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true, "cache_read_input_token_cost_batches": 3.75e-8, "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", "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": 272000, "max_output_tokens": 128000, "deprecation_date": "2027-09-21", "cache_read_input_token_cost_batches": 1e-8, "cache_read_input_token_cost_flex": 1e-8, "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 }, "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, "default_reasoning_effort": "none", "input_cost_per_token_batches": 1e-7, "input_cost_per_token_flex": 1e-7, "output_cost_per_token_batches": 6.25e-7, "output_cost_per_token_flex": 6.25e-7, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true, "model_id": "azure/gpt-5.4-nano", "model_name": "GPT-5.4 Nano", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.19999999999999998, "output_cost_per_million": 1.25, "cache_read_cost_per_token": 2e-8, "cache_read_cost_per_million": 0.02, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2e-7, "output_cost_per_token": 0.00000125, "max_input_tokens": 272000, "max_output_tokens": 128000, "deprecation_date": "2027-09-21", "cache_read_input_token_cost_flex": 1e-8, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", "input_cost_per_token_batches": 1e-7, "input_cost_per_token_flex": 1e-7, "output_cost_per_token_batches": 6.25e-7, "output_cost_per_token_flex": 6.25e-7, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true, "cache_read_input_token_cost_batches": 1e-8, "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", "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": 922000, "max_output_tokens": 128000, "deprecation_date": "2027-09-07", "cache_read_input_token_cost_above_272k_tokens": 0.000006, "input_cost_per_token_above_272k_tokens": 0.00006, "input_cost_per_token_above_272k_tokens_batches": 0.00003, "input_cost_per_token_above_272k_tokens_flex": 0.00003, "input_cost_per_token_batches": 0.000015, "input_cost_per_token_flex": 0.000015, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.00027, "output_cost_per_token_above_272k_tokens_batches": 0.000135, "output_cost_per_token_above_272k_tokens_flex": 0.000135, "output_cost_per_token_batches": 0.00009, "output_cost_per_token_flex": 0.00009, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "azure/gpt-5.4-pro", "model_name": "GPT-5.4 Pro", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 30, "output_cost_per_million": 180, "cache_read_cost_per_token": 0.000003, "cache_read_cost_per_million": 3, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "supports_json_mode": false, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": false, "input_cost_per_token": 0.00003, "output_cost_per_token": 0.00018, "max_input_tokens": 922000, "max_output_tokens": 128000, "deprecation_date": "2027-09-07", "cache_read_input_token_cost_above_272k_tokens": 0.000006, "input_cost_per_token_above_272k_tokens": 0.00006, "input_cost_per_token_above_272k_tokens_flex": 0.00003, "input_cost_per_token_batches": 0.000015, "input_cost_per_token_flex": 0.000015, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.00027, "output_cost_per_token_above_272k_tokens_flex": 0.000135, "output_cost_per_token_batches": 0.00009, "output_cost_per_token_flex": 0.00009, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "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, "input_cost_per_token_above_272k_tokens_batches": 0.00003, "output_cost_per_token_above_272k_tokens_batches": 0.000135, "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", "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": 922000, "max_output_tokens": 128000, "deprecation_date": "2027-10-26", "cache_read_input_token_cost_above_272k_tokens": 0.000001, "cache_read_input_token_cost_above_272k_tokens_batches": 5e-7, "cache_read_input_token_cost_priority": 0.00000125, "cache_read_input_token_cost_above_272k_tokens_priority": 0.000002, "cache_read_input_token_cost_batches": 2.5e-7, "cache_read_input_token_cost_flex": 2.5e-7, "input_cost_per_token_above_272k_tokens": 0.00001, "input_cost_per_token_above_272k_tokens_batches": 0.000005, "input_cost_per_token_above_272k_tokens_flex": 0.000005, "input_cost_per_token_priority": 0.0000125, "input_cost_per_token_above_272k_tokens_priority": 0.00002, "input_cost_per_token_batches": 0.0000025, "input_cost_per_token_flex": 0.0000025, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.000045, "output_cost_per_token_above_272k_tokens_batches": 0.0000225, "output_cost_per_token_priority": 0.000075, "output_cost_per_token_above_272k_tokens_priority": 0.00009, "output_cost_per_token_batches": 0.000015, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "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", "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": 922000, "max_output_tokens": 128000, "deprecation_date": "2027-10-26", "cache_read_input_token_cost_above_272k_tokens": 0.000001, "cache_read_input_token_cost_above_272k_tokens_batches": 5e-7, "cache_read_input_token_cost_priority": 0.00000125, "cache_read_input_token_cost_above_272k_tokens_priority": 0.000002, "cache_read_input_token_cost_batches": 2.5e-7, "cache_read_input_token_cost_flex": 2.5e-7, "input_cost_per_token_above_272k_tokens": 0.00001, "input_cost_per_token_priority": 0.0000125, "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": 0.000075, "output_cost_per_token_above_272k_tokens_priority": 0.00009, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "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, "input_cost_per_token_above_272k_tokens_batches": 0.000005, "input_cost_per_token_above_272k_tokens_flex": 0.000005, "input_cost_per_token_batches": 0.0000025, "input_cost_per_token_flex": 0.0000025, "output_cost_per_token_above_272k_tokens_batches": 0.0000225, "output_cost_per_token_batches": 0.000015, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "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", "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": 922000, "max_output_tokens": 128000, "deprecation_date": "2027-10-26", "cache_read_input_token_cost_above_272k_tokens": 0.000001, "cache_read_input_token_cost_priority": 0.00000125, "cache_read_input_token_cost_above_272k_tokens_priority": 0.000002, "cache_read_input_token_cost_flex": 2.5e-7, "input_cost_per_token_batches": 0.0000025, "input_cost_per_token_above_272k_tokens": 0.00001, "input_cost_per_token_above_272k_tokens_flex": 0.000005, "input_cost_per_token_priority": 0.0000125, "input_cost_per_token_above_272k_tokens_priority": 0.00002, "input_cost_per_token_flex": 0.0000025, "max_tokens": 128000, "output_cost_per_token_batches": 0.000015, "output_cost_per_token_above_272k_tokens": 0.000045, "output_cost_per_token_priority": 0.000075, "output_cost_per_token_above_272k_tokens_priority": 0.00009, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "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, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "cache_read_input_token_cost_above_272k_tokens_batches": 5e-7, "cache_read_input_token_cost_batches": 2.5e-7, "input_cost_per_token_above_272k_tokens_batches": 0.000005, "output_cost_per_token_above_272k_tokens_batches": 0.0000225, "model_id": "azure/gpt-5.5-2026-04-24", "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", "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, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "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, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "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": true, "supports_response_schema": true, "input_cost_per_token": 0.000004, "output_cost_per_token": 0.00002, "max_input_tokens": 922000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_272k_tokens": 0.00001, "cache_creation_input_token_cost_priority": 0.00001, "cache_creation_input_token_cost_above_272k_tokens_priority": 0.00002, "cache_read_input_token_cost_above_272k_tokens": 8e-7, "cache_read_input_token_cost_priority": 8e-7, "cache_read_input_token_cost_above_272k_tokens_priority": 0.0000016, "input_cost_per_token_above_272k_tokens": 0.000008, "input_cost_per_token_priority": 0.000008, "input_cost_per_token_above_272k_tokens_priority": 0.000016, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.00003, "output_cost_per_token_priority": 0.00004, "output_cost_per_token_above_272k_tokens_priority": 0.00006, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "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-5.6", "model_name": "GPT-5.6", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 4, "output_cost_per_million": 20, "cache_read_cost_per_token": 4e-7, "cache_read_cost_per_million": 0.39999999999999997, "cache_write_cost_per_token": 0.000005, "cache_write_cost_per_million": 5, "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": 0.0000012, "max_input_tokens": 922000, "max_output_tokens": 128000, "deprecation_date": "2028-01-11", "cache_creation_input_token_cost_above_272k_tokens": 5e-7, "cache_creation_input_token_cost_above_272k_tokens_flex": 2.5e-7, "cache_creation_input_token_cost_priority": 5e-7, "cache_creation_input_token_cost_above_272k_tokens_priority": 0.000001, "cache_creation_input_token_cost_flex": 1.25e-7, "cache_read_input_token_cost_above_272k_tokens": 4e-8, "cache_read_input_token_cost_above_272k_tokens_flex": 2e-8, "cache_read_input_token_cost_priority": 4e-8, "cache_read_input_token_cost_above_272k_tokens_priority": 8e-8, "cache_read_input_token_cost_flex": 1e-8, "input_cost_per_token_above_272k_tokens": 4e-7, "input_cost_per_token_above_272k_tokens_flex": 2e-7, "input_cost_per_token_priority": 4e-7, "input_cost_per_token_above_272k_tokens_priority": 8e-7, "input_cost_per_token_flex": 1e-7, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.0000018, "output_cost_per_token_above_272k_tokens_flex": 9e-7, "output_cost_per_token_priority": 0.0000024, "output_cost_per_token_above_272k_tokens_priority": 0.0000036, "output_cost_per_token_flex": 6e-7, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "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-5.6-luna", "model_name": "GPT-5.6 Luna", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.19999999999999998, "output_cost_per_million": 1.2, "cache_read_cost_per_token": 2e-8, "cache_read_cost_per_million": 0.02, "cache_write_cost_per_token": 2.5e-7, "cache_write_cost_per_million": 0.25, "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": 2e-7, "output_cost_per_token": 0.0000012, "max_input_tokens": 922000, "max_output_tokens": 128000, "deprecation_date": "2028-01-11", "cache_creation_input_token_cost_above_272k_tokens": 5e-7, "cache_creation_input_token_cost_above_272k_tokens_flex": 2.5e-7, "cache_creation_input_token_cost_priority": 5e-7, "cache_creation_input_token_cost_above_272k_tokens_priority": 0.000001, "cache_creation_input_token_cost_flex": 1.25e-7, "cache_read_input_token_cost_above_272k_tokens": 4e-8, "cache_read_input_token_cost_above_272k_tokens_flex": 2e-8, "cache_read_input_token_cost_priority": 4e-8, "cache_read_input_token_cost_above_272k_tokens_priority": 8e-8, "cache_read_input_token_cost_flex": 1e-8, "input_cost_per_token_above_272k_tokens": 4e-7, "input_cost_per_token_above_272k_tokens_flex": 2e-7, "input_cost_per_token_priority": 4e-7, "input_cost_per_token_above_272k_tokens_priority": 8e-7, "input_cost_per_token_flex": 1e-7, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.0000018, "output_cost_per_token_above_272k_tokens_flex": 9e-7, "output_cost_per_token_priority": 0.0000024, "output_cost_per_token_above_272k_tokens_priority": 0.0000036, "output_cost_per_token_flex": 6e-7, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "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, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "model_id": "azure/gpt-5.6-luna-2026-07-09", "model_name": "GPT-5.6 Luna (Jul 2026)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.19999999999999998, "output_cost_per_million": 1.2, "cache_read_cost_per_token": 2e-8, "cache_read_cost_per_million": 0.02, "cache_write_cost_per_token": 2.5e-7, "cache_write_cost_per_million": 0.25, "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": 0.000004, "output_cost_per_token": 0.00002, "max_input_tokens": 922000, "max_output_tokens": 128000, "deprecation_date": "2028-01-11", "cache_creation_input_token_cost_above_272k_tokens": 0.00001, "cache_creation_input_token_cost_above_272k_tokens_flex": 0.000005, "cache_creation_input_token_cost_priority": 0.00001, "cache_creation_input_token_cost_above_272k_tokens_priority": 0.00002, "cache_creation_input_token_cost_flex": 0.0000025, "cache_read_input_token_cost_above_272k_tokens": 8e-7, "cache_read_input_token_cost_above_272k_tokens_flex": 4e-7, "cache_read_input_token_cost_priority": 8e-7, "cache_read_input_token_cost_above_272k_tokens_priority": 0.0000016, "cache_read_input_token_cost_flex": 2e-7, "input_cost_per_token_above_272k_tokens": 0.000008, "input_cost_per_token_above_272k_tokens_flex": 0.000004, "input_cost_per_token_priority": 0.000008, "input_cost_per_token_above_272k_tokens_priority": 0.000016, "input_cost_per_token_flex": 0.000002, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.00003, "output_cost_per_token_above_272k_tokens_flex": 0.000015, "output_cost_per_token_priority": 0.00004, "output_cost_per_token_above_272k_tokens_priority": 0.00006, "output_cost_per_token_flex": 0.00001, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "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-5.6-sol", "model_name": "GPT-5.6 Sol", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 4, "output_cost_per_million": 20, "cache_read_cost_per_token": 4e-7, "cache_read_cost_per_million": 0.39999999999999997, "cache_write_cost_per_token": 0.000005, "cache_write_cost_per_million": 5, "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": 0.000004, "output_cost_per_token": 0.00002, "max_input_tokens": 922000, "max_output_tokens": 128000, "deprecation_date": "2028-01-11", "cache_creation_input_token_cost_above_272k_tokens": 0.00001, "cache_creation_input_token_cost_above_272k_tokens_flex": 0.000005, "cache_creation_input_token_cost_priority": 0.00001, "cache_creation_input_token_cost_above_272k_tokens_priority": 0.00002, "cache_creation_input_token_cost_flex": 0.0000025, "cache_read_input_token_cost_above_272k_tokens": 8e-7, "cache_read_input_token_cost_above_272k_tokens_flex": 4e-7, "cache_read_input_token_cost_priority": 8e-7, "cache_read_input_token_cost_above_272k_tokens_priority": 0.0000016, "cache_read_input_token_cost_flex": 2e-7, "input_cost_per_token_above_272k_tokens": 0.000008, "input_cost_per_token_above_272k_tokens_flex": 0.000004, "input_cost_per_token_priority": 0.000008, "input_cost_per_token_above_272k_tokens_priority": 0.000016, "input_cost_per_token_flex": 0.000002, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.00003, "output_cost_per_token_above_272k_tokens_flex": 0.000015, "output_cost_per_token_priority": 0.00004, "output_cost_per_token_above_272k_tokens_priority": 0.00006, "output_cost_per_token_flex": 0.00001, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "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-5.6-sol-2026-07-09", "model_name": "GPT-5.6 Sol (Jul 2026)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 4, "output_cost_per_million": 20, "cache_read_cost_per_token": 4e-7, "cache_read_cost_per_million": 0.39999999999999997, "cache_write_cost_per_token": 0.000005, "cache_write_cost_per_million": 5, "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": 0.000002, "output_cost_per_token": 0.000012, "max_input_tokens": 922000, "max_output_tokens": 128000, "deprecation_date": "2028-01-11", "cache_creation_input_token_cost_above_272k_tokens": 0.000005, "cache_creation_input_token_cost_above_272k_tokens_flex": 0.0000025, "cache_creation_input_token_cost_priority": 0.000005, "cache_creation_input_token_cost_above_272k_tokens_priority": 0.00001, "cache_creation_input_token_cost_flex": 0.00000125, "cache_read_input_token_cost_above_272k_tokens": 4e-7, "cache_read_input_token_cost_above_272k_tokens_flex": 2e-7, "cache_read_input_token_cost_priority": 4e-7, "cache_read_input_token_cost_above_272k_tokens_priority": 8e-7, "cache_read_input_token_cost_flex": 1e-7, "input_cost_per_token_above_272k_tokens": 0.000004, "input_cost_per_token_above_272k_tokens_flex": 0.000002, "input_cost_per_token_priority": 0.000004, "input_cost_per_token_above_272k_tokens_priority": 0.000008, "input_cost_per_token_flex": 0.000001, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.000018, "output_cost_per_token_above_272k_tokens_flex": 0.000009, "output_cost_per_token_priority": 0.000024, "output_cost_per_token_above_272k_tokens_priority": 0.000036, "output_cost_per_token_flex": 0.000006, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "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-5.6-terra", "model_name": "GPT-5.6 Terra", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2, "output_cost_per_million": 12, "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", "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": 0.000012, "max_input_tokens": 922000, "max_output_tokens": 128000, "deprecation_date": "2028-01-11", "cache_creation_input_token_cost_above_272k_tokens": 0.000005, "cache_creation_input_token_cost_above_272k_tokens_flex": 0.0000025, "cache_creation_input_token_cost_priority": 0.000005, "cache_creation_input_token_cost_above_272k_tokens_priority": 0.00001, "cache_creation_input_token_cost_flex": 0.00000125, "cache_read_input_token_cost_above_272k_tokens": 4e-7, "cache_read_input_token_cost_above_272k_tokens_flex": 2e-7, "cache_read_input_token_cost_priority": 4e-7, "cache_read_input_token_cost_above_272k_tokens_priority": 8e-7, "cache_read_input_token_cost_flex": 1e-7, "input_cost_per_token_above_272k_tokens": 0.000004, "input_cost_per_token_above_272k_tokens_flex": 0.000002, "input_cost_per_token_priority": 0.000004, "input_cost_per_token_above_272k_tokens_priority": 0.000008, "input_cost_per_token_flex": 0.000001, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.000018, "output_cost_per_token_above_272k_tokens_flex": 0.000009, "output_cost_per_token_priority": 0.000024, "output_cost_per_token_above_272k_tokens_priority": 0.000036, "output_cost_per_token_flex": 0.000006, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "model_id": "azure/gpt-5.6-terra-2026-07-09", "model_name": "GPT-5.6 Terra (Jul 2026)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2, "output_cost_per_million": 12, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 0.0000025, "cache_write_cost_per_million": 2.5, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00001, "output_cost_per_token": 0.00005, "max_input_tokens": 922000, "max_output_tokens": 128000, "deprecation_date": "2028-01-11", "cache_creation_input_token_cost_above_272k_tokens": 0.000025, "cache_read_input_token_cost_above_272k_tokens": 0.000002, "input_cost_per_token_above_272k_tokens": 0.00002, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.000075, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_computer_use": true, "supports_max_reasoning_effort": false, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, "supports_none_reasoning_effort": 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_xhigh_reasoning_effort": true, "model_id": "azure/gpt-6-astra", "model_name": "GPT-6 Astra", "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", "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": 0.00001, "output_cost_per_token": 0.00005, "max_input_tokens": 922000, "max_output_tokens": 128000, "deprecation_date": "2028-01-11", "cache_creation_input_token_cost_above_272k_tokens": 0.000025, "cache_read_input_token_cost_above_272k_tokens": 0.000002, "input_cost_per_token_above_272k_tokens": 0.00002, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.000075, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_computer_use": true, "supports_max_reasoning_effort": false, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, "supports_none_reasoning_effort": 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_xhigh_reasoning_effort": true, "model_id": "azure/gpt-6-astra-2026-09-03", "model_name": "GPT-6 Astra (Sep 2026)", "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", "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": 5e-7, "max_input_tokens": 922000, "max_output_tokens": 128000, "deprecation_date": "2028-03-11", "cache_creation_input_token_cost_above_272k_tokens": 2.5e-7, "cache_read_input_token_cost_above_272k_tokens": 2e-8, "input_cost_per_token_above_272k_tokens": 2e-7, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 7.5e-7, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_computer_use": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, "supports_none_reasoning_effort": 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_xhigh_reasoning_effort": true, "model_id": "azure/gpt-6-luna", "model_name": "GPT-6 Luna", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0.5, "cache_read_cost_per_token": 1e-8, "cache_read_cost_per_million": 0.01, "cache_write_cost_per_token": 1.25e-7, "cache_write_cost_per_million": 0.125, "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": 5e-7, "max_input_tokens": 922000, "max_output_tokens": 128000, "deprecation_date": "2028-03-11", "cache_creation_input_token_cost_above_272k_tokens": 2.5e-7, "cache_read_input_token_cost_above_272k_tokens": 2e-8, "input_cost_per_token_above_272k_tokens": 2e-7, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 7.5e-7, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_computer_use": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, "supports_none_reasoning_effort": 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_xhigh_reasoning_effort": true, "model_id": "azure/gpt-6-luna-2026-09-22", "model_name": "GPT-6 Luna (Sep 2026)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0.5, "cache_read_cost_per_token": 1e-8, "cache_read_cost_per_million": 0.01, "cache_write_cost_per_token": 1.25e-7, "cache_write_cost_per_million": 0.125, "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": 0.000002, "output_cost_per_token": 0.00001, "max_input_tokens": 922000, "max_output_tokens": 128000, "deprecation_date": "2028-03-11", "cache_creation_input_token_cost_above_272k_tokens": 0.000005, "cache_creation_input_token_cost_above_272k_tokens_priority": 0.00001, "cache_creation_input_token_cost_priority": 0.000005, "cache_read_input_token_cost_above_272k_tokens": 4e-7, "cache_read_input_token_cost_above_272k_tokens_priority": 8e-7, "cache_read_input_token_cost_priority": 4e-7, "input_cost_per_token_above_272k_tokens": 0.000004, "input_cost_per_token_above_272k_tokens_priority": 0.000008, "input_cost_per_token_priority": 0.000004, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.000015, "output_cost_per_token_above_272k_tokens_priority": 0.00003, "output_cost_per_token_priority": 0.00002, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_computer_use": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, "supports_none_reasoning_effort": 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_xhigh_reasoning_effort": true, "model_id": "azure/gpt-6-sol", "model_name": "GPT-6 Sol", "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", "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": 0.00001, "max_input_tokens": 922000, "max_output_tokens": 128000, "deprecation_date": "2028-03-11", "cache_creation_input_token_cost_above_272k_tokens": 0.000005, "cache_creation_input_token_cost_above_272k_tokens_priority": 0.00001, "cache_creation_input_token_cost_priority": 0.000005, "cache_read_input_token_cost_above_272k_tokens": 4e-7, "cache_read_input_token_cost_above_272k_tokens_priority": 8e-7, "cache_read_input_token_cost_priority": 4e-7, "input_cost_per_token_above_272k_tokens": 0.000004, "input_cost_per_token_above_272k_tokens_priority": 0.000008, "input_cost_per_token_priority": 0.000004, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.000015, "output_cost_per_token_above_272k_tokens_priority": 0.00003, "output_cost_per_token_priority": 0.00002, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_computer_use": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, "supports_none_reasoning_effort": 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_xhigh_reasoning_effort": true, "model_id": "azure/gpt-6-sol-2026-09-22", "model_name": "GPT-6 Sol (Sep 2026)", "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", "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": 0.00001, "max_input_tokens": 922000, "max_output_tokens": 128000, "deprecation_date": "2028-03-11", "cache_creation_input_token_cost_above_272k_tokens": 0.000005, "cache_read_input_token_cost_above_272k_tokens": 2e-7, "input_cost_per_token_above_272k_tokens": 0.000004, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.000015, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_computer_use": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, "supports_none_reasoning_effort": 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_xhigh_reasoning_effort": true, "model_id": "azure/gpt-6.1-sol", "model_name": "GPT-6.1 Sol", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2, "output_cost_per_million": 10, "cache_read_cost_per_token": 1e-7, "cache_read_cost_per_million": 0.09999999999999999, "cache_write_cost_per_token": 0.0000025, "cache_write_cost_per_million": 2.5, "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": 0.000002, "output_cost_per_token": 0.00001, "max_input_tokens": 922000, "max_output_tokens": 128000, "deprecation_date": "2028-03-11", "cache_creation_input_token_cost_above_272k_tokens": 0.000005, "cache_read_input_token_cost_above_272k_tokens": 2e-7, "input_cost_per_token_above_272k_tokens": 0.000004, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.000015, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_computer_use": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, "supports_none_reasoning_effort": 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_xhigh_reasoning_effort": true, "model_id": "azure/gpt-6.1-sol-2026-09-29", "model_name": "GPT-6.1 Sol (Sep 2026)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2, "output_cost_per_million": 10, "cache_read_cost_per_token": 1e-7, "cache_read_cost_per_million": 0.09999999999999999, "cache_write_cost_per_token": 0.0000025, "cache_write_cost_per_million": 2.5, "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": 0.000005, "output_cost_per_token": 0.00003, "max_input_tokens": 272000, "max_output_tokens": 128000, "deprecation_date": "2026-12-02", "max_tokens": 128000, "reasoning_effort_levels": [ "medium" ], "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", "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, "supports_web_search": true, "model_id": "azure/gpt-chat-latest", "model_name": "GPT Chat Latest", "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", "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": 0.00001, "output_cost_per_token": 0.00004, "max_input_tokens": 200000, "max_output_tokens": 100000, "deprecation_date": "2026-11-19", "max_tokens": 100000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "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", "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": 922000, "max_output_tokens": 128000, "deprecation_date": "2027-10-26", "cache_read_input_token_cost_above_272k_tokens": 0.0000011, "cache_read_input_token_cost_above_272k_tokens_batches": 5.5e-7, "cache_read_input_token_cost_batches": 2.75e-7, "cache_read_input_token_cost_priority": 0.000001375, "input_cost_per_token_above_272k_tokens": 0.000011, "input_cost_per_token_above_272k_tokens_batches": 0.0000055, "input_cost_per_token_batches": 0.00000275, "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, "output_cost_per_token_above_272k_tokens_batches": 0.00002475, "output_cost_per_token_batches": 0.0000165, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "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", "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": 922000, "max_output_tokens": 128000, "deprecation_date": "2027-10-26", "cache_read_input_token_cost_above_272k_tokens": 0.0000011, "cache_read_input_token_cost_above_272k_tokens_batches": 5.5e-7, "cache_read_input_token_cost_batches": 2.75e-7, "cache_read_input_token_cost_priority": 0.000001375, "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, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "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, "input_cost_per_token_above_272k_tokens_batches": 0.0000055, "input_cost_per_token_batches": 0.00000275, "output_cost_per_token_above_272k_tokens_batches": 0.00002475, "output_cost_per_token_batches": 0.0000165, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "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", "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": 922000, "max_output_tokens": 128000, "deprecation_date": "2027-10-26", "cache_read_input_token_cost_above_272k_tokens": 0.0000011, "cache_read_input_token_cost_priority": 0.000001375, "input_cost_per_token_batches": 0.00000275, "input_cost_per_token_above_272k_tokens": 0.000011, "input_cost_per_token_priority": 0.00001375, "output_cost_per_token_batches": 0.0000165, "output_cost_per_token_above_272k_tokens": 0.0000495, "output_cost_per_token_priority": 0.0000825, "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 }, "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, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "cache_read_input_token_cost_above_272k_tokens_batches": 5.5e-7, "cache_read_input_token_cost_batches": 2.75e-7, "input_cost_per_token_above_272k_tokens_batches": 0.0000055, "output_cost_per_token_above_272k_tokens_batches": 0.00002475, "model_id": "azure/us/gpt-5.5-2026-04-24", "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", "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": 0.0000044, "output_cost_per_token": 0.000022, "max_input_tokens": 922000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_272k_tokens": 0.000011, "cache_creation_input_token_cost_above_272k_tokens_priority": 0.000022, "cache_creation_input_token_cost_priority": 0.000011, "cache_read_input_token_cost_above_272k_tokens": 8.8e-7, "cache_read_input_token_cost_above_272k_tokens_priority": 0.00000176, "cache_read_input_token_cost_priority": 8.8e-7, "input_cost_per_token_above_272k_tokens": 0.0000088, "input_cost_per_token_above_272k_tokens_priority": 0.0000176, "input_cost_per_token_priority": 0.0000088, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.000033, "output_cost_per_token_above_272k_tokens_priority": 0.000066, "output_cost_per_token_priority": 0.000044, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "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-5.6", "model_name": "GPT-5.6", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 4.4, "output_cost_per_million": 22, "cache_read_cost_per_token": 4.4e-7, "cache_read_cost_per_million": 0.44, "cache_write_cost_per_token": 0.0000055, "cache_write_cost_per_million": 5.5, "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": 2.2e-7, "output_cost_per_token": 0.00000132, "max_input_tokens": 922000, "max_output_tokens": 128000, "deprecation_date": "2028-01-11", "cache_creation_input_token_cost_above_272k_tokens": 5.5e-7, "cache_creation_input_token_cost_above_272k_tokens_priority": 0.0000011, "cache_creation_input_token_cost_priority": 5.5e-7, "cache_read_input_token_cost_above_272k_tokens": 4.4e-8, "cache_read_input_token_cost_above_272k_tokens_priority": 8.8e-8, "cache_read_input_token_cost_priority": 4.4e-8, "input_cost_per_token_above_272k_tokens": 4.4e-7, "input_cost_per_token_above_272k_tokens_priority": 8.8e-7, "input_cost_per_token_priority": 4.4e-7, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.00000198, "output_cost_per_token_above_272k_tokens_priority": 0.00000396, "output_cost_per_token_priority": 0.00000264, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "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-5.6-luna", "model_name": "GPT-5.6 Luna", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.22, "output_cost_per_million": 1.32, "cache_read_cost_per_token": 2.2e-8, "cache_read_cost_per_million": 0.022, "cache_write_cost_per_token": 2.75e-7, "cache_write_cost_per_million": 0.275, "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": 0.0000044, "output_cost_per_token": 0.000022, "max_input_tokens": 922000, "max_output_tokens": 128000, "deprecation_date": "2028-01-11", "cache_creation_input_token_cost_above_272k_tokens": 0.000011, "cache_creation_input_token_cost_above_272k_tokens_priority": 0.000022, "cache_creation_input_token_cost_priority": 0.000011, "cache_read_input_token_cost_above_272k_tokens": 8.8e-7, "cache_read_input_token_cost_above_272k_tokens_priority": 0.00000176, "cache_read_input_token_cost_priority": 8.8e-7, "input_cost_per_token_above_272k_tokens": 0.0000088, "input_cost_per_token_above_272k_tokens_priority": 0.0000176, "input_cost_per_token_priority": 0.0000088, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.000033, "output_cost_per_token_above_272k_tokens_priority": 0.000066, "output_cost_per_token_priority": 0.000044, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "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-5.6-sol", "model_name": "GPT-5.6 Sol", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 4.4, "output_cost_per_million": 22, "cache_read_cost_per_token": 4.4e-7, "cache_read_cost_per_million": 0.44, "cache_write_cost_per_token": 0.0000055, "cache_write_cost_per_million": 5.5, "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": 0.0000022, "output_cost_per_token": 0.0000132, "max_input_tokens": 922000, "max_output_tokens": 128000, "deprecation_date": "2028-01-11", "cache_creation_input_token_cost_above_272k_tokens": 0.0000055, "cache_creation_input_token_cost_above_272k_tokens_priority": 0.000011, "cache_creation_input_token_cost_priority": 0.0000055, "cache_read_input_token_cost_above_272k_tokens": 4.4e-7, "cache_read_input_token_cost_above_272k_tokens_priority": 8.8e-7, "cache_read_input_token_cost_priority": 4.4e-7, "input_cost_per_token_above_272k_tokens": 0.0000044, "input_cost_per_token_above_272k_tokens_priority": 0.0000088, "input_cost_per_token_priority": 0.0000044, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.0000198, "output_cost_per_token_above_272k_tokens_priority": 0.0000396, "output_cost_per_token_priority": 0.0000264, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "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-5.6-terra", "model_name": "GPT-5.6 Terra", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2.2, "output_cost_per_million": 13.200000000000001, "cache_read_cost_per_token": 2.2e-7, "cache_read_cost_per_million": 0.22, "cache_write_cost_per_token": 0.00000275, "cache_write_cost_per_million": 2.75, "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": 0.000011, "output_cost_per_token": 0.000055, "max_input_tokens": 922000, "max_output_tokens": 128000, "deprecation_date": "2028-01-11", "cache_creation_input_token_cost_above_272k_tokens": 0.0000275, "cache_read_input_token_cost_above_272k_tokens": 0.0000022, "input_cost_per_token_above_272k_tokens": 0.000022, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.0000825, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_computer_use": true, "supports_max_reasoning_effort": false, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, "supports_none_reasoning_effort": 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_xhigh_reasoning_effort": true, "model_id": "azure/us/gpt-6-astra", "model_name": "GPT-6 Astra", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 11, "output_cost_per_million": 55, "cache_read_cost_per_token": 0.0000011, "cache_read_cost_per_million": 1.1, "cache_write_cost_per_token": 0.00001375, "cache_write_cost_per_million": 13.75, "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": 5.5e-7, "max_input_tokens": 922000, "max_output_tokens": 128000, "deprecation_date": "2028-03-11", "cache_creation_input_token_cost_above_272k_tokens": 2.75e-7, "cache_read_input_token_cost_above_272k_tokens": 2.2e-8, "input_cost_per_token_above_272k_tokens": 2.2e-7, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 8.25e-7, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_computer_use": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, "supports_none_reasoning_effort": 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_xhigh_reasoning_effort": true, "model_id": "azure/us/gpt-6-luna", "model_name": "GPT-6 Luna", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.11, "output_cost_per_million": 0.55, "cache_read_cost_per_token": 1.1e-8, "cache_read_cost_per_million": 0.011, "cache_write_cost_per_token": 1.375e-7, "cache_write_cost_per_million": 0.1375, "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": 0.0000022, "output_cost_per_token": 0.000011, "max_input_tokens": 922000, "max_output_tokens": 128000, "deprecation_date": "2028-03-11", "cache_creation_input_token_cost_above_272k_tokens": 0.0000055, "cache_creation_input_token_cost_above_272k_tokens_priority": 0.000011, "cache_creation_input_token_cost_priority": 0.0000055, "cache_read_input_token_cost_above_272k_tokens": 4.4e-7, "cache_read_input_token_cost_above_272k_tokens_priority": 8.8e-7, "cache_read_input_token_cost_priority": 4.4e-7, "input_cost_per_token_above_272k_tokens": 0.0000044, "input_cost_per_token_above_272k_tokens_priority": 0.0000088, "input_cost_per_token_priority": 0.0000044, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.0000165, "output_cost_per_token_above_272k_tokens_priority": 0.000033, "output_cost_per_token_priority": 0.000022, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://azure.microsoft.com/en-us/blog/gpt-6-astra-sol-and-luna-for-production-agents-in-microsoft-foundry/", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_computer_use": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, "supports_none_reasoning_effort": 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_xhigh_reasoning_effort": true, "model_id": "azure/us/gpt-6-sol", "model_name": "GPT-6 Sol", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2.2, "output_cost_per_million": 11, "cache_read_cost_per_token": 2.2e-7, "cache_read_cost_per_million": 0.22, "cache_write_cost_per_token": 0.00000275, "cache_write_cost_per_million": 2.75, "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": 0.0000022, "output_cost_per_token": 0.000011, "max_input_tokens": 922000, "max_output_tokens": 128000, "deprecation_date": "2028-03-11", "cache_creation_input_token_cost_above_272k_tokens": 0.0000055, "cache_read_input_token_cost_above_272k_tokens": 2.2e-7, "input_cost_per_token_above_272k_tokens": 0.0000044, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.0000165, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_computer_use": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, "supports_none_reasoning_effort": 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_xhigh_reasoning_effort": true, "model_id": "azure/us/gpt-6.1-sol", "model_name": "GPT-6.1 Sol", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 2.2, "output_cost_per_million": 11, "cache_read_cost_per_token": 1.1e-7, "cache_read_cost_per_million": 0.11, "cache_write_cost_per_token": 0.00000275, "cache_write_cost_per_million": 2.75, "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": 0.0000055, "output_cost_per_token": 0.000033, "max_input_tokens": 272000, "max_output_tokens": 128000, "deprecation_date": "2026-12-02", "max_tokens": 128000, "reasoning_effort_levels": [ "medium" ], "source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/", "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, "supports_web_search": true, "model_id": "azure/us/gpt-chat-latest", "model_name": "GPT Chat Latest", "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", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_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, "input_cost_per_token_above_272k_tokens": 0.0000055, "cache_read_input_token_cost_above_272k_tokens": 5.5e-7, "output_cost_per_token_above_272k_tokens": 0.00002475, "search_context_cost_per_query": { "search_context_size_high": 0.012, "search_context_size_low": 0.012, "search_context_size_medium": 0.012 }, "max_tokens": 128000, "use_openai_responses_path": true, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_minimal_reasoning_effort": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_web_search": true, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-54.html", "model_id": "bedrock_mantle/openai.gpt-5.4", "model_name": "Openai.GPT-5.4", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 2.75, "output_cost_per_million": 16.5, "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": "responses", "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": 0.0000055, "output_cost_per_token": 0.000033, "max_input_tokens": 1050000, "max_output_tokens": 128000, "input_cost_per_token_above_272k_tokens": 0.000011, "cache_read_input_token_cost_above_272k_tokens": 0.0000011, "output_cost_per_token_above_272k_tokens": 0.0000495, "search_context_cost_per_query": { "search_context_size_high": 0.012, "search_context_size_low": 0.012, "search_context_size_medium": 0.012 }, "max_tokens": 128000, "use_openai_responses_path": true, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_minimal_reasoning_effort": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_web_search": true, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-55.html", "model_id": "bedrock_mantle/openai.gpt-5.5", "model_name": "Openai.GPT-5.5", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "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": "responses", "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": 2.2e-7, "output_cost_per_token": 0.00000132, "max_input_tokens": 1050000, "max_output_tokens": 128000, "input_cost_per_token_above_272k_tokens": 4.4e-7, "cache_creation_input_token_cost_above_272k_tokens": 5.5e-7, "cache_read_input_token_cost_above_272k_tokens": 4.4e-8, "output_cost_per_token_above_272k_tokens": 0.00000198, "search_context_cost_per_query": { "search_context_size_high": 0.012, "search_context_size_low": 0.012, "search_context_size_medium": 0.012 }, "max_tokens": 128000, "use_openai_responses_path": true, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_prompt_caching": true, "supports_prompt_cache_breakpoint": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_web_search": true, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-luna.html", "model_id": "bedrock_mantle/openai.gpt-5.6-luna", "model_name": "Openai.GPT-5.6 Luna", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.22, "output_cost_per_million": 1.32, "cache_read_cost_per_token": 2.2e-8, "cache_read_cost_per_million": 0.022, "cache_write_cost_per_token": 2.75e-7, "cache_write_cost_per_million": 0.275, "model_type": "responses", "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": 0.0000044, "output_cost_per_token": 0.000022, "max_input_tokens": 1050000, "max_output_tokens": 128000, "input_cost_per_token_above_272k_tokens": 0.0000088, "cache_creation_input_token_cost_above_272k_tokens": 0.000011, "cache_read_input_token_cost_above_272k_tokens": 8.8e-7, "output_cost_per_token_above_272k_tokens": 0.000033, "search_context_cost_per_query": { "search_context_size_high": 0.012, "search_context_size_low": 0.012, "search_context_size_medium": 0.012 }, "max_tokens": 128000, "use_openai_responses_path": true, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_prompt_caching": true, "supports_prompt_cache_breakpoint": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_web_search": true, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-sol.html", "model_id": "bedrock_mantle/openai.gpt-5.6-sol", "model_name": "Openai.GPT-5.6 Sol", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 4.4, "output_cost_per_million": 22, "cache_read_cost_per_token": 4.4e-7, "cache_read_cost_per_million": 0.44, "cache_write_cost_per_token": 0.0000055, "cache_write_cost_per_million": 5.5, "model_type": "responses", "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": 0.0000022, "output_cost_per_token": 0.0000132, "max_input_tokens": 1050000, "max_output_tokens": 128000, "input_cost_per_token_above_272k_tokens": 0.0000044, "cache_creation_input_token_cost_above_272k_tokens": 0.0000055, "cache_read_input_token_cost_above_272k_tokens": 4.4e-7, "output_cost_per_token_above_272k_tokens": 0.0000198, "search_context_cost_per_query": { "search_context_size_high": 0.012, "search_context_size_low": 0.012, "search_context_size_medium": 0.012 }, "max_tokens": 128000, "use_openai_responses_path": true, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_prompt_caching": true, "supports_prompt_cache_breakpoint": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_web_search": true, "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-56-terra.html", "model_id": "bedrock_mantle/openai.gpt-5.6-terra", "model_name": "Openai.GPT-5.6 Terra", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 2.2, "output_cost_per_million": 13.200000000000001, "cache_read_cost_per_token": 2.2e-7, "cache_read_cost_per_million": 0.22, "cache_write_cost_per_token": 0.00000275, "cache_write_cost_per_million": 2.75, "model_type": "responses", "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": 1.5e-7, "output_cost_per_token": 4.7e-7, "max_input_tokens": 991808, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://docs.modelstudio.console.alibabacloud.com/en/model-studio/model-pricing", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_video_input": true, "supports_web_search": true, "model_id": "dashscope/qwen3.8-flash", "model_name": "Qwen3.8 Flash", "provider_id": "dashscope", "provider_name": "Dashscope", "input_cost_per_million": 0.15, "output_cost_per_million": 0.47, "cache_read_cost_per_token": 1.6e-8, "cache_read_cost_per_million": 0.016, "cache_write_cost_per_token": 2e-7, "cache_write_cost_per_million": 0.19999999999999998, "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": 1.5e-7, "output_cost_per_token": 4.7e-7, "max_input_tokens": 991808, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://docs.modelstudio.console.alibabacloud.com/en/model-studio/model-pricing", "supports_audio_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_video_input": true, "supports_web_search": true, "model_id": "dashscope/qwen3.8-omni-flash", "model_name": "Qwen3.8 Omni Flash", "provider_id": "dashscope", "provider_name": "Dashscope", "input_cost_per_million": 0.15, "output_cost_per_million": 0.47, "cache_read_cost_per_token": 1.6e-8, "cache_read_cost_per_million": 0.016, "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_response_schema": true, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000025, "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "source": "https://fireworks.ai/pricing", "supports_tool_choice": true, "supports_web_search": true, "model_id": "fireworks_ai/accounts/fireworks/models/kimi-k2-thinking", "model_name": "Kimi K2 Thinking", "provider_id": "fireworks", "provider_name": "Fireworks AI", "input_cost_per_million": 0.6, "output_cost_per_million": 2.5, "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_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000025, "max_input_tokens": 1048576, "max_output_tokens": 65536, "cache_read_input_audio_token_cost": 1e-7, "cache_read_input_token_cost_batches": 3e-8, "cache_read_input_token_cost_flex": 3e-8, "cache_read_input_token_cost_priority": 5.4e-8, "input_cost_per_audio_token": 0.000001, "max_tokens": 65536, "output_cost_per_reasoning_token": 0.0000025, "rpm": 100000, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_web_search": true, "tpm": 8000000, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "google_maps_grounding_cost_per_query": 0.025, "input_cost_per_audio_token_batches": 5e-7, "input_cost_per_audio_token_priority": 0.0000018, "input_cost_per_token_batches": 1.5e-7, "input_cost_per_token_flex": 1.5e-7, "input_cost_per_token_priority": 5.4e-7, "output_cost_per_token_batches": 0.00000125, "output_cost_per_token_flex": 0.00000125, "output_cost_per_token_priority": 0.0000045, "supports_audio_input": true, "supports_image_size": false, "model_id": "2.5-flash", "model_name": "2.5 Flash", "provider_id": "google", "provider_name": "Google", "input_cost_per_million": 0.3, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 3e-8, "cache_read_cost_per_million": 0.03, "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": 1048576, "max_output_tokens": 65536, "cache_read_input_audio_token_cost": 3e-8, "cache_read_input_token_cost_batches": 1e-8, "cache_read_input_token_cost_flex": 1e-8, "cache_read_input_token_cost_priority": 1.8e-8, "input_cost_per_audio_token": 3e-7, "max_tokens": 65536, "output_cost_per_reasoning_token": 4e-7, "rpm": 15, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_web_search": true, "tpm": 250000, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "google_maps_grounding_cost_per_query": 0.025, "input_cost_per_audio_token_batches": 1.5e-7, "input_cost_per_audio_token_priority": 5.4e-7, "input_cost_per_token_batches": 5e-8, "input_cost_per_token_flex": 5e-8, "input_cost_per_token_priority": 1.8e-7, "output_cost_per_token_batches": 2e-7, "output_cost_per_token_flex": 2e-7, "output_cost_per_token_priority": 7.2e-7, "supports_audio_input": true, "supports_image_size": false, "model_id": "2.5-flash-lite", "model_name": "2.5 Flash Lite", "provider_id": "google", "provider_name": "Google", "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0.39999999999999997, "cache_read_cost_per_token": 1e-8, "cache_read_cost_per_million": 0.01, "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_vision": true, "supports_response_schema": false, "input_cost_per_token": 5e-7, "output_cost_per_token": 0.000002, "max_input_tokens": 131072, "max_output_tokens": 8192, "input_cost_per_audio_token": 0.000003, "max_tokens": 8192, "output_cost_per_audio_token": 0.000012, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "tpm": 250000, "rpm": 10, "gemini_native_audio": true, "supports_web_search": true, "supports_reasoning": true, "model_id": "2.5-flash-native-audio-preview-12-2025", "model_name": "2.5 Flash Native Audio Preview 12 2025", "provider_id": "google", "provider_name": "Google", "input_cost_per_million": 0.5, "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": "realtime", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_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": 1048576, "max_output_tokens": 65536, "cache_read_input_token_cost_above_200k_tokens": 2.5e-7, "cache_read_input_token_cost_above_200k_tokens_priority": 4.5e-7, "cache_read_input_token_cost_batches": 1.25e-7, "cache_read_input_token_cost_flex": 1.25e-7, "cache_read_input_token_cost_priority": 2.25e-7, "input_cost_per_token_above_200k_tokens": 0.0000025, "input_cost_per_token_priority": 0.00000225, "input_cost_per_token_above_200k_tokens_priority": 0.0000045, "max_tokens": 65536, "output_cost_per_token_above_200k_tokens": 0.000015, "output_cost_per_token_priority": 0.000018, "output_cost_per_token_above_200k_tokens_priority": 0.000027, "rpm": 2000, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_pdf_input": true, "supports_prompt_caching": true, "prompt_cache_min_tokens": 2048, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_video_input": true, "supports_web_search": true, "tpm": 800000, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "google_maps_grounding_cost_per_query": 0.025, "input_cost_per_token_batches": 6.25e-7, "input_cost_per_token_flex": 6.25e-7, "output_cost_per_token_batches": 0.000005, "output_cost_per_token_flex": 0.000005, "supports_url_context": true, "model_id": "2.5-pro", "model_name": "2.5 Pro", "provider_id": "google", "provider_name": "Google", "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": 5e-7, "output_cost_per_token": 0.000003, "max_input_tokens": 1048576, "max_output_tokens": 65536, "cache_read_input_audio_token_cost": 1e-7, "cache_read_input_token_cost_batches": 5e-8, "cache_read_input_token_cost_flex": 5e-8, "input_cost_per_audio_token": 0.000001, "max_tokens": 65536, "output_cost_per_reasoning_token": 0.000003, "rpm": 2000, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_web_search": true, "supports_native_streaming": true, "tpm": 800000, "input_cost_per_token_priority": 9e-7, "input_cost_per_audio_token_priority": 0.0000018, "output_cost_per_token_priority": 0.0000054, "cache_read_input_token_cost_priority": 9e-8, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_audio_token_batches": 5e-7, "input_cost_per_token_batches": 2.5e-7, "input_cost_per_token_flex": 2.5e-7, "output_cost_per_token_batches": 0.0000015, "output_cost_per_token_flex": 0.0000015, "supports_audio_input": true, "model_id": "3-flash-preview", "model_name": "3 Flash Preview", "provider_id": "google", "provider_name": "Google", "input_cost_per_million": 0.5, "output_cost_per_million": 3, "cache_read_cost_per_token": 5e-8, "cache_read_cost_per_million": 0.049999999999999996, "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_vision": true, "supports_response_schema": false, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000012, "max_input_tokens": 65536, "max_output_tokens": 32768, "input_cost_per_image": 0.0011, "input_cost_per_token_batches": 0.000001, "input_cost_per_token_flex": 0.000001, "input_cost_per_token_priority": 0.0000036, "max_tokens": 32768, "output_cost_per_image": 0.134, "output_cost_per_image_token": 0.00012, "output_cost_per_image_token_batches": 0.00006, "rpm": 1000, "tpm": 4000000, "output_cost_per_token_batches": 0.000006, "output_cost_per_token_flex": 0.000006, "output_cost_per_token_priority": 0.0000216, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/images/generations", "/v1/images/edits" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_prompt_caching": false, "supports_system_messages": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", "supports_reasoning": true, "model_id": "3-pro-image", "model_name": "3 Pro Image", "provider_id": "google", "provider_name": "Google", "input_cost_per_million": 2, "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": "image", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": false, "supports_vision": true, "supports_response_schema": false, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000012, "max_input_tokens": 131072, "max_output_tokens": 32768, "deprecation_date": "2026-06-25", "input_cost_per_image": 0.0011, "input_cost_per_token_batches": 0.000001, "input_cost_per_token_flex": 0.000001, "input_cost_per_token_priority": 0.0000036, "max_tokens": 32768, "output_cost_per_image": 0.134, "output_cost_per_image_token": 0.00012, "rpm": 1000, "tpm": 4000000, "output_cost_per_token_batches": 0.000006, "output_cost_per_token_flex": 0.000006, "output_cost_per_token_priority": 0.0000216, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/images/generations", "/v1/images/edits" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_prompt_caching": true, "supports_system_messages": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", "supports_reasoning": false, "model_id": "3-pro-image-preview", "model_name": "3 Pro Image Preview", "provider_id": "google", "provider_name": "Google", "input_cost_per_million": 2, "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": "image", "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": false, "supports_vision": true, "supports_response_schema": false, "input_cost_per_token": 5e-7, "output_cost_per_token": 0.000003, "max_input_tokens": 131072, "max_output_tokens": 32768, "deprecation_date": "2026-10-29", "input_cost_per_token_batches": 2.5e-7, "max_tokens": 32768, "output_cost_per_image": 0.045, "output_cost_per_image_token": 0.00006, "output_cost_per_image_token_batches": 0.00003, "output_cost_per_token_batches": 0.0000015, "rpm": 1000, "tpm": 4000000, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/images/generations", "/v1/images/edits" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_prompt_caching": false, "supports_reasoning": true, "supports_system_messages": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", "supports_pdf_input": true, "model_id": "3.1-flash-image", "model_name": "3.1 Flash Image", "provider_id": "google", "provider_name": "Google", "input_cost_per_million": 0.5, "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": "image", "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": false, "supports_vision": true, "supports_response_schema": false, "input_cost_per_token": 5e-7, "output_cost_per_token": 0.000003, "max_input_tokens": 65536, "max_output_tokens": 65536, "deprecation_date": "2026-06-25", "input_cost_per_token_batches": 2.5e-7, "max_tokens": 65536, "output_cost_per_image": 0.045, "output_cost_per_image_token": 0.00006, "output_cost_per_token_batches": 0.0000015, "rpm": 1000, "tpm": 4000000, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/images/generations", "/v1/images/edits" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_prompt_caching": true, "supports_reasoning": false, "supports_system_messages": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", "model_id": "3.1-flash-image-preview", "model_name": "3.1 Flash Image Preview", "provider_id": "google", "provider_name": "Google", "input_cost_per_million": 0.5, "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": "image", "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": 2.5e-7, "output_cost_per_token": 0.0000015, "max_input_tokens": 1048576, "max_output_tokens": 65536, "deprecation_date": "2027-05-07", "cache_read_input_audio_token_cost": 5e-8, "cache_read_input_token_cost_batches": 1.25e-8, "cache_read_input_token_cost_flex": 1.25e-8, "cache_read_input_token_cost_priority": 4.5e-8, "input_cost_per_audio_token": 5e-7, "input_cost_per_token_batches": 1.25e-7, "input_cost_per_token_flex": 1.25e-7, "input_cost_per_token_priority": 4.5e-7, "max_tokens": 65536, "output_cost_per_reasoning_token": 0.0000015, "output_cost_per_token_batches": 7.5e-7, "output_cost_per_token_flex": 7.5e-7, "output_cost_per_token_priority": 0.0000027, "rpm": 15, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_audio_output": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_web_search": true, "supports_native_streaming": true, "tpm": 250000, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_audio_token_batches": 2.5e-7, "input_cost_per_audio_token_priority": 9e-7, "model_id": "3.1-flash-lite", "model_name": "3.1 Flash Lite", "provider_id": "google", "provider_name": "Google", "input_cost_per_million": 0.25, "output_cost_per_million": 1.5, "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": 2.5e-7, "output_cost_per_token": 0.0000015, "max_input_tokens": 1048576, "max_output_tokens": 65536, "deprecation_date": "2026-05-25", "cache_read_input_audio_token_cost": 5e-8, "cache_read_input_token_cost_batches": 1.25e-8, "cache_read_input_token_cost_flex": 1.25e-8, "cache_read_input_token_cost_priority": 4.5e-8, "input_cost_per_audio_token": 5e-7, "input_cost_per_token_batches": 1.25e-7, "input_cost_per_token_flex": 1.25e-7, "input_cost_per_token_priority": 4.5e-7, "max_tokens": 65536, "output_cost_per_reasoning_token": 0.0000015, "output_cost_per_token_batches": 7.5e-7, "output_cost_per_token_flex": 7.5e-7, "output_cost_per_token_priority": 0.0000027, "rpm": 15, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_audio_output": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_web_search": true, "supports_native_streaming": true, "tpm": 250000, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_audio_token_batches": 2.5e-7, "model_id": "3.1-flash-lite-preview", "model_name": "3.1 Flash Lite Preview", "provider_id": "google", "provider_name": "Google", "input_cost_per_million": 0.25, "output_cost_per_million": 1.5, "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_vision": true, "supports_response_schema": false, "input_cost_per_token": 7.5e-7, "output_cost_per_token": 0.0000045, "max_input_tokens": 131072, "max_output_tokens": 65536, "input_cost_per_audio_token": 0.000003, "input_cost_per_image_token": 0.000001, "input_cost_per_video_per_second": 0.000033333333333333335, "input_cost_per_video_token": 0.000001, "max_tokens": 65536, "output_cost_per_audio_token": 0.000012, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_web_search": true, "tpm": 250000, "rpm": 10, "gemini_audio_only_live": true, "input_cost_per_second": 0.0000833333333333, "supports_reasoning": true, "model_id": "3.1-flash-live-preview", "model_name": "3.1 Flash Live Preview", "provider_id": "google", "provider_name": "Google", "input_cost_per_million": 0.75, "output_cost_per_million": 4.5, "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": "realtime", "deprecation_date": null, "supports_json_mode": false, "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": 0.000012, "max_input_tokens": 1048576, "max_output_tokens": 65536, "prompt_cache_min_tokens": 4096, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "input_cost_per_token_above_200k_tokens": 0.000004, "input_cost_per_token_batches": 0.000001, "max_tokens": 65536, "output_cost_per_token_above_200k_tokens": 0.000018, "output_cost_per_token_batches": 0.000006, "rpm": 2000, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_video_input": true, "supports_web_search": true, "supports_url_context": true, "supports_native_streaming": true, "tpm": 800000, "input_cost_per_token_priority": 0.0000036, "input_cost_per_token_above_200k_tokens_priority": 0.0000072, "output_cost_per_token_priority": 0.0000216, "output_cost_per_token_above_200k_tokens_priority": 0.0000324, "cache_read_input_token_cost_priority": 3.6e-7, "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-7, "cache_read_input_token_cost_batches": 2e-7, "cache_read_input_token_cost_flex": 2e-7, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_token_flex": 0.000001, "output_cost_per_token_flex": 0.000006, "model_id": "3.1-pro-preview", "model_name": "3.1 Pro Preview", "provider_id": "google", "provider_name": "Google", "input_cost_per_million": 2, "output_cost_per_million": 12, "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": "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": 0.000012, "max_input_tokens": 1048576, "max_output_tokens": 65536, "prompt_cache_min_tokens": 4096, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "input_cost_per_token_above_200k_tokens": 0.000004, "input_cost_per_token_batches": 0.000001, "max_tokens": 65536, "output_cost_per_token_above_200k_tokens": 0.000018, "output_cost_per_token_batches": 0.000006, "rpm": 2000, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_video_input": true, "supports_web_search": true, "supports_url_context": true, "supports_native_streaming": true, "tpm": 800000, "input_cost_per_token_priority": 0.0000036, "input_cost_per_token_above_200k_tokens_priority": 0.0000072, "output_cost_per_token_priority": 0.0000216, "output_cost_per_token_above_200k_tokens_priority": 0.0000324, "cache_read_input_token_cost_priority": 3.6e-7, "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-7, "cache_read_input_token_cost_batches": 2e-7, "cache_read_input_token_cost_flex": 2e-7, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_token_flex": 0.000001, "output_cost_per_token_flex": 0.000006, "model_id": "3.1-pro-preview-customtools", "model_name": "3.1 Pro Preview Customtools", "provider_id": "google", "provider_name": "Google", "input_cost_per_million": 2, "output_cost_per_million": 12, "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": "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": 0.0000015, "output_cost_per_token": 0.000009, "max_input_tokens": 1048576, "max_output_tokens": 65536, "prompt_cache_min_tokens": 4096, "cache_read_input_token_cost_batches": 7.5e-8, "input_cost_per_audio_token": 0.0000015, "max_tokens": 65536, "output_cost_per_reasoning_token": 0.000009, "rpm": 2000, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_audio_input": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_web_search": true, "supports_native_streaming": true, "tpm": 800000, "input_cost_per_token_priority": 0.0000027, "input_cost_per_audio_token_priority": 0.0000027, "output_cost_per_token_priority": 0.0000162, "cache_read_input_token_cost_priority": 2.7e-7, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_token_batches": 7.5e-7, "output_cost_per_token_batches": 0.0000045, "input_cost_per_token_flex": 7.5e-7, "output_cost_per_token_flex": 0.0000045, "cache_read_input_token_cost_flex": 8e-8, "model_id": "3.5-flash", "model_name": "3.5 Flash", "provider_id": "google", "provider_name": "Google", "input_cost_per_million": 1.5, "output_cost_per_million": 9, "cache_read_cost_per_token": 1.5e-7, "cache_read_cost_per_million": 0.15, "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": 3e-7, "output_cost_per_token": 0.0000025, "max_input_tokens": 1048576, "max_output_tokens": 65536, "cache_read_input_token_cost_batches": 2e-8, "cache_read_input_token_cost_flex": 2e-8, "cache_read_input_token_cost_priority": 5e-8, "input_cost_per_token_batches": 1.5e-7, "input_cost_per_token_flex": 1.5e-7, "input_cost_per_token_priority": 5.4e-7, "max_tokens": 65536, "output_cost_per_reasoning_token": 0.0000025, "output_cost_per_token_batches": 0.00000125, "output_cost_per_token_flex": 0.00000125, "output_cost_per_token_priority": 0.0000045, "rpm": 15, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_audio_output": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_web_search": true, "supports_native_streaming": true, "tpm": 250000, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "model_id": "3.5-flash-lite", "model_name": "3.5 Flash Lite", "provider_id": "google", "provider_name": "Google", "input_cost_per_million": 0.3, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 3e-8, "cache_read_cost_per_million": 0.03, "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": 0.00000375, "max_input_tokens": 1048576, "max_output_tokens": 65536, "prompt_cache_min_tokens": 4096, "cache_read_input_token_cost_batches": 3.75e-8, "cache_read_input_token_cost_flex": 3.75e-8, "input_cost_per_token_batches": 3.75e-7, "input_cost_per_token_flex": 3.75e-7, "max_tokens": 65536, "output_cost_per_reasoning_token": 0.00000375, "output_cost_per_token_batches": 0.000001875, "output_cost_per_token_flex": 0.000001875, "rpm": 2000, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_audio_input": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_web_search": true, "supports_native_streaming": true, "tpm": 800000, "input_cost_per_token_priority": 0.00000135, "output_cost_per_token_priority": 0.00000675, "cache_read_input_token_cost_priority": 1.35e-7, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "model_id": "3.6-flash", "model_name": "3.6 Flash", "provider_id": "google", "provider_name": "Google", "input_cost_per_million": 0.75, "output_cost_per_million": 3.75, "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": 0.00000375, "max_input_tokens": 1048576, "max_output_tokens": 65536, "prompt_cache_min_tokens": 4096, "cache_read_input_token_cost_batches": 3.75e-8, "cache_read_input_token_cost_flex": 3.75e-8, "input_cost_per_token_batches": 3.75e-7, "input_cost_per_token_flex": 3.75e-7, "max_tokens": 65536, "output_cost_per_reasoning_token": 0.00000375, "output_cost_per_token_batches": 0.000001875, "output_cost_per_token_flex": 0.000001875, "rpm": 2000, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_audio_input": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_minimal_reasoning_effort": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_web_search": true, "supports_native_streaming": true, "tpm": 800000, "input_cost_per_token_priority": 0.00000135, "output_cost_per_token_priority": 0.00000675, "cache_read_input_token_cost_priority": 1.35e-7, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "model_id": "3.7-flash", "model_name": "3.7 Flash", "provider_id": "google", "provider_name": "Google", "input_cost_per_million": 0.75, "output_cost_per_million": 3.75, "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": 0.00000375, "max_input_tokens": 1048576, "max_output_tokens": 65536, "prompt_cache_min_tokens": 4096, "cache_read_input_token_cost_batches": 3.75e-8, "cache_read_input_token_cost_flex": 3.75e-8, "input_cost_per_token_batches": 3.75e-7, "input_cost_per_token_flex": 3.75e-7, "max_tokens": 65536, "output_cost_per_reasoning_token": 0.00000375, "output_cost_per_token_batches": 0.000001875, "output_cost_per_token_flex": 0.000001875, "rpm": 2000, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_audio_input": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_minimal_reasoning_effort": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_web_search": true, "supports_native_streaming": true, "tpm": 800000, "input_cost_per_token_priority": 0.00000135, "output_cost_per_token_priority": 0.00000675, "cache_read_input_token_cost_priority": 1.35e-7, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "model_id": "3.8-flash", "model_name": "3.8 Flash", "provider_id": "google", "provider_name": "Google", "input_cost_per_million": 0.75, "output_cost_per_million": 3.75, "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_vision": true, "supports_response_schema": false, "input_cost_per_token": 7.5e-7, "output_cost_per_token": 0.0000045, "max_input_tokens": 131072, "max_output_tokens": 65536, "input_cost_per_audio_token": 0.000003, "input_cost_per_image_token": 0.000001, "input_cost_per_video_token": 0.000001, "max_tokens": 65536, "output_cost_per_audio_token": 0.000012, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supports_audio_input": true, "tpm": 250000, "rpm": 10, "supports_web_search": true, "supports_reasoning": true, "model_id": "3.8-live", "model_name": "3.8 Live", "provider_id": "google", "provider_name": "Google", "input_cost_per_million": 0.75, "output_cost_per_million": 4.5, "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": "realtime", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": false, "input_cost_per_token": 7.5e-7, "output_cost_per_token": 0.0000045, "max_input_tokens": 131072, "max_output_tokens": 65536, "input_cost_per_audio_token": 0.000003, "input_cost_per_image_token": 0.000001, "input_cost_per_video_token": 0.000001, "max_tokens": 65536, "output_cost_per_audio_token": 0.000012, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supports_audio_input": true, "tpm": 250000, "rpm": 10, "supports_web_search": true, "supports_reasoning": true, "model_id": "3.8-live-extended-thinking", "model_name": "3.8 Live Extended Thinking", "provider_id": "google", "provider_name": "Google", "input_cost_per_million": 0.75, "output_cost_per_million": 4.5, "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": "realtime", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": false, "supports_vision": true, "supports_response_schema": false, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000012, "max_input_tokens": 1048576, "max_output_tokens": 65536, "input_cost_per_token_batches": 0.000001, "max_tokens": 65536, "rpm": 1000, "tpm": 4000000, "output_cost_per_token_batches": 0.000006, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_prompt_caching": false, "supports_system_messages": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "model_id": "deep-research-max-preview-04-2026", "model_name": "Deep Research Max Preview 04 2026", "provider_id": "google", "provider_name": "Google", "input_cost_per_million": 2, "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": false, "supports_parallel_functions": false }, { "supports_function_calling": false, "supports_vision": true, "supports_response_schema": false, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000012, "max_input_tokens": 1048576, "max_output_tokens": 65536, "input_cost_per_token_batches": 0.000001, "max_tokens": 65536, "rpm": 1000, "tpm": 4000000, "output_cost_per_token_batches": 0.000006, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_prompt_caching": false, "supports_system_messages": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "model_id": "deep-research-preview-04-2026", "model_name": "Deep Research Preview 04 2026", "provider_id": "google", "provider_name": "Google", "input_cost_per_million": 2, "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": 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": 7.5e-7, "output_cost_per_token": 0.00000375, "max_input_tokens": 1048576, "max_output_tokens": 65536, "max_tokens": 65536, "output_cost_per_reasoning_token": 0.00000375, "rpm": 15, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_web_search": true, "tpm": 250000, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "google_maps_grounding_cost_per_query": 0.014, "cache_read_input_token_cost_flex": 3.75e-8, "cache_read_input_token_cost_priority": 1.35e-7, "input_cost_per_token_batches": 3.75e-7, "input_cost_per_token_flex": 3.75e-7, "input_cost_per_token_priority": 0.00000135, "output_cost_per_token_batches": 0.000001875, "output_cost_per_token_flex": 0.000001875, "output_cost_per_token_priority": 0.00000675, "prompt_cache_min_tokens": 4096, "supports_audio_input": true, "supports_native_streaming": true, "supports_video_input": true, "web_search_billing_unit": "per_query", "model_id": "flash-latest", "model_name": "Flash Latest", "provider_id": "google", "provider_name": "Google", "input_cost_per_million": 0.75, "output_cost_per_million": 3.75, "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": 3e-7, "output_cost_per_token": 0.0000025, "max_input_tokens": 1048576, "max_output_tokens": 65536, "max_tokens": 65536, "output_cost_per_reasoning_token": 0.0000025, "rpm": 15, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_web_search": true, "tpm": 250000, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "google_maps_grounding_cost_per_query": 0.014, "cache_read_input_token_cost_flex": 2e-8, "cache_read_input_token_cost_priority": 5e-8, "input_cost_per_token_batches": 1.5e-7, "input_cost_per_token_flex": 1.5e-7, "input_cost_per_token_priority": 5.4e-7, "output_cost_per_token_batches": 0.00000125, "output_cost_per_token_flex": 0.00000125, "output_cost_per_token_priority": 0.0000045, "supports_audio_input": true, "supports_native_streaming": true, "supports_video_input": true, "web_search_billing_unit": "per_query", "model_id": "flash-lite-latest", "model_name": "Flash Lite Latest", "provider_id": "google", "provider_name": "Google", "input_cost_per_million": 0.3, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 3e-8, "cache_read_cost_per_million": 0.03, "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_vision": true, "supports_response_schema": false, "input_cost_per_token": 5e-7, "output_cost_per_token": 0.000002, "max_input_tokens": 131072, "max_output_tokens": 8192, "input_cost_per_audio_token": 0.000003, "max_tokens": 8192, "output_cost_per_audio_token": 0.000012, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "gemini_native_audio": true, "supports_web_search": true, "model_id": "gemini-2.5-flash-native-audio-preview-12-2025", "model_name": "Gemini 2.5 Flash Native Audio Preview 12 2025", "provider_id": "google", "provider_name": "Google", "input_cost_per_million": 0.5, "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": "realtime", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": false, "input_cost_per_token": 7.5e-7, "output_cost_per_token": 0.0000045, "max_input_tokens": 131072, "max_output_tokens": 65536, "input_cost_per_audio_token": 0.000003, "input_cost_per_image_token": 0.000001, "input_cost_per_video_per_second": 0.000033333333333333335, "input_cost_per_video_token": 0.000001, "max_tokens": 65536, "output_cost_per_audio_token": 0.000012, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_web_search": true, "gemini_audio_only_live": true, "input_cost_per_second": 0.0000833333333333, "model_id": "gemini-3.1-flash-live-preview", "model_name": "Gemini 3.1 Flash Live Preview", "provider_id": "google", "provider_name": "Google", "input_cost_per_million": 0.75, "output_cost_per_million": 4.5, "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": "realtime", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": false, "input_cost_per_token": 7.5e-7, "output_cost_per_token": 0.0000045, "max_input_tokens": 131072, "max_output_tokens": 65536, "input_cost_per_audio_token": 0.000003, "input_cost_per_image_token": 0.000001, "input_cost_per_video_per_second": 0.000033333333333333335, "max_tokens": 65536, "output_cost_per_audio_token": 0.000012, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_web_search": true, "gemini_audio_only_live": true, "model_id": "gemini-3.8-live", "model_name": "Gemini 3.8 Live", "provider_id": "google", "provider_name": "Google", "input_cost_per_million": 0.75, "output_cost_per_million": 4.5, "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": "realtime", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": false, "input_cost_per_token": 7.5e-7, "output_cost_per_token": 0.0000045, "max_input_tokens": 131072, "max_output_tokens": 65536, "input_cost_per_audio_token": 0.000003, "input_cost_per_image_token": 0.000001, "input_cost_per_video_per_second": 0.000033333333333333335, "max_tokens": 65536, "output_cost_per_audio_token": 0.000012, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_web_search": true, "gemini_audio_only_live": true, "supports_reasoning": true, "model_id": "gemini-3.8-live-extended-thinking", "model_name": "Gemini 3.8 Live Extended Thinking", "provider_id": "google", "provider_name": "Google", "input_cost_per_million": 0.75, "output_cost_per_million": 4.5, "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": "realtime", "deprecation_date": null, "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": 3e-7, "output_cost_per_token": 0.0000025, "max_input_tokens": 1048576, "max_output_tokens": 65535, "input_cost_per_audio_token": 0.000001, "max_tokens": 65535, "output_cost_per_reasoning_token": 0.0000025, "rpm": 100000, "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_web_search": true, "tpm": 8000000, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "model_id": "gemini-exp-1206", "model_name": "Gemini Exp (Jun 2012)", "provider_id": "google", "provider_name": "Google", "input_cost_per_million": 0.3, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 3e-8, "cache_read_cost_per_million": 0.03, "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": 0.00000375, "max_input_tokens": 1048576, "max_output_tokens": 65536, "max_tokens": 65536, "output_cost_per_reasoning_token": 0.00000375, "rpm": 100000, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_web_search": true, "tpm": 8000000, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "google_maps_grounding_cost_per_query": 0.014, "cache_read_input_token_cost_flex": 3.75e-8, "cache_read_input_token_cost_priority": 1.35e-7, "input_cost_per_token_batches": 3.75e-7, "input_cost_per_token_flex": 3.75e-7, "input_cost_per_token_priority": 0.00000135, "output_cost_per_token_batches": 0.000001875, "output_cost_per_token_flex": 0.000001875, "output_cost_per_token_priority": 0.00000675, "prompt_cache_min_tokens": 4096, "supports_audio_input": true, "supports_native_streaming": true, "supports_video_input": true, "web_search_billing_unit": "per_query", "model_id": "gemini-flash-latest", "model_name": "Gemini Flash Latest", "provider_id": "google", "provider_name": "Google", "input_cost_per_million": 0.75, "output_cost_per_million": 3.75, "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": 3e-7, "output_cost_per_token": 0.0000025, "max_input_tokens": 1048576, "max_output_tokens": 65536, "max_tokens": 65536, "output_cost_per_reasoning_token": 0.0000025, "rpm": 15, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_web_search": true, "tpm": 250000, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "google_maps_grounding_cost_per_query": 0.014, "cache_read_input_token_cost_flex": 2e-8, "cache_read_input_token_cost_priority": 5e-8, "input_cost_per_token_batches": 1.5e-7, "input_cost_per_token_flex": 1.5e-7, "input_cost_per_token_priority": 5.4e-7, "output_cost_per_token_batches": 0.00000125, "output_cost_per_token_flex": 0.00000125, "output_cost_per_token_priority": 0.0000045, "supports_audio_input": true, "supports_native_streaming": true, "supports_video_input": true, "web_search_billing_unit": "per_query", "model_id": "gemini-flash-lite-latest", "model_name": "Gemini Flash Lite Latest", "provider_id": "google", "provider_name": "Google", "input_cost_per_million": 0.3, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 3e-8, "cache_read_cost_per_million": 0.03, "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_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000012, "max_input_tokens": 1048576, "max_output_tokens": 65536, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "input_cost_per_token_above_200k_tokens": 0.000004, "max_tokens": 65536, "output_cost_per_token_above_200k_tokens": 0.000018, "rpm": 2000, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_video_input": true, "supports_web_search": true, "tpm": 800000, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "google_maps_grounding_cost_per_query": 0.014, "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-7, "cache_read_input_token_cost_priority": 3.6e-7, "input_cost_per_token_above_200k_tokens_priority": 0.0000072, "input_cost_per_token_batches": 0.000001, "input_cost_per_token_priority": 0.0000036, "output_cost_per_token_above_200k_tokens_priority": 0.0000324, "output_cost_per_token_batches": 0.000006, "output_cost_per_token_priority": 0.0000216, "prompt_cache_min_tokens": 4096, "supports_native_streaming": true, "supports_url_context": true, "web_search_billing_unit": "per_query", "cache_read_input_token_cost_flex": 2e-7, "input_cost_per_token_flex": 0.000001, "output_cost_per_token_flex": 0.000006, "model_id": "gemini-pro-latest", "model_name": "Gemini Pro Latest", "provider_id": "google", "provider_name": "Google", "input_cost_per_million": 2, "output_cost_per_million": 12, "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": "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": 5e-7, "output_cost_per_token": 0.000002, "max_input_tokens": 1048576, "max_output_tokens": 65535, "input_cost_per_audio_token": 0.000003, "max_tokens": 65535, "output_cost_per_audio_token": 0.000012, "rpm": 100000, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_pdf_input": true, "supports_prompt_caching": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_web_search": true, "tpm": 8000000, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "gemini_native_audio": true, "model_id": "live-2.5-flash-preview-native-audio-09-2025", "model_name": "Live 2.5 Flash Preview Native Audio 09 2025", "provider_id": "google", "provider_name": "Google", "input_cost_per_million": 0.5, "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": "realtime", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": false, "supports_vision": true, "supports_response_schema": false, "input_cost_per_token": 0.0000015, "output_cost_per_token": 0.0000075, "max_input_tokens": 131072, "max_output_tokens": 32768, "input_cost_per_token_batches": 7.5e-7, "max_tokens": 32768, "output_cost_per_image": 0.0336, "output_cost_per_image_token": 0.00003, "output_cost_per_token_batches": 0.00000375, "rpm": 1000, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/images/generations", "/v1/images/edits" ], "supported_modalities": [ "text", "image", "video" ], "supported_output_modalities": [ "text", "image" ], "supports_pdf_input": true, "supports_prompt_caching": false, "supports_reasoning": true, "supports_system_messages": true, "supports_web_search": true, "tpm": 4000000, "web_search_billing_unit": "per_query", "model_id": "nano-banana-2.1", "model_name": "Nano Banana 2.1", "provider_id": "google", "provider_name": "Google", "input_cost_per_million": 1.5, "output_cost_per_million": 7.5, "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": "image", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": false, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000012, "max_input_tokens": 131072, "max_output_tokens": 32768, "input_cost_per_image": 0.0011, "input_cost_per_token_batches": 0.000001, "input_cost_per_token_flex": 0.000001, "input_cost_per_token_priority": 0.0000036, "max_tokens": 32768, "output_cost_per_image": 0.134, "output_cost_per_image_token": 0.00012, "rpm": 1000, "tpm": 4000000, "output_cost_per_token_batches": 0.000006, "output_cost_per_token_flex": 0.000006, "output_cost_per_token_priority": 0.0000216, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/images/edits" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "image" ], "supports_prompt_caching": true, "supports_reasoning": false, "supports_system_messages": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", "model_id": "nano-banana-pro-preview", "model_name": "Nano Banana Pro Preview", "provider_id": "google", "provider_name": "Google", "input_cost_per_million": 2, "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": "image", "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": 0.000012, "max_input_tokens": 1048576, "max_output_tokens": 65536, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "input_cost_per_token_above_200k_tokens": 0.000004, "max_tokens": 65536, "output_cost_per_token_above_200k_tokens": 0.000018, "rpm": 2000, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_video_input": true, "supports_web_search": true, "tpm": 800000, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "google_maps_grounding_cost_per_query": 0.014, "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-7, "cache_read_input_token_cost_priority": 3.6e-7, "input_cost_per_token_above_200k_tokens_priority": 0.0000072, "input_cost_per_token_batches": 0.000001, "input_cost_per_token_priority": 0.0000036, "output_cost_per_token_above_200k_tokens_priority": 0.0000324, "output_cost_per_token_batches": 0.000006, "output_cost_per_token_priority": 0.0000216, "prompt_cache_min_tokens": 4096, "supports_native_streaming": true, "supports_url_context": true, "web_search_billing_unit": "per_query", "cache_read_input_token_cost_flex": 2e-7, "input_cost_per_token_flex": 0.000001, "output_cost_per_token_flex": 0.000006, "model_id": "pro-latest", "model_name": "Pro Latest", "provider_id": "google", "provider_name": "Google", "input_cost_per_million": 2, "output_cost_per_million": 12, "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": "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": 0.000001, "output_cost_per_token": 0.000005, "max_input_tokens": 131072, "max_output_tokens": 65536, "cache_read_input_token_cost_batches": 5e-8, "input_cost_per_audio_token": 0.000001, "input_cost_per_token_batches": 5e-7, "max_tokens": 65536, "output_cost_per_reasoning_token": 0.000005, "output_cost_per_token_batches": 0.0000025, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_audio_output": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_web_search": true, "web_search_billing_unit": "per_query", "model_id": "robotics-er-2-preview", "model_name": "Robotics Er 2 Preview", "provider_id": "google", "provider_name": "Google", "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, "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_vision": true, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000005, "max_input_tokens": 131072, "max_output_tokens": 65536, "input_cost_per_audio_token": 0.000001, "max_tokens": 65536, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.014, "search_context_size_medium": 0.014 }, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_reasoning": true, "supports_video_input": true, "supports_web_search": true, "web_search_billing_unit": "per_query", "model_id": "robotics-er-2-streaming-preview", "model_name": "Robotics Er 2 Streaming Preview", "provider_id": "google", "provider_name": "Google", "input_cost_per_million": 1, "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": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_response_schema": true, "input_cost_per_token": 7.5e-8, "output_cost_per_token": 3e-7, "max_input_tokens": 131072, "max_output_tokens": 65536, "max_tokens": 65536, "search_context_cost_per_query": { "search_context_size_high": 0.005, "search_context_size_low": 0.005, "search_context_size_medium": 0.005 }, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openai/gpt-oss-safeguard-20b", "model_name": "GPT Oss Safeguard 20B", "provider_id": "groq", "provider_name": "Groq", "input_cost_per_million": 0.075, "output_cost_per_million": 0.3, "cache_read_cost_per_token": 3.7e-8, "cache_read_cost_per_million": 0.037, "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_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00000425, "max_input_tokens": 1048576, "max_output_tokens": 131072, "max_tokens": 131072, "search_context_cost_per_query": { "search_context_size_high": 0.0025, "search_context_size_low": 0.0025, "search_context_size_medium": 0.0025 }, "source": "https://ai.developer.meta.com/docs/pricing-rate-limits", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "supported_modalities": [ "text", "image", "video" ], "supported_output_modalities": [ "text" ], "supports_minimal_reasoning_effort": 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_xhigh_reasoning_effort": true, "model_id": "meta/muse-spark-1.1", "model_name": "Muse Spark 1.1", "provider_id": "meta", "provider_name": "Meta", "input_cost_per_million": 1.25, "output_cost_per_million": 4.25, "cache_read_cost_per_token": 1.5e-7, "cache_read_cost_per_million": 0.15, "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": 0.00000425, "max_input_tokens": 1048576, "max_output_tokens": 131072, "max_tokens": 131072, "search_context_cost_per_query": { "search_context_size_high": 0.0025, "search_context_size_low": 0.0025, "search_context_size_medium": 0.0025 }, "source": "https://ai.developer.meta.com/docs/pricing-rate-limits", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "supported_modalities": [ "text", "image", "video" ], "supported_output_modalities": [ "text" ], "supports_minimal_reasoning_effort": 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_xhigh_reasoning_effort": true, "model_id": "meta/muse-spark-1.2", "model_name": "Muse Spark 1.2", "provider_id": "meta", "provider_name": "Meta", "input_cost_per_million": 1.25, "output_cost_per_million": 4.25, "cache_read_cost_per_token": 1.5e-7, "cache_read_cost_per_million": 0.15, "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": 2e-7, "max_input_tokens": 1048576, "max_output_tokens": 131072, "max_tokens": 131072, "search_context_cost_per_query": { "search_context_size_high": 0.0025, "search_context_size_low": 0.0025, "search_context_size_medium": 0.0025 }, "source": "https://ai.developer.meta.com/docs/pricing-rate-limits", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "supported_modalities": [ "text", "image", "video" ], "supported_output_modalities": [ "text" ], "supports_minimal_reasoning_effort": 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_xhigh_reasoning_effort": true, "model_id": "meta/muse-spark-1.2-contributor", "model_name": "Muse Spark 1.2 Contributor", "provider_id": "meta", "provider_name": "Meta", "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0.19999999999999998, "cache_read_cost_per_token": 2e-9, "cache_read_cost_per_million": 0.002, "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": 0.00000425, "max_input_tokens": 1048576, "max_output_tokens": 131072, "max_tokens": 131072, "search_context_cost_per_query": { "search_context_size_high": 0.0025, "search_context_size_low": 0.0025, "search_context_size_medium": 0.0025 }, "source": "https://ai.developer.meta.com/docs/pricing-rate-limits", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "supported_modalities": [ "text", "image", "video" ], "supported_output_modalities": [ "text" ], "supports_minimal_reasoning_effort": 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_xhigh_reasoning_effort": true, "model_id": "meta/muse-spark-1.3", "model_name": "Muse Spark 1.3", "provider_id": "meta", "provider_name": "Meta", "input_cost_per_million": 1.25, "output_cost_per_million": 4.25, "cache_read_cost_per_token": 1.5e-7, "cache_read_cost_per_million": 0.15, "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": 2e-7, "max_input_tokens": 1048576, "max_output_tokens": 131072, "max_tokens": 131072, "search_context_cost_per_query": { "search_context_size_high": 0.0025, "search_context_size_low": 0.0025, "search_context_size_medium": 0.0025 }, "source": "https://ai.developer.meta.com/docs/pricing-rate-limits", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/messages" ], "supported_modalities": [ "text", "image", "video" ], "supported_output_modalities": [ "text" ], "supports_minimal_reasoning_effort": 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_xhigh_reasoning_effort": true, "model_id": "meta/muse-spark-1.3-contributor", "model_name": "Muse Spark 1.3 Contributor", "provider_id": "meta", "provider_name": "Meta", "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0.19999999999999998, "cache_read_cost_per_token": 2e-9, "cache_read_cost_per_million": 0.002, "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": 400000, "max_output_tokens": 128000, "max_tokens": 128000, "reasoning_effort_levels": [ "medium" ], "source": "https://developers.openai.com/api/docs/pricing", "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, "supports_web_search": true, "model_id": "chat-latest", "model_name": "Chat Latest", "provider_id": "openai", "provider_name": "OpenAI", "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": 0.000004, "output_cost_per_token": 0.00002, "max_input_tokens": 922000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_272k_tokens": 0.00001, "cache_read_input_token_cost_above_272k_tokens": 8e-7, "input_cost_per_token_above_272k_tokens": 0.000008, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.00003, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_computer_use": true, "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, "source": "https://developers.openai.com/api/docs/models/gpt-daybreak-blue-latest", "model_id": "daybreak-blue-latest", "model_name": "Daybreak Blue Latest", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 4, "output_cost_per_million": 20, "cache_read_cost_per_token": 4e-7, "cache_read_cost_per_million": 0.39999999999999997, "cache_write_cost_per_token": 0.000005, "cache_write_cost_per_million": 5, "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": 0.0000125, "output_cost_per_token": 0.000075, "max_input_tokens": 400000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_272k_tokens": 0.00003125, "cache_read_input_token_cost_above_272k_tokens": 0.0000025, "input_cost_per_token_above_272k_tokens": 0.000025, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.0001125, "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, "supports_web_search": true, "source": "https://developers.openai.com/api/docs/models/gpt-daybreak-red-latest", "supports_computer_use": true, "model_id": "daybreak-red-latest", "model_name": "Daybreak Red Latest", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 12.5, "output_cost_per_million": 75, "cache_read_cost_per_token": 0.00000125, "cache_read_cost_per_million": 1.25, "cache_write_cost_per_token": 0.000015625, "cache_write_cost_per_million": 15.625, "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, "cache_read_input_token_cost_priority": 8.75e-7, "input_cost_per_token_batches": 0.000001, "input_cost_per_token_priority": 0.0000035, "max_tokens": 32768, "output_cost_per_token_batches": 0.000004, "output_cost_per_token_priority": 0.000014, "search_context_cost_per_query": { "search_context_size_high": 0.025, "search_context_size_low": 0.025, "search_context_size_medium": 0.025 }, "source": "https://developers.openai.com/api/docs/pricing", "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_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "gpt-4.1", "model_name": "GPT-4.1", "provider_id": "openai", "provider_name": "OpenAI", "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, "cache_read_input_token_cost_priority": 8.75e-7, "input_cost_per_token_priority": 0.0000035, "input_cost_per_token_batches": 0.000001, "max_tokens": 32768, "output_cost_per_token_priority": 0.000014, "output_cost_per_token_batches": 0.000004, "search_context_cost_per_query": { "search_context_size_high": 0.025, "search_context_size_low": 0.025, "search_context_size_medium": 0.025 }, "source": "https://developers.openai.com/api/docs/pricing", "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_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "gpt-4.1-2025-04-14", "model_name": "GPT-4.1 (Apr 2025)", "provider_id": "openai", "provider_name": "OpenAI", "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": 4e-7, "output_cost_per_token": 0.0000016, "max_input_tokens": 1047576, "max_output_tokens": 32768, "cache_read_input_token_cost_priority": 1.75e-7, "input_cost_per_token_batches": 2e-7, "input_cost_per_token_priority": 7e-7, "max_tokens": 32768, "output_cost_per_token_batches": 8e-7, "output_cost_per_token_priority": 0.0000028, "search_context_cost_per_query": { "search_context_size_high": 0.025, "search_context_size_low": 0.025, "search_context_size_medium": 0.025 }, "source": "https://developers.openai.com/api/docs/pricing", "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_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "gpt-4.1-mini", "model_name": "GPT-4.1 mini", "provider_id": "openai", "provider_name": "OpenAI", "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, "cache_read_input_token_cost_priority": 1.75e-7, "input_cost_per_token_priority": 7e-7, "input_cost_per_token_batches": 2e-7, "max_tokens": 32768, "output_cost_per_token_priority": 0.0000028, "output_cost_per_token_batches": 8e-7, "search_context_cost_per_query": { "search_context_size_high": 0.025, "search_context_size_low": 0.025, "search_context_size_medium": 0.025 }, "source": "https://developers.openai.com/api/docs/pricing", "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_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "gpt-4.1-mini-2025-04-14", "model_name": "GPT-4.1 mini (Apr 2025)", "provider_id": "openai", "provider_name": "OpenAI", "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": 1.5e-7, "output_cost_per_token": 6e-7, "max_input_tokens": 128000, "max_output_tokens": 16384, "input_cost_per_token_batches": 7.5e-8, "max_tokens": 16384, "output_cost_per_token_batches": 3e-7, "search_context_cost_per_query": { "search_context_size_high": 0.025, "search_context_size_low": 0.025, "search_context_size_medium": 0.025 }, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "gpt-4o-mini-search-preview", "model_name": "GPT-4o Mini Search Preview", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 0.15, "output_cost_per_million": 0.6, "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": 0.0000025, "output_cost_per_token": 0.00001, "max_input_tokens": 128000, "max_output_tokens": 16384, "input_cost_per_token_batches": 0.00000125, "max_tokens": 16384, "output_cost_per_token_batches": 0.000005, "search_context_cost_per_query": { "search_context_size_high": 0.025, "search_context_size_low": 0.025, "search_context_size_medium": 0.025 }, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "gpt-4o-search-preview", "model_name": "GPT-4o Search Preview", "provider_id": "openai", "provider_name": "OpenAI", "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, "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_batches": 6.25e-8, "cache_read_input_token_cost_flex": 6.25e-8, "cache_read_input_token_cost_priority": 2.5e-7, "input_cost_per_token_batches": 6.25e-7, "input_cost_per_token_flex": 6.25e-7, "input_cost_per_token_priority": 0.0000025, "max_tokens": 128000, "output_cost_per_token_batches": 0.000005, "output_cost_per_token_flex": 0.000005, "output_cost_per_token_priority": 0.00002, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://developers.openai.com/api/docs/pricing", "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, "supports_minimal_reasoning_effort": true, "model_id": "gpt-5", "model_name": "GPT-5", "provider_id": "openai", "provider_name": "OpenAI", "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, "deprecation_date": "2026-12-11", "cache_read_input_token_cost_batches": 6.25e-8, "cache_read_input_token_cost_flex": 6.25e-8, "cache_read_input_token_cost_priority": 2.5e-7, "input_cost_per_token_batches": 6.25e-7, "input_cost_per_token_flex": 6.25e-7, "input_cost_per_token_priority": 0.0000025, "max_tokens": 128000, "output_cost_per_token_batches": 0.000005, "output_cost_per_token_flex": 0.000005, "output_cost_per_token_priority": 0.00002, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://developers.openai.com/api/docs/pricing", "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, "supports_minimal_reasoning_effort": true, "model_id": "gpt-5-2025-08-07", "model_name": "GPT-5 (Aug 2025)", "provider_id": "openai", "provider_name": "OpenAI", "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", "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, "deprecation_date": "2026-07-23", "max_tokens": 128000, "source": "https://developers.openai.com/api/docs/models/gpt-5-codex", "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_tool_choice": true, "supports_web_search": true, "model_id": "gpt-5-codex", "model_name": "GPT-5 Codex", "provider_id": "openai", "provider_name": "OpenAI", "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", "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_batches": 1.25e-8, "cache_read_input_token_cost_flex": 1.25e-8, "cache_read_input_token_cost_priority": 4.5e-8, "input_cost_per_token_batches": 1.25e-7, "input_cost_per_token_flex": 1.25e-7, "input_cost_per_token_priority": 4.5e-7, "max_tokens": 128000, "output_cost_per_token_batches": 0.000001, "output_cost_per_token_flex": 0.000001, "output_cost_per_token_priority": 0.0000036, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://developers.openai.com/api/docs/pricing", "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, "supports_minimal_reasoning_effort": true, "model_id": "gpt-5-mini", "model_name": "GPT-5 Mini", "provider_id": "openai", "provider_name": "OpenAI", "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, "deprecation_date": "2026-12-11", "cache_read_input_token_cost_batches": 1.25e-8, "cache_read_input_token_cost_flex": 1.25e-8, "cache_read_input_token_cost_priority": 4.5e-8, "input_cost_per_token_batches": 1.25e-7, "input_cost_per_token_flex": 1.25e-7, "input_cost_per_token_priority": 4.5e-7, "max_tokens": 128000, "output_cost_per_token_batches": 0.000001, "output_cost_per_token_flex": 0.000001, "output_cost_per_token_priority": 0.0000036, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://developers.openai.com/api/docs/pricing", "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, "supports_minimal_reasoning_effort": true, "model_id": "gpt-5-mini-2025-08-07", "model_name": "GPT-5 Mini (Aug 2025)", "provider_id": "openai", "provider_name": "OpenAI", "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", "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, "cache_read_input_token_cost_batches": 2.5e-9, "cache_read_input_token_cost_flex": 2.5e-9, "input_cost_per_token_batches": 2.5e-8, "input_cost_per_token_flex": 2.5e-8, "input_cost_per_token_priority": 0.0000025, "max_tokens": 128000, "output_cost_per_token_batches": 2e-7, "output_cost_per_token_flex": 2e-7, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://developers.openai.com/api/docs/pricing", "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, "supports_minimal_reasoning_effort": true, "model_id": "gpt-5-nano", "model_name": "GPT-5 Nano", "provider_id": "openai", "provider_name": "OpenAI", "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, "deprecation_date": "2026-12-11", "cache_read_input_token_cost_batches": 2.5e-9, "cache_read_input_token_cost_flex": 2.5e-9, "input_cost_per_token_batches": 2.5e-8, "input_cost_per_token_priority": 0.0000025, "input_cost_per_token_flex": 2.5e-8, "max_tokens": 128000, "output_cost_per_token_batches": 2e-7, "output_cost_per_token_flex": 2e-7, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://developers.openai.com/api/docs/pricing", "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, "supports_minimal_reasoning_effort": true, "model_id": "gpt-5-nano-2025-08-07", "model_name": "GPT-5 Nano (Aug 2025)", "provider_id": "openai", "provider_name": "OpenAI", "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", "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": 400000, "max_output_tokens": 272000, "input_cost_per_token_batches": 0.0000075, "max_tokens": 272000, "output_cost_per_token_batches": 0.00006, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": false, "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, "supports_minimal_reasoning_effort": true, "model_id": "gpt-5-pro", "model_name": "GPT-5 Pro", "provider_id": "openai", "provider_name": "OpenAI", "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": 0.000015, "output_cost_per_token": 0.00012, "max_input_tokens": 400000, "max_output_tokens": 272000, "deprecation_date": "2026-12-11", "input_cost_per_token_batches": 0.0000075, "max_tokens": 272000, "output_cost_per_token_batches": 0.00006, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_native_streaming": false, "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, "supports_minimal_reasoning_effort": true, "model_id": "gpt-5-pro-2025-10-06", "model_name": "GPT-5 Pro (Oct 2025)", "provider_id": "openai", "provider_name": "OpenAI", "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", "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, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://developers.openai.com/api/docs/pricing", "supports_pdf_input": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false, "supports_minimal_reasoning_effort": true, "model_id": "gpt-5-search-api", "model_name": "GPT-5 Search API", "provider_id": "openai", "provider_name": "OpenAI", "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, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://developers.openai.com/api/docs/pricing", "supports_pdf_input": true, "supports_prompt_caching": 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": "gpt-5-search-api-2025-10-14", "model_name": "GPT-5 Search API (Oct 2025)", "provider_id": "openai", "provider_name": "OpenAI", "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, "deprecation_date": "2027-04-01", "cache_read_input_token_cost_batches": 6.25e-8, "cache_read_input_token_cost_flex": 6.25e-8, "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, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "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_web_search": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", "input_cost_per_token_batches": 6.25e-7, "input_cost_per_token_flex": 6.25e-7, "output_cost_per_token_batches": 0.000005, "output_cost_per_token_flex": 0.000005, "source": "https://developers.openai.com/api/docs/pricing", "supports_xhigh_reasoning_effort": false, "supports_minimal_reasoning_effort": false, "model_id": "gpt-5.1", "model_name": "GPT-5.1", "provider_id": "openai", "provider_name": "OpenAI", "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", "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_batches": 6.25e-8, "cache_read_input_token_cost_flex": 6.25e-8, "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, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "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_web_search": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", "input_cost_per_token_batches": 6.25e-7, "input_cost_per_token_flex": 6.25e-7, "output_cost_per_token_batches": 0.000005, "output_cost_per_token_flex": 0.000005, "source": "https://developers.openai.com/api/docs/pricing", "supports_xhigh_reasoning_effort": false, "supports_minimal_reasoning_effort": false, "model_id": "gpt-5.1-2025-11-13", "model_name": "GPT-5.1 (Nov 2025)", "provider_id": "openai", "provider_name": "OpenAI", "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": 400000, "max_output_tokens": 128000, "deprecation_date": "2026-07-23", "max_tokens": 128000, "source": "https://developers.openai.com/api/docs/models/gpt-5.1-codex", "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_tool_choice": true, "supports_web_search": true, "model_id": "gpt-5.1-codex", "model_name": "GPT-5.1 Codex", "provider_id": "openai", "provider_name": "OpenAI", "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", "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": 400000, "max_output_tokens": 128000, "deprecation_date": "2026-07-23", "max_tokens": 128000, "source": "https://developers.openai.com/api/docs/models/gpt-5.1-codex-max", "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_tool_choice": true, "supports_web_search": true, "model_id": "gpt-5.1-codex-max", "model_name": "GPT-5.1 Codex Max", "provider_id": "openai", "provider_name": "OpenAI", "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", "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_batches": 8.75e-8, "cache_read_input_token_cost_flex": 8.75e-8, "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, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "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_web_search": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", "input_cost_per_token_batches": 8.75e-7, "input_cost_per_token_flex": 8.75e-7, "output_cost_per_token_batches": 0.000007, "output_cost_per_token_flex": 0.000007, "source": "https://developers.openai.com/api/docs/pricing", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "model_id": "gpt-5.2", "model_name": "GPT-5.2", "provider_id": "openai", "provider_name": "OpenAI", "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_batches": 8.75e-8, "cache_read_input_token_cost_flex": 8.75e-8, "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, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "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_web_search": true, "supports_none_reasoning_effort": true, "default_reasoning_effort": "none", "input_cost_per_token_batches": 8.75e-7, "input_cost_per_token_flex": 8.75e-7, "output_cost_per_token_batches": 0.000007, "output_cost_per_token_flex": 0.000007, "source": "https://developers.openai.com/api/docs/pricing", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "model_id": "gpt-5.2-2025-12-11", "model_name": "GPT-5.2 (Dec 2025)", "provider_id": "openai", "provider_name": "OpenAI", "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, "deprecation_date": "2026-07-23", "max_tokens": 128000, "source": "https://developers.openai.com/api/docs/models/gpt-5.2-codex", "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_tool_choice": true, "supports_web_search": true, "model_id": "gpt-5.2-codex", "model_name": "GPT-5.2 Codex", "provider_id": "openai", "provider_name": "OpenAI", "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", "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, "input_cost_per_token_batches": 0.0000105, "max_tokens": 128000, "output_cost_per_token_batches": 0.000084, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://developers.openai.com/api/docs/pricing", "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": "gpt-5.2-pro", "model_name": "GPT-5.2 Pro", "provider_id": "openai", "provider_name": "OpenAI", "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, "input_cost_per_token_batches": 0.0000105, "max_tokens": 128000, "output_cost_per_token_batches": 0.000084, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://developers.openai.com/api/docs/pricing", "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": "gpt-5.2-pro-2025-12-11", "model_name": "GPT-5.2 Pro (Dec 2025)", "provider_id": "openai", "provider_name": "OpenAI", "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": 272000, "max_output_tokens": 128000, "deprecation_date": "2027-04-01", "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, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://developers.openai.com/api/docs/pricing", "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, "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false, "supports_minimal_reasoning_effort": true, "model_id": "gpt-5.3-codex", "model_name": "GPT-5.3 Codex", "provider_id": "openai", "provider_name": "OpenAI", "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", "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": 272000, "max_output_tokens": 128000, "cache_read_input_token_cost_batches": 3.75e-8, "cache_read_input_token_cost_flex": 3.75e-8, "cache_read_input_token_cost_priority": 1.5e-7, "input_cost_per_token_flex": 3.75e-7, "input_cost_per_token_batches": 3.75e-7, "input_cost_per_token_priority": 0.0000015, "max_tokens": 128000, "output_cost_per_token_flex": 0.00000225, "output_cost_per_token_batches": 0.00000225, "output_cost_per_token_priority": 0.000009, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "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, "default_reasoning_effort": "none", "source": "https://developers.openai.com/api/docs/pricing", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "model_id": "gpt-5.4-mini", "model_name": "GPT-5.4 Mini", "provider_id": "openai", "provider_name": "OpenAI", "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": 272000, "max_output_tokens": 128000, "cache_read_input_token_cost_batches": 3.75e-8, "cache_read_input_token_cost_flex": 3.75e-8, "cache_read_input_token_cost_priority": 1.5e-7, "input_cost_per_token_flex": 3.75e-7, "input_cost_per_token_batches": 3.75e-7, "input_cost_per_token_priority": 0.0000015, "max_tokens": 128000, "output_cost_per_token_flex": 0.00000225, "output_cost_per_token_batches": 0.00000225, "output_cost_per_token_priority": 0.000009, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "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, "default_reasoning_effort": "none", "source": "https://developers.openai.com/api/docs/pricing", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "model_id": "gpt-5.4-mini-2026-03-17", "model_name": "GPT-5.4 Mini (Mar 2026)", "provider_id": "openai", "provider_name": "OpenAI", "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": 272000, "max_output_tokens": 128000, "deprecation_date": "2027-04-01", "cache_read_input_token_cost_batches": 1e-8, "cache_read_input_token_cost_flex": 1e-8, "input_cost_per_token_flex": 1e-7, "input_cost_per_token_batches": 1e-7, "max_tokens": 128000, "output_cost_per_token_flex": 6.25e-7, "output_cost_per_token_batches": 6.25e-7, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "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, "default_reasoning_effort": "none", "source": "https://developers.openai.com/api/docs/pricing", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "model_id": "gpt-5.4-nano", "model_name": "GPT-5.4 Nano", "provider_id": "openai", "provider_name": "OpenAI", "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", "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": 272000, "max_output_tokens": 128000, "cache_read_input_token_cost_batches": 1e-8, "cache_read_input_token_cost_flex": 1e-8, "input_cost_per_token_flex": 1e-7, "input_cost_per_token_batches": 1e-7, "max_tokens": 128000, "output_cost_per_token_flex": 6.25e-7, "output_cost_per_token_batches": 6.25e-7, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "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, "default_reasoning_effort": "none", "source": "https://developers.openai.com/api/docs/pricing", "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "model_id": "gpt-5.4-nano-2026-03-17", "model_name": "GPT-5.4 Nano (Mar 2026)", "provider_id": "openai", "provider_name": "OpenAI", "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, "input_cost_per_token_above_272k_tokens": 0.00006, "input_cost_per_token_flex": 0.000015, "input_cost_per_token_batches": 0.000015, "input_cost_per_token_above_272k_tokens_batches": 0.00003, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.00027, "output_cost_per_token_flex": 0.00009, "output_cost_per_token_batches": 0.00009, "output_cost_per_token_above_272k_tokens_batches": 0.000135, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/responses", "/v1/batch" ], "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, "input_cost_per_token_above_272k_tokens_flex": 0.00003, "output_cost_per_token_above_272k_tokens_flex": 0.000135, "source": "https://developers.openai.com/api/docs/pricing", "model_id": "gpt-5.4-pro", "model_name": "GPT-5.4 Pro", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 30, "output_cost_per_million": 180, "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": 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, "input_cost_per_token_above_272k_tokens": 0.00006, "input_cost_per_token_flex": 0.000015, "input_cost_per_token_batches": 0.000015, "input_cost_per_token_above_272k_tokens_batches": 0.00003, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.00027, "output_cost_per_token_flex": 0.00009, "output_cost_per_token_batches": 0.00009, "output_cost_per_token_above_272k_tokens_batches": 0.000135, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/responses", "/v1/batch" ], "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, "input_cost_per_token_above_272k_tokens_flex": 0.00003, "output_cost_per_token_above_272k_tokens_flex": 0.000135, "source": "https://developers.openai.com/api/docs/pricing", "model_id": "gpt-5.4-pro-2026-03-05", "model_name": "GPT-5.4 Pro (Mar 2026)", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 30, "output_cost_per_million": 180, "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": 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_batches": 2.5e-7, "cache_read_input_token_cost_above_272k_tokens_batches": 5e-7, "cache_read_input_token_cost_flex": 2.5e-7, "cache_read_input_token_cost_priority": 0.00000125, "input_cost_per_token_above_272k_tokens": 0.00001, "input_cost_per_token_flex": 0.0000025, "input_cost_per_token_batches": 0.0000025, "input_cost_per_token_above_272k_tokens_batches": 0.000005, "input_cost_per_token_priority": 0.0000125, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.000045, "output_cost_per_token_flex": 0.000015, "output_cost_per_token_batches": 0.000015, "output_cost_per_token_above_272k_tokens_batches": 0.0000225, "output_cost_per_token_priority": 0.000075, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "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, "input_cost_per_token_above_272k_tokens_flex": 0.000005, "output_cost_per_token_above_272k_tokens_flex": 0.0000225, "cache_read_input_token_cost_above_272k_tokens_flex": 5e-7, "source": "https://developers.openai.com/api/docs/pricing", "model_id": "gpt-5.5", "model_name": "GPT-5.5", "provider_id": "openai", "provider_name": "OpenAI", "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_batches": 2.5e-7, "cache_read_input_token_cost_above_272k_tokens_batches": 5e-7, "cache_read_input_token_cost_flex": 2.5e-7, "cache_read_input_token_cost_priority": 0.00000125, "input_cost_per_token_above_272k_tokens": 0.00001, "input_cost_per_token_flex": 0.0000025, "input_cost_per_token_batches": 0.0000025, "input_cost_per_token_above_272k_tokens_batches": 0.000005, "input_cost_per_token_priority": 0.0000125, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.000045, "output_cost_per_token_flex": 0.000015, "output_cost_per_token_batches": 0.000015, "output_cost_per_token_above_272k_tokens_batches": 0.0000225, "output_cost_per_token_priority": 0.000075, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "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, "input_cost_per_token_above_272k_tokens_flex": 0.000005, "output_cost_per_token_above_272k_tokens_flex": 0.0000225, "cache_read_input_token_cost_above_272k_tokens_flex": 5e-7, "source": "https://developers.openai.com/api/docs/pricing", "model_id": "gpt-5.5-2026-04-23", "model_name": "GPT-5.5 (Apr 2026)", "provider_id": "openai", "provider_name": "OpenAI", "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, "input_cost_per_token_above_272k_tokens": 0.00006, "input_cost_per_token_flex": 0.000015, "input_cost_per_token_batches": 0.000015, "input_cost_per_token_above_272k_tokens_batches": 0.00003, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.00027, "output_cost_per_token_flex": 0.00009, "output_cost_per_token_batches": 0.00009, "output_cost_per_token_above_272k_tokens_batches": 0.000135, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/responses", "/v1/batch" ], "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": "gpt-5.5-pro", "model_name": "GPT-5.5 Pro", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 30, "output_cost_per_million": 180, "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": 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, "input_cost_per_token_above_272k_tokens": 0.00006, "input_cost_per_token_flex": 0.000015, "input_cost_per_token_batches": 0.000015, "input_cost_per_token_above_272k_tokens_batches": 0.00003, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.00027, "output_cost_per_token_flex": 0.00009, "output_cost_per_token_batches": 0.00009, "output_cost_per_token_above_272k_tokens_batches": 0.000135, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/responses", "/v1/batch" ], "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": "gpt-5.5-pro-2026-04-23", "model_name": "GPT-5.5 Pro (Apr 2026)", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 30, "output_cost_per_million": 180, "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": 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": 0.000004, "output_cost_per_token": 0.00002, "max_input_tokens": 922000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_272k_tokens": 0.00001, "cache_creation_input_token_cost_above_272k_tokens_flex": 0.000005, "cache_creation_input_token_cost_above_272k_tokens_priority": 0.00002, "cache_creation_input_token_cost_flex": 0.0000025, "cache_creation_input_token_cost_priority": 0.00001, "cache_read_input_token_cost_above_272k_tokens": 8e-7, "cache_read_input_token_cost_above_272k_tokens_flex": 4e-7, "cache_read_input_token_cost_above_272k_tokens_priority": 0.0000016, "cache_read_input_token_cost_batches": 2e-7, "cache_read_input_token_cost_above_272k_tokens_batches": 4e-7, "cache_creation_input_token_cost_batches": 0.0000025, "cache_creation_input_token_cost_above_272k_tokens_batches": 0.000005, "cache_read_input_token_cost_flex": 2e-7, "cache_read_input_token_cost_priority": 8e-7, "input_cost_per_token_above_272k_tokens": 0.000008, "input_cost_per_token_above_272k_tokens_flex": 0.000004, "input_cost_per_token_above_272k_tokens_priority": 0.000016, "input_cost_per_token_batches": 0.000002, "input_cost_per_token_above_272k_tokens_batches": 0.000004, "input_cost_per_token_flex": 0.000002, "input_cost_per_token_priority": 0.000008, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.00003, "output_cost_per_token_above_272k_tokens_flex": 0.000015, "output_cost_per_token_above_272k_tokens_priority": 0.00006, "output_cost_per_token_batches": 0.00001, "output_cost_per_token_above_272k_tokens_batches": 0.000015, "output_cost_per_token_flex": 0.00001, "output_cost_per_token_priority": 0.00004, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, "supports_none_reasoning_effort": true, "supports_pdf_input": true, "supports_prompt_cache_breakpoint": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true, "model_id": "gpt-5.6", "model_name": "GPT-5.6", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 4, "output_cost_per_million": 20, "cache_read_cost_per_token": 4e-7, "cache_read_cost_per_million": 0.39999999999999997, "cache_write_cost_per_token": 0.000005, "cache_write_cost_per_million": 5, "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": 0.0000125, "output_cost_per_token": 0.000075, "max_input_tokens": 400000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_272k_tokens": 0.00003125, "cache_read_input_token_cost_above_272k_tokens": 0.0000025, "input_cost_per_token_above_272k_tokens": 0.000025, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.0001125, "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, "supports_web_search": true, "source": "https://developers.openai.com/api/docs/pricing", "supports_computer_use": true, "model_id": "gpt-5.6-cyber", "model_name": "GPT-5.6 Cyber", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 12.5, "output_cost_per_million": 75, "cache_read_cost_per_token": 0.00000125, "cache_read_cost_per_million": 1.25, "cache_write_cost_per_token": 0.000015625, "cache_write_cost_per_million": 15.625, "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": 0.0000012, "max_input_tokens": 922000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_272k_tokens": 5e-7, "cache_creation_input_token_cost_above_272k_tokens_flex": 2.5e-7, "cache_creation_input_token_cost_above_272k_tokens_priority": 0.000001, "cache_creation_input_token_cost_flex": 1.25e-7, "cache_creation_input_token_cost_priority": 5e-7, "cache_read_input_token_cost_above_272k_tokens": 4e-8, "cache_read_input_token_cost_above_272k_tokens_flex": 2e-8, "cache_read_input_token_cost_above_272k_tokens_priority": 8e-8, "cache_read_input_token_cost_batches": 1e-8, "cache_read_input_token_cost_above_272k_tokens_batches": 2e-8, "cache_creation_input_token_cost_batches": 1.25e-7, "cache_creation_input_token_cost_above_272k_tokens_batches": 2.5e-7, "cache_read_input_token_cost_flex": 1e-8, "cache_read_input_token_cost_priority": 4e-8, "input_cost_per_token_above_272k_tokens": 4e-7, "input_cost_per_token_above_272k_tokens_flex": 2e-7, "input_cost_per_token_above_272k_tokens_priority": 8e-7, "input_cost_per_token_batches": 1e-7, "input_cost_per_token_above_272k_tokens_batches": 2e-7, "input_cost_per_token_flex": 1e-7, "input_cost_per_token_priority": 4e-7, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.0000018, "output_cost_per_token_above_272k_tokens_flex": 9e-7, "output_cost_per_token_above_272k_tokens_priority": 0.0000036, "output_cost_per_token_batches": 6e-7, "output_cost_per_token_above_272k_tokens_batches": 9e-7, "output_cost_per_token_flex": 6e-7, "output_cost_per_token_priority": 0.0000024, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, "supports_none_reasoning_effort": true, "supports_pdf_input": true, "supports_prompt_cache_breakpoint": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true, "model_id": "gpt-5.6-luna", "model_name": "GPT-5.6 Luna", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 0.19999999999999998, "output_cost_per_million": 1.2, "cache_read_cost_per_token": 2e-8, "cache_read_cost_per_million": 0.02, "cache_write_cost_per_token": 2.5e-7, "cache_write_cost_per_million": 0.25, "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": 0.000004, "output_cost_per_token": 0.00002, "max_input_tokens": 922000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_272k_tokens": 0.00001, "cache_creation_input_token_cost_above_272k_tokens_flex": 0.000005, "cache_creation_input_token_cost_above_272k_tokens_priority": 0.00002, "cache_creation_input_token_cost_flex": 0.0000025, "cache_creation_input_token_cost_priority": 0.00001, "cache_read_input_token_cost_above_272k_tokens": 8e-7, "cache_read_input_token_cost_above_272k_tokens_flex": 4e-7, "cache_read_input_token_cost_above_272k_tokens_priority": 0.0000016, "cache_read_input_token_cost_batches": 2e-7, "cache_read_input_token_cost_above_272k_tokens_batches": 4e-7, "cache_creation_input_token_cost_batches": 0.0000025, "cache_creation_input_token_cost_above_272k_tokens_batches": 0.000005, "cache_read_input_token_cost_flex": 2e-7, "cache_read_input_token_cost_priority": 8e-7, "input_cost_per_token_above_272k_tokens": 0.000008, "input_cost_per_token_above_272k_tokens_flex": 0.000004, "input_cost_per_token_above_272k_tokens_priority": 0.000016, "input_cost_per_token_batches": 0.000002, "input_cost_per_token_above_272k_tokens_batches": 0.000004, "input_cost_per_token_flex": 0.000002, "input_cost_per_token_priority": 0.000008, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.00003, "output_cost_per_token_above_272k_tokens_flex": 0.000015, "output_cost_per_token_above_272k_tokens_priority": 0.00006, "output_cost_per_token_batches": 0.00001, "output_cost_per_token_above_272k_tokens_batches": 0.000015, "output_cost_per_token_flex": 0.00001, "output_cost_per_token_priority": 0.00004, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_computer_use": true, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, "supports_none_reasoning_effort": true, "supports_pdf_input": true, "supports_prompt_cache_breakpoint": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true, "model_id": "gpt-5.6-sol", "model_name": "GPT-5.6 Sol", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 4, "output_cost_per_million": 20, "cache_read_cost_per_token": 4e-7, "cache_read_cost_per_million": 0.39999999999999997, "cache_write_cost_per_token": 0.000005, "cache_write_cost_per_million": 5, "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": 0.000012, "max_input_tokens": 922000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_272k_tokens": 0.000005, "cache_creation_input_token_cost_above_272k_tokens_flex": 0.0000025, "cache_creation_input_token_cost_above_272k_tokens_priority": 0.00001, "cache_creation_input_token_cost_flex": 0.00000125, "cache_creation_input_token_cost_priority": 0.000005, "cache_read_input_token_cost_above_272k_tokens": 4e-7, "cache_read_input_token_cost_above_272k_tokens_flex": 2e-7, "cache_read_input_token_cost_above_272k_tokens_priority": 8e-7, "cache_read_input_token_cost_batches": 1e-7, "cache_read_input_token_cost_above_272k_tokens_batches": 2e-7, "cache_creation_input_token_cost_batches": 0.00000125, "cache_creation_input_token_cost_above_272k_tokens_batches": 0.0000025, "cache_read_input_token_cost_flex": 1e-7, "cache_read_input_token_cost_priority": 4e-7, "input_cost_per_token_above_272k_tokens": 0.000004, "input_cost_per_token_above_272k_tokens_flex": 0.000002, "input_cost_per_token_above_272k_tokens_priority": 0.000008, "input_cost_per_token_batches": 0.000001, "input_cost_per_token_above_272k_tokens_batches": 0.000002, "input_cost_per_token_flex": 0.000001, "input_cost_per_token_priority": 0.000004, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.000018, "output_cost_per_token_above_272k_tokens_flex": 0.000009, "output_cost_per_token_above_272k_tokens_priority": 0.000036, "output_cost_per_token_batches": 0.000006, "output_cost_per_token_above_272k_tokens_batches": 0.000009, "output_cost_per_token_flex": 0.000006, "output_cost_per_token_priority": 0.000024, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, "supports_none_reasoning_effort": true, "supports_pdf_input": true, "supports_prompt_cache_breakpoint": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true, "model_id": "gpt-5.6-terra", "model_name": "GPT-5.6 Terra", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 2, "output_cost_per_million": 12, "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": true }, { "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": 0.00005, "max_input_tokens": 922000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_272k_tokens": 0.000025, "cache_creation_input_token_cost_above_272k_tokens_flex": 0.0000125, "cache_creation_input_token_cost_above_272k_tokens_priority": 0.00005, "cache_creation_input_token_cost_flex": 0.00000625, "cache_creation_input_token_cost_priority": 0.000025, "cache_read_input_token_cost_above_272k_tokens": 0.000002, "cache_read_input_token_cost_above_272k_tokens_flex": 0.000001, "cache_read_input_token_cost_above_272k_tokens_priority": 0.000004, "cache_read_input_token_cost_batches": 5e-7, "cache_read_input_token_cost_above_272k_tokens_batches": 0.000001, "cache_creation_input_token_cost_batches": 0.00000625, "cache_creation_input_token_cost_above_272k_tokens_batches": 0.0000125, "cache_creation_input_token_cost_above_272k_tokens_ultrafast": 0.00015, "cache_creation_input_token_cost_ultrafast": 0.000075, "cache_read_input_token_cost_above_272k_tokens_ultrafast": 0.000012, "cache_read_input_token_cost_flex": 5e-7, "cache_read_input_token_cost_priority": 0.000002, "cache_read_input_token_cost_ultrafast": 0.000006, "input_cost_per_token_above_272k_tokens": 0.00002, "input_cost_per_token_above_272k_tokens_flex": 0.00001, "input_cost_per_token_above_272k_tokens_priority": 0.00004, "input_cost_per_token_batches": 0.000005, "input_cost_per_token_above_272k_tokens_batches": 0.00001, "input_cost_per_token_above_272k_tokens_ultrafast": 0.00012, "input_cost_per_token_flex": 0.000005, "input_cost_per_token_priority": 0.00002, "input_cost_per_token_ultrafast": 0.00006, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.000075, "output_cost_per_token_above_272k_tokens_flex": 0.0000375, "output_cost_per_token_above_272k_tokens_priority": 0.00015, "output_cost_per_token_batches": 0.000025, "output_cost_per_token_above_272k_tokens_batches": 0.0000375, "output_cost_per_token_above_272k_tokens_ultrafast": 0.00045, "output_cost_per_token_flex": 0.000025, "output_cost_per_token_priority": 0.0001, "output_cost_per_token_ultrafast": 0.0003, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_computer_use": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, "supports_none_reasoning_effort": false, "supports_pdf_input": true, "supports_prompt_cache_breakpoint": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true, "model_id": "gpt-6-astra", "model_name": "GPT-6 Astra", "provider_id": "openai", "provider_name": "OpenAI", "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": 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": 5e-7, "max_input_tokens": 922000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_272k_tokens": 2.5e-7, "cache_creation_input_token_cost_above_272k_tokens_flex": 1.25e-7, "cache_creation_input_token_cost_above_272k_tokens_priority": 5e-7, "cache_creation_input_token_cost_flex": 6.25e-8, "cache_creation_input_token_cost_priority": 2.5e-7, "cache_read_input_token_cost_above_272k_tokens": 2e-8, "cache_read_input_token_cost_above_272k_tokens_flex": 1e-8, "cache_read_input_token_cost_above_272k_tokens_priority": 4e-8, "cache_read_input_token_cost_batches": 5e-9, "cache_read_input_token_cost_above_272k_tokens_batches": 1e-8, "cache_creation_input_token_cost_batches": 6.25e-8, "cache_creation_input_token_cost_above_272k_tokens_batches": 1.25e-7, "cache_read_input_token_cost_flex": 5e-9, "cache_read_input_token_cost_priority": 2e-8, "input_cost_per_token_above_272k_tokens": 2e-7, "input_cost_per_token_above_272k_tokens_flex": 1e-7, "input_cost_per_token_above_272k_tokens_priority": 4e-7, "input_cost_per_token_batches": 5e-8, "input_cost_per_token_above_272k_tokens_batches": 1e-7, "input_cost_per_token_flex": 5e-8, "input_cost_per_token_priority": 2e-7, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 7.5e-7, "output_cost_per_token_above_272k_tokens_flex": 3.75e-7, "output_cost_per_token_above_272k_tokens_priority": 0.0000015, "output_cost_per_token_batches": 2.5e-7, "output_cost_per_token_above_272k_tokens_batches": 3.75e-7, "output_cost_per_token_flex": 2.5e-7, "output_cost_per_token_priority": 0.000001, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses", "/v1/decisions" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_computer_use": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, "supports_none_reasoning_effort": true, "supports_pdf_input": true, "supports_prompt_cache_breakpoint": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true, "model_id": "gpt-6-luna", "model_name": "GPT-6 Luna", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0.5, "cache_read_cost_per_token": 1e-8, "cache_read_cost_per_million": 0.01, "cache_write_cost_per_token": 1.25e-7, "cache_write_cost_per_million": 0.125, "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": 0.00001, "max_input_tokens": 922000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_272k_tokens": 0.000005, "cache_creation_input_token_cost_above_272k_tokens_flex": 0.0000025, "cache_creation_input_token_cost_above_272k_tokens_priority": 0.00001, "cache_creation_input_token_cost_flex": 0.00000125, "cache_creation_input_token_cost_priority": 0.000005, "cache_read_input_token_cost_above_272k_tokens": 4e-7, "cache_read_input_token_cost_above_272k_tokens_flex": 2e-7, "cache_read_input_token_cost_above_272k_tokens_priority": 8e-7, "cache_read_input_token_cost_batches": 1e-7, "cache_read_input_token_cost_above_272k_tokens_batches": 2e-7, "cache_creation_input_token_cost_batches": 0.00000125, "cache_creation_input_token_cost_above_272k_tokens_batches": 0.0000025, "cache_read_input_token_cost_flex": 1e-7, "cache_read_input_token_cost_priority": 4e-7, "input_cost_per_token_above_272k_tokens": 0.000004, "input_cost_per_token_above_272k_tokens_flex": 0.000002, "input_cost_per_token_above_272k_tokens_priority": 0.000008, "input_cost_per_token_batches": 0.000001, "input_cost_per_token_above_272k_tokens_batches": 0.000002, "input_cost_per_token_flex": 0.000001, "input_cost_per_token_priority": 0.000004, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.000015, "output_cost_per_token_above_272k_tokens_flex": 0.0000075, "output_cost_per_token_above_272k_tokens_priority": 0.00003, "output_cost_per_token_batches": 0.000005, "output_cost_per_token_above_272k_tokens_batches": 0.0000075, "output_cost_per_token_flex": 0.000005, "output_cost_per_token_priority": 0.00002, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_computer_use": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, "supports_none_reasoning_effort": true, "supports_pdf_input": true, "supports_prompt_cache_breakpoint": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true, "model_id": "gpt-6-sol", "model_name": "GPT-6 Sol", "provider_id": "openai", "provider_name": "OpenAI", "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": 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": 0.00001, "max_input_tokens": 922000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_272k_tokens": 0.000005, "cache_creation_input_token_cost_above_272k_tokens_batches": 0.0000025, "cache_creation_input_token_cost_above_272k_tokens_flex": 0.0000025, "cache_creation_input_token_cost_above_272k_tokens_priority": 0.00001, "cache_creation_input_token_cost_batches": 0.00000125, "cache_creation_input_token_cost_flex": 0.00000125, "cache_creation_input_token_cost_priority": 0.000005, "cache_read_input_token_cost_above_272k_tokens": 2e-7, "cache_read_input_token_cost_above_272k_tokens_batches": 1e-7, "cache_read_input_token_cost_above_272k_tokens_flex": 1e-7, "cache_read_input_token_cost_above_272k_tokens_priority": 4e-7, "cache_read_input_token_cost_batches": 5e-8, "cache_read_input_token_cost_flex": 5e-8, "cache_read_input_token_cost_priority": 2e-7, "input_cost_per_token_above_272k_tokens": 0.000004, "input_cost_per_token_above_272k_tokens_batches": 0.000002, "input_cost_per_token_above_272k_tokens_flex": 0.000002, "input_cost_per_token_above_272k_tokens_priority": 0.000008, "input_cost_per_token_batches": 0.000001, "input_cost_per_token_flex": 0.000001, "input_cost_per_token_priority": 0.000004, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.000015, "output_cost_per_token_above_272k_tokens_batches": 0.0000075, "output_cost_per_token_above_272k_tokens_flex": 0.0000075, "output_cost_per_token_above_272k_tokens_priority": 0.00003, "output_cost_per_token_batches": 0.000005, "output_cost_per_token_flex": 0.000005, "output_cost_per_token_priority": 0.00002, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_computer_use": true, "supports_max_reasoning_effort": true, "supports_minimal_reasoning_effort": false, "supports_native_streaming": true, "supports_none_reasoning_effort": false, "supports_pdf_input": true, "supports_prompt_cache_breakpoint": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "supports_xhigh_reasoning_effort": true, "model_id": "gpt-6.1-sol", "model_name": "GPT-6.1 Sol", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 2, "output_cost_per_million": 10, "cache_read_cost_per_token": 1e-7, "cache_read_cost_per_million": 0.09999999999999999, "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": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000004, "output_cost_per_token": 0.00002, "max_input_tokens": 922000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_272k_tokens": 0.00001, "cache_read_input_token_cost_above_272k_tokens": 8e-7, "input_cost_per_token_above_272k_tokens": 0.000008, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.00003, "supported_endpoints": [ "/v1/responses" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_computer_use": true, "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, "source": "https://developers.openai.com/api/docs/models/gpt-daybreak-blue-latest", "model_id": "gpt-daybreak-blue-latest", "model_name": "GPT Daybreak Blue Latest", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 4, "output_cost_per_million": 20, "cache_read_cost_per_token": 4e-7, "cache_read_cost_per_million": 0.39999999999999997, "cache_write_cost_per_token": 0.000005, "cache_write_cost_per_million": 5, "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": 0.0000125, "output_cost_per_token": 0.000075, "max_input_tokens": 400000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_272k_tokens": 0.00003125, "cache_read_input_token_cost_above_272k_tokens": 0.0000025, "input_cost_per_token_above_272k_tokens": 0.000025, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.0001125, "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, "supports_web_search": true, "source": "https://developers.openai.com/api/docs/models/gpt-daybreak-red-latest", "supports_computer_use": true, "model_id": "gpt-daybreak-red-latest", "model_name": "GPT Daybreak Red Latest", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 12.5, "output_cost_per_million": 75, "cache_read_cost_per_token": 0.00000125, "cache_read_cost_per_million": 1.25, "cache_write_cost_per_token": 0.000015625, "cache_write_cost_per_million": 15.625, "model_type": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "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, "cache_read_input_token_cost_flex": 2.5e-7, "cache_read_input_token_cost_priority": 8.75e-7, "input_cost_per_token_batches": 0.000001, "input_cost_per_token_flex": 0.000001, "input_cost_per_token_priority": 0.0000035, "max_tokens": 100000, "output_cost_per_token_batches": 0.000004, "output_cost_per_token_flex": 0.000004, "output_cost_per_token_priority": 0.000014, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/responses", "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "o3", "model_name": "o3", "provider_id": "openai", "provider_name": "OpenAI", "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": "2026-12-11", "cache_read_input_token_cost_flex": 2.5e-7, "cache_read_input_token_cost_priority": 8.75e-7, "input_cost_per_token_batches": 0.000001, "input_cost_per_token_flex": 0.000001, "input_cost_per_token_priority": 0.0000035, "max_tokens": 100000, "output_cost_per_token_batches": 0.000004, "output_cost_per_token_flex": 0.000004, "output_cost_per_token_priority": 0.000014, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/responses", "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "o3-2025-04-16", "model_name": "o3 (Apr 2025)", "provider_id": "openai", "provider_name": "OpenAI", "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": 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, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/responses", "/v1/batch" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "o3-pro", "model_name": "o3 Pro", "provider_id": "openai", "provider_name": "OpenAI", "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, "deprecation_date": "2026-12-11", "input_cost_per_token_batches": 0.00001, "max_tokens": 100000, "output_cost_per_token_batches": 0.00004, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://developers.openai.com/api/docs/pricing", "supported_endpoints": [ "/v1/responses", "/v1/batch" ], "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "o3-pro-2025-06-10", "model_name": "o3 Pro (Jun 2025)", "provider_id": "openai", "provider_name": "OpenAI", "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", "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, "deprecation_date": "2026-10-23", "cache_read_input_token_cost_flex": 1.38e-7, "cache_read_input_token_cost_priority": 5e-7, "input_cost_per_token_batches": 5.5e-7, "input_cost_per_token_flex": 5.5e-7, "input_cost_per_token_priority": 0.000002, "max_tokens": 100000, "output_cost_per_token_batches": 0.0000022, "output_cost_per_token_flex": 0.0000022, "output_cost_per_token_priority": 0.000008, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://developers.openai.com/api/docs/pricing", "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "o4-mini", "model_name": "o4 mini", "provider_id": "openai", "provider_name": "OpenAI", "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", "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, "deprecation_date": "2026-10-23", "cache_read_input_token_cost_flex": 1.38e-7, "cache_read_input_token_cost_priority": 5e-7, "input_cost_per_token_batches": 5.5e-7, "input_cost_per_token_flex": 5.5e-7, "input_cost_per_token_priority": 0.000002, "max_tokens": 100000, "output_cost_per_token_batches": 0.0000022, "output_cost_per_token_flex": 0.0000022, "output_cost_per_token_priority": 0.000008, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "source": "https://developers.openai.com/api/docs/pricing", "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "o4-mini-2025-04-16", "model_name": "o4 mini (Apr 2025)", "provider_id": "openai", "provider_name": "OpenAI", "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", "supports_json_mode": true, "supports_parallel_functions": false }, { "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, "cache_creation_input_token_cost_above_1hr": 0.00002, "max_tokens": 128000, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/~anthropic/claude-fable-latest", "model_name": "Claude Fable Latest", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 10, "output_cost_per_million": 50, "cache_read_cost_per_token": 2.5e-7, "cache_read_cost_per_million": 0.25, "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, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/~anthropic/claude-haiku-latest", "model_name": "Claude Haiku Latest", "provider_id": "openrouter", "provider_name": "OpenRouter", "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": 0.000004, "output_cost_per_token": 0.00002, "max_input_tokens": 1000000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_1hr": 0.000008, "max_tokens": 128000, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/~anthropic/claude-opus-latest", "model_name": "Claude Opus Latest", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 4, "output_cost_per_million": 20, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 0.000005, "cache_write_cost_per_million": 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": 0.000002, "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, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/~anthropic/claude-sonnet-latest", "model_name": "Claude Sonnet Latest", "provider_id": "openrouter", "provider_name": "OpenRouter", "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 }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 7.5e-7, "output_cost_per_token": 0.00000375, "max_input_tokens": 1048576, "max_output_tokens": 65536, "cache_read_input_audio_token_cost": 7.5e-8, "input_cost_per_audio_token": 7.5e-7, "max_tokens": 65536, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/~google/gemini-flash-latest", "model_name": "Gemini Flash Latest", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.75, "output_cost_per_million": 3.75, "cache_read_cost_per_token": 7.5e-8, "cache_read_cost_per_million": 0.075, "cache_write_cost_per_token": 4.16666666666667e-8, "cache_write_cost_per_million": 0.0416666666666667, "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": 0.000012, "max_input_tokens": 1048576, "max_output_tokens": 65536, "cache_read_input_audio_token_cost": 2e-7, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "input_cost_per_audio_token": 0.000002, "input_cost_per_token_above_200k_tokens": 0.000004, "max_tokens": 65536, "output_cost_per_token_above_200k_tokens": 0.000018, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/~google/gemini-pro-latest", "model_name": "Gemini Pro Latest", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 2, "output_cost_per_million": 12, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 3.75e-7, "cache_write_cost_per_million": 0.375, "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": 0.00001, "output_cost_per_token": 0.00005, "max_input_tokens": 1050000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_272k_tokens": 0.000025, "cache_read_input_token_cost_above_272k_tokens": 0.000002, "input_cost_per_token_above_272k_tokens": 0.00002, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.000075, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/~openai/gpt-astra-latest", "model_name": "GPT Astra Latest", "provider_id": "openrouter", "provider_name": "OpenRouter", "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": 1e-7, "output_cost_per_token": 5e-7, "max_input_tokens": 1050000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_272k_tokens": 2.5e-7, "cache_read_input_token_cost_above_272k_tokens": 2e-8, "input_cost_per_token_above_272k_tokens": 2e-7, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 7.5e-7, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/~openai/gpt-luna-latest", "model_name": "GPT Luna Latest", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0.5, "cache_read_cost_per_token": 1e-8, "cache_read_cost_per_million": 0.01, "cache_write_cost_per_token": 1.25e-7, "cache_write_cost_per_million": 0.125, "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": 7.5e-7, "output_cost_per_token": 0.0000045, "max_input_tokens": 400000, "max_output_tokens": 128000, "max_tokens": 128000, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/~openai/gpt-mini-latest", "model_name": "GPT Mini Latest", "provider_id": "openrouter", "provider_name": "OpenRouter", "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": 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": 1050000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_272k_tokens": 0.000005, "cache_read_input_token_cost_above_272k_tokens": 4e-7, "input_cost_per_token_above_272k_tokens": 0.000004, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.000015, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/~openai/gpt-sol-latest", "model_name": "GPT Sol Latest", "provider_id": "openrouter", "provider_name": "OpenRouter", "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 }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000012, "max_input_tokens": 1050000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_272k_tokens": 0.000005, "cache_read_input_token_cost_above_272k_tokens": 4e-7, "input_cost_per_token_above_272k_tokens": 0.000004, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.000018, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/~openai/gpt-terra-latest", "model_name": "GPT Terra Latest", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 2, "output_cost_per_million": 12, "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 }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000006, "max_input_tokens": 500000, "max_output_tokens": 450000, "cache_read_input_token_cost_above_200k_tokens": 0.000001, "input_cost_per_token_above_200k_tokens": 0.000004, "max_tokens": 450000, "output_cost_per_token_above_200k_tokens": 0.000012, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/~x-ai/grok-latest", "model_name": "Grok Latest", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 2, "output_cost_per_million": 6, "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_vision": true, "supports_response_schema": false, "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.00000125, "max_input_tokens": 200000, "max_output_tokens": 4096, "cache_creation_input_token_cost_above_1hr": 5e-7, "input_cost_per_image": 0.0004, "max_tokens": 4096, "supports_tool_choice": true, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": false, "supports_web_search": true, "model_id": "openrouter/anthropic/claude-3-haiku", "model_name": "Claude 3 Haiku", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.25, "output_cost_per_million": 1.25, "cache_read_cost_per_token": 3e-8, "cache_read_cost_per_million": 0.03, "cache_write_cost_per_token": 3e-7, "cache_write_cost_per_million": 0.3, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "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, "supports_sampling_params": false, "supports_adaptive_thinking": true, "thinking_always_on": true, "source": "https://openrouter.ai/api/v1/models", "supports_tool_choice": true, "supports_reasoning": true, "supports_pdf_input": true, "supports_audio_input": false, "supports_prompt_caching": true, "cache_creation_input_token_cost_above_1hr": 0.00002, "prompt_cache_min_tokens": 512, "supports_web_search": true, "model_id": "openrouter/anthropic/claude-fable-5", "model_name": "Claude Fable 5", "provider_id": "openrouter", "provider_name": "OpenRouter", "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": 0.000005, "output_cost_per_token": 0.000025, "max_input_tokens": 1000000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_1hr": 0.00001, "max_tokens": 128000, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/anthropic/claude-fable-5:batch", "model_name": "Claude Fable 5:batch", "provider_id": "openrouter", "provider_name": "OpenRouter", "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": 0.00001, "output_cost_per_token": 0.00005, "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "supports_sampling_params": false, "supports_adaptive_thinking": true, "thinking_always_on": true, "source": "https://openrouter.ai/api/v1/models", "supports_tool_choice": true, "supports_reasoning": true, "supports_pdf_input": true, "supports_audio_input": false, "supports_prompt_caching": true, "cache_creation_input_token_cost_above_1hr": 0.00002, "prompt_cache_min_tokens": 512, "supports_web_search": true, "model_id": "openrouter/anthropic/claude-fable-5.1", "model_name": "Claude Fable 5.1", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 10, "output_cost_per_million": 50, "cache_read_cost_per_token": 2.5e-7, "cache_read_cost_per_million": 0.25, "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": 0.000005, "output_cost_per_token": 0.000025, "max_input_tokens": 1000000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_1hr": 0.00001, "max_tokens": 128000, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/anthropic/claude-fable-5.1:batch", "model_name": "Claude Fable 5.1:batch", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 5, "output_cost_per_million": 25, "cache_read_cost_per_token": 1.25e-7, "cache_read_cost_per_million": 0.125, "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": 0.000001, "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_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "prompt_cache_min_tokens": 4096, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_web_search": true, "model_id": "openrouter/anthropic/claude-haiku-4.5", "model_name": "Claude Haiku 4.5", "provider_id": "openrouter", "provider_name": "OpenRouter", "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": 5e-7, "output_cost_per_token": 0.0000025, "max_input_tokens": 200000, "max_output_tokens": 64000, "cache_creation_input_token_cost_above_1hr": 0.000001, "max_tokens": 64000, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/anthropic/claude-haiku-4.5:batch", "model_name": "Claude Haiku 4.5:batch", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.5, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 5e-8, "cache_read_cost_per_million": 0.049999999999999996, "cache_write_cost_per_token": 6.25e-7, "cache_write_cost_per_million": 0.625, "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": 1e-7, "output_cost_per_token": 5e-7, "max_input_tokens": 1000000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_1hr": 2e-7, "input_cost_per_token_above_100k_tokens": 5e-7, "output_cost_per_token_above_100k_tokens": 0.0000025, "cache_read_input_token_cost_above_100k_tokens": 5e-8, "cache_creation_input_token_cost_above_100k_tokens": 6.25e-7, "cache_creation_input_token_cost_above_1hr_above_100k_tokens": 0.000001, "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 }, "source": "https://openrouter.ai/api/v1/models", "supports_tool_choice": true, "supports_reasoning": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_web_search": true, "supports_adaptive_thinking": true, "prompt_cache_min_tokens": 512, "supports_sampling_params": false, "model_id": "openrouter/anthropic/claude-haiku-5.5", "model_name": "Claude Haiku 5.5", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0.5, "cache_read_cost_per_token": 1e-8, "cache_read_cost_per_million": 0.01, "cache_write_cost_per_token": 1.25e-7, "cache_write_cost_per_million": 0.125, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": false, "input_cost_per_token": 0.000015, "output_cost_per_token": 0.000075, "max_input_tokens": 200000, "max_output_tokens": 32000, "input_cost_per_image": 0.0048, "cache_creation_input_token_cost_above_1hr": 0.00003, "max_tokens": 32000, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "prompt_cache_min_tokens": 1024, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_web_search": true, "model_id": "openrouter/anthropic/claude-opus-4.1", "model_name": "Claude Opus 4.1", "provider_id": "openrouter", "provider_name": "OpenRouter", "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": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000075, "output_cost_per_token": 0.0000375, "max_input_tokens": 200000, "max_output_tokens": 32000, "cache_creation_input_token_cost_above_1hr": 0.000015, "max_tokens": 32000, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/anthropic/claude-opus-4.1:batch", "model_name": "Claude Opus 4.1:batch", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 7.5, "output_cost_per_million": 37.5, "cache_read_cost_per_token": 7.5e-7, "cache_read_cost_per_million": 0.75, "cache_write_cost_per_token": 0.000009375, "cache_write_cost_per_million": 9.375, "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_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_output_config": true, "prompt_cache_min_tokens": 4096, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_web_search": true, "model_id": "openrouter/anthropic/claude-opus-4.5", "model_name": "Claude Opus 4.5", "provider_id": "openrouter", "provider_name": "OpenRouter", "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": 0.0000025, "output_cost_per_token": 0.0000125, "max_input_tokens": 200000, "max_output_tokens": 64000, "cache_creation_input_token_cost_above_1hr": 0.000005, "max_tokens": 64000, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/anthropic/claude-opus-4.5:batch", "model_name": "Claude Opus 4.5:batch", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 2.5, "output_cost_per_million": 12.5, "cache_read_cost_per_token": 2.5e-7, "cache_read_cost_per_million": 0.25, "cache_write_cost_per_token": 0.000003125, "cache_write_cost_per_million": 3.125, "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": 1000000, "max_output_tokens": 128000, "supports_adaptive_thinking": true, "supports_legacy_thinking": true, "cache_creation_input_token_cost_above_1hr": 0.00001, "max_tokens": 128000, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_max_reasoning_effort": true, "supports_tool_choice": true, "prompt_cache_min_tokens": 4096, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_web_search": true, "model_id": "openrouter/anthropic/claude-opus-4.6", "model_name": "Claude Opus 4.6", "provider_id": "openrouter", "provider_name": "OpenRouter", "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": 0.0000025, "output_cost_per_token": 0.0000125, "max_input_tokens": 1000000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_1hr": 0.000005, "max_tokens": 128000, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/anthropic/claude-opus-4.6:batch", "model_name": "Claude Opus 4.6:batch", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 2.5, "output_cost_per_million": 12.5, "cache_read_cost_per_token": 2.5e-7, "cache_read_cost_per_million": 0.25, "cache_write_cost_per_token": 0.000003125, "cache_write_cost_per_million": 3.125, "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": 1000000, "max_output_tokens": 128000, "supports_adaptive_thinking": true, "cache_creation_input_token_cost_above_1hr": 0.00001, "max_tokens": 128000, "supports_assistant_prefill": false, "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_xhigh_reasoning_effort": true, "prompt_cache_min_tokens": 2048, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_web_search": true, "model_id": "openrouter/anthropic/claude-opus-4.7", "model_name": "Claude Opus 4.7", "provider_id": "openrouter", "provider_name": "OpenRouter", "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": 0.0000025, "output_cost_per_token": 0.0000125, "max_input_tokens": 1000000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_1hr": 0.000005, "max_tokens": 128000, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/anthropic/claude-opus-4.7:batch", "model_name": "Claude Opus 4.7:batch", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 2.5, "output_cost_per_million": 12.5, "cache_read_cost_per_token": 2.5e-7, "cache_read_cost_per_million": 0.25, "cache_write_cost_per_token": 0.000003125, "cache_write_cost_per_million": 3.125, "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": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "supports_sampling_params": false, "supports_adaptive_thinking": true, "source": "https://openrouter.ai/api/v1/models", "supports_tool_choice": true, "supports_reasoning": true, "supports_pdf_input": true, "supports_audio_input": false, "supports_prompt_caching": true, "cache_creation_input_token_cost_above_1hr": 0.00001, "supports_web_search": true, "model_id": "openrouter/anthropic/claude-opus-4.8", "model_name": "Claude Opus 4.8", "provider_id": "openrouter", "provider_name": "OpenRouter", "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": 0.0000025, "output_cost_per_token": 0.0000125, "max_input_tokens": 1000000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_1hr": 0.000005, "max_tokens": 128000, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/anthropic/claude-opus-4.8:batch", "model_name": "Claude Opus 4.8:batch", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 2.5, "output_cost_per_million": 12.5, "cache_read_cost_per_token": 2.5e-7, "cache_read_cost_per_million": 0.25, "cache_write_cost_per_token": 0.000003125, "cache_write_cost_per_million": 3.125, "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": 1000000, "max_output_tokens": 128000, "prompt_cache_min_tokens": 512, "supports_adaptive_thinking": true, "cache_creation_input_token_cost_above_1hr": 0.00001, "max_tokens": 128000, "source": "https://openrouter.ai/api/v1/models", "supports_assistant_prefill": false, "supports_audio_input": false, "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_web_search": true, "supports_xhigh_reasoning_effort": true, "model_id": "openrouter/anthropic/claude-opus-5", "model_name": "Claude Opus 5", "provider_id": "openrouter", "provider_name": "OpenRouter", "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": 0.0000025, "output_cost_per_token": 0.0000125, "max_input_tokens": 1000000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_1hr": 0.000005, "max_tokens": 128000, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/anthropic/claude-opus-5:batch", "model_name": "Claude Opus 5:batch", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 2.5, "output_cost_per_million": 12.5, "cache_read_cost_per_token": 2.5e-7, "cache_read_cost_per_million": 0.25, "cache_write_cost_per_token": 0.000003125, "cache_write_cost_per_million": 3.125, "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": 0.000004, "output_cost_per_token": 0.00002, "max_input_tokens": 1000000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_1hr": 0.000008, "max_tokens": 128000, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/anthropic/claude-opus-5.5", "model_name": "Claude Opus 5.5", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 4, "output_cost_per_million": 20, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 0.000005, "cache_write_cost_per_million": 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": 0.000002, "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, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/anthropic/claude-opus-5.5:batch", "model_name": "Claude Opus 5.5:batch", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 2, "output_cost_per_million": 10, "cache_read_cost_per_token": 1e-7, "cache_read_cost_per_million": 0.09999999999999999, "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 }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": false, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 200000, "max_output_tokens": 64000, "input_cost_per_image": 0.0048, "cache_creation_input_token_cost_above_1hr": 0.000006, "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_read_input_token_cost_above_200k_tokens": 6e-7, "input_cost_per_token_above_200k_tokens": 0.000006, "output_cost_per_token_above_200k_tokens": 0.0000225, "max_tokens": 64000, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "prompt_cache_min_tokens": 1024, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_web_search": true, "model_id": "openrouter/anthropic/claude-sonnet-4", "model_name": "Claude Sonnet 4", "provider_id": "openrouter", "provider_name": "OpenRouter", "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": false, "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, "input_cost_per_image": 0.0048, "cache_creation_input_token_cost_above_1hr": 0.000006, "input_cost_per_token_above_200k_tokens": 0.000006, "output_cost_per_token_above_200k_tokens": 0.0000225, "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_read_input_token_cost_above_200k_tokens": 6e-7, "max_tokens": 64000, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "prompt_cache_min_tokens": 1024, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_web_search": true, "model_id": "openrouter/anthropic/claude-sonnet-4.5", "model_name": "Claude Sonnet 4.5", "provider_id": "openrouter", "provider_name": "OpenRouter", "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": 0.0000015, "output_cost_per_token": 0.0000075, "max_input_tokens": 1000000, "max_output_tokens": 64000, "cache_creation_input_token_cost_above_1hr": 0.000003, "cache_creation_input_token_cost_above_200k_tokens": 0.00000375, "cache_read_input_token_cost_above_200k_tokens": 3e-7, "input_cost_per_token_above_200k_tokens": 0.000003, "max_tokens": 64000, "output_cost_per_token_above_200k_tokens": 0.00001125, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/anthropic/claude-sonnet-4.5:batch", "model_name": "Claude Sonnet 4.5:batch", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 1.5, "output_cost_per_million": 7.5, "cache_read_cost_per_token": 1.5e-7, "cache_read_cost_per_million": 0.15, "cache_write_cost_per_token": 0.000001875, "cache_write_cost_per_million": 1.875, "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": 128000, "supports_adaptive_thinking": true, "supports_legacy_thinking": true, "cache_creation_input_token_cost_above_1hr": 0.000006, "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_read_input_token_cost_above_200k_tokens": 6e-7, "input_cost_per_token_above_200k_tokens": 0.000006, "max_tokens": 128000, "output_cost_per_token_above_200k_tokens": 0.0000225, "source": "https://openrouter.ai/api/v1/models", "supports_assistant_prefill": true, "supports_computer_use": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_max_reasoning_effort": true, "supports_tool_choice": true, "prompt_cache_min_tokens": 1024, "supports_audio_input": false, "supports_pdf_input": true, "supports_web_search": true, "model_id": "openrouter/anthropic/claude-sonnet-4.6", "model_name": "Claude Sonnet 4.6", "provider_id": "openrouter", "provider_name": "OpenRouter", "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": 0.0000015, "output_cost_per_token": 0.0000075, "max_input_tokens": 1000000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_1hr": 0.000003, "max_tokens": 128000, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/anthropic/claude-sonnet-4.6:batch", "model_name": "Claude Sonnet 4.6:batch", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 1.5, "output_cost_per_million": 7.5, "cache_read_cost_per_token": 1.5e-7, "cache_read_cost_per_million": 0.15, "cache_write_cost_per_token": 0.000001875, "cache_write_cost_per_million": 1.875, "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, "max_tokens": 128000, "supports_sampling_params": false, "supports_adaptive_thinking": true, "source": "https://openrouter.ai/api/v1/models", "supports_tool_choice": true, "supports_reasoning": true, "supports_pdf_input": true, "supports_audio_input": false, "supports_prompt_caching": true, "cache_creation_input_token_cost_above_1hr": 0.000004, "supports_web_search": true, "model_id": "openrouter/anthropic/claude-sonnet-5", "model_name": "Claude Sonnet 5", "provider_id": "openrouter", "provider_name": "OpenRouter", "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 }, { "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": 1000000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_1hr": 0.000002, "max_tokens": 128000, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/anthropic/claude-sonnet-5:batch", "model_name": "Claude Sonnet 5:batch", "provider_id": "openrouter", "provider_name": "OpenRouter", "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": 0.000002, "output_cost_per_token": 0.00001, "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "supports_sampling_params": false, "supports_adaptive_thinking": true, "source": "https://openrouter.ai/api/v1/models", "supports_tool_choice": true, "supports_reasoning": true, "supports_pdf_input": true, "supports_audio_input": false, "supports_prompt_caching": true, "cache_creation_input_token_cost_above_1hr": 0.000004, "supports_web_search": true, "model_id": "openrouter/anthropic/claude-sonnet-5.5", "model_name": "Claude Sonnet 5.5", "provider_id": "openrouter", "provider_name": "OpenRouter", "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 }, { "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": 1000000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_1hr": 0.000002, "max_tokens": 128000, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/anthropic/claude-sonnet-5.5:batch", "model_name": "Claude Sonnet 5.5:batch", "provider_id": "openrouter", "provider_name": "OpenRouter", "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": 3e-7, "output_cost_per_token": 0.0000025, "max_input_tokens": 1048576, "max_output_tokens": 65535, "deprecation_date": "2026-10-20", "cache_read_input_audio_token_cost": 1e-7, "input_cost_per_audio_token": 0.000001, "max_tokens": 65535, "supports_audio_output": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_image_size": false, "supports_prompt_caching": true, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": true, "supports_pdf_input": true, "supports_reasoning": true, "supports_web_search": true, "supports_video_input": true, "model_id": "openrouter/google/gemini-2.5-flash", "model_name": "Gemini 2.5 Flash", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.3, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 3e-8, "cache_read_cost_per_million": 0.03, "cache_write_cost_per_token": 8.33333333333333e-8, "cache_write_cost_per_million": 0.0833333333333333, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": false, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000025, "max_input_tokens": 32768, "max_output_tokens": 8192, "deprecation_date": "2027-03-15", "cache_read_input_audio_token_cost": 1e-7, "input_cost_per_audio_token": 0.000001, "output_cost_per_image_token": 0.00003, "max_tokens": 8192, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": false, "supports_tool_choice": false, "supports_prompt_caching": true, "supports_reasoning": false, "supports_web_search": true, "model_id": "openrouter/google/gemini-2.5-flash-image", "model_name": "Gemini 2.5 Flash Image", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.3, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 3e-8, "cache_read_cost_per_million": 0.03, "cache_write_cost_per_token": 8.33333333333333e-8, "cache_write_cost_per_million": 0.0833333333333333, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_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": 1048576, "max_output_tokens": 65535, "deprecation_date": "2026-10-20", "cache_read_input_audio_token_cost": 3e-8, "max_tokens": 65535, "source": "https://openrouter.ai/api/v1/models", "supports_tool_choice": true, "supports_reasoning": true, "supports_pdf_input": true, "supports_audio_input": true, "input_cost_per_audio_token": 3e-7, "supports_prompt_caching": true, "supports_web_search": true, "supports_video_input": true, "model_id": "openrouter/google/gemini-2.5-flash-lite", "model_name": "Gemini 2.5 Flash Lite", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0.39999999999999997, "cache_read_cost_per_token": 1e-8, "cache_read_cost_per_million": 0.01, "cache_write_cost_per_token": 8.33333333333333e-8, "cache_write_cost_per_million": 0.0833333333333333, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 5e-8, "output_cost_per_token": 2e-7, "max_input_tokens": 1048576, "max_output_tokens": 65535, "cache_read_input_audio_token_cost": 3e-8, "input_cost_per_audio_token": 1.5e-7, "max_tokens": 65535, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "supports_video_input": true, "model_id": "openrouter/google/gemini-2.5-flash-lite:batch", "model_name": "Gemini 2.5 Flash Lite:batch", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.049999999999999996, "output_cost_per_million": 0.19999999999999998, "cache_read_cost_per_token": 1e-8, "cache_read_cost_per_million": 0.01, "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_vision": true, "supports_response_schema": true, "input_cost_per_token": 1.5e-7, "output_cost_per_token": 0.00000125, "max_input_tokens": 1048576, "max_output_tokens": 65535, "deprecation_date": "2026-10-20", "cache_read_input_audio_token_cost": 1e-7, "input_cost_per_audio_token": 5e-7, "max_tokens": 65535, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "supports_video_input": true, "model_id": "openrouter/google/gemini-2.5-flash:batch", "model_name": "Gemini 2.5 Flash:batch", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.15, "output_cost_per_million": 1.25, "cache_read_cost_per_token": 3e-8, "cache_read_cost_per_million": 0.03, "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_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 1048576, "max_output_tokens": 65536, "deprecation_date": "2026-10-20", "cache_read_input_audio_token_cost": 1.25e-7, "input_cost_per_audio_token": 0.00000125, "max_tokens": 65536, "supports_audio_output": false, "supports_system_messages": true, "supports_tool_choice": true, "cache_read_input_token_cost_above_200k_tokens": 2.5e-7, "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000015, "supports_prompt_caching": true, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": true, "supports_pdf_input": true, "supports_reasoning": true, "supports_web_search": true, "supports_video_input": true, "model_id": "openrouter/google/gemini-2.5-pro", "model_name": "Gemini 2.5 Pro", "provider_id": "openrouter", "provider_name": "OpenRouter", "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": 3.75e-7, "cache_write_cost_per_million": 0.375, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_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": 1048576, "max_output_tokens": 65536, "cache_read_input_audio_token_cost": 1.25e-7, "input_cost_per_audio_token": 0.00000125, "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000015, "cache_read_input_token_cost_above_200k_tokens": 2.5e-7, "max_tokens": 65536, "source": "https://openrouter.ai/api/v1/models", "supports_tool_choice": true, "supports_reasoning": true, "supports_pdf_input": true, "supports_audio_input": true, "supports_prompt_caching": true, "supports_web_search": true, "model_id": "openrouter/google/gemini-2.5-pro-preview", "model_name": "Gemini 2.5 Pro Preview", "provider_id": "openrouter", "provider_name": "OpenRouter", "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": 3.75e-7, "cache_write_cost_per_million": 0.375, "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": 6.25e-7, "output_cost_per_token": 0.000005, "max_input_tokens": 1048576, "max_output_tokens": 65536, "deprecation_date": "2026-10-20", "cache_read_input_audio_token_cost": 1.25e-7, "cache_read_input_token_cost_above_200k_tokens": 2.5e-7, "input_cost_per_audio_token": 6.25e-7, "input_cost_per_token_above_200k_tokens": 0.00000125, "max_tokens": 65536, "output_cost_per_token_above_200k_tokens": 0.0000075, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "supports_video_input": true, "model_id": "openrouter/google/gemini-2.5-pro:batch", "model_name": "Gemini 2.5 Pro:batch", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.625, "output_cost_per_million": 5, "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", "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": 5e-7, "output_cost_per_token": 0.000003, "max_input_tokens": 1048576, "max_output_tokens": 65536, "cache_read_input_audio_token_cost": 1e-7, "input_cost_per_audio_token": 0.000001, "max_tokens": 65536, "output_cost_per_reasoning_token": 0.000003, "rpm": 2000, "source": "https://openrouter.ai/api/v1/models", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_audio_output": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_web_search": true, "tpm": 800000, "supports_video_input": true, "model_id": "openrouter/google/gemini-3-flash-preview", "model_name": "Gemini 3 Flash Preview", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.5, "output_cost_per_million": 3, "cache_read_cost_per_token": 5e-8, "cache_read_cost_per_million": 0.049999999999999996, "cache_write_cost_per_token": 8.33333333333333e-8, "cache_write_cost_per_million": 0.0833333333333333, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.0000015, "max_input_tokens": 1048576, "max_output_tokens": 65536, "input_cost_per_audio_token": 5e-7, "max_tokens": 65536, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": true, "supports_pdf_input": true, "supports_prompt_caching": false, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "supports_video_input": true, "model_id": "openrouter/google/gemini-3-flash-preview:batch", "model_name": "Gemini 3 Flash Preview:batch", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.25, "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_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000012, "max_input_tokens": 131072, "max_output_tokens": 32768, "cache_read_input_audio_token_cost": 2e-7, "input_cost_per_audio_token": 0.000002, "output_cost_per_image_token": 0.00012, "max_tokens": 32768, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": false, "supports_tool_choice": true, "supports_reasoning": true, "supports_prompt_caching": true, "supports_web_search": true, "model_id": "openrouter/google/gemini-3-pro-image", "model_name": "Gemini 3 Pro Image", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 2, "output_cost_per_million": 12, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 3.75e-7, "cache_write_cost_per_million": 0.375, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": false, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000012, "max_input_tokens": 65536, "max_output_tokens": 32768, "cache_read_input_audio_token_cost": 2e-7, "input_cost_per_audio_token": 0.000002, "output_cost_per_image_token": 0.00012, "max_tokens": 32768, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": false, "supports_tool_choice": false, "supports_reasoning": true, "supports_prompt_caching": true, "supports_web_search": true, "model_id": "openrouter/google/gemini-3-pro-image-preview", "model_name": "Gemini 3 Pro Image Preview", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 2, "output_cost_per_million": 12, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 3.75e-7, "cache_write_cost_per_million": 0.375, "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": 0.000012, "max_input_tokens": 1048576, "max_output_tokens": 65535, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "cache_creation_input_token_cost_above_200k_tokens": 2.5e-7, "input_cost_per_token_above_200k_tokens": 0.000004, "input_cost_per_token_batches": 0.000001, "max_tokens": 65535, "output_cost_per_token_above_200k_tokens": 0.000018, "output_cost_per_token_batches": 0.000006, "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_video_input": true, "supports_web_search": true, "model_id": "openrouter/google/gemini-3-pro-preview", "model_name": "Gemini 3 Pro Preview", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 2, "output_cost_per_million": 12, "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": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": false, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 5e-7, "output_cost_per_token": 0.000003, "max_input_tokens": 131072, "max_output_tokens": 32768, "output_cost_per_image_token": 0.00006, "max_tokens": 32768, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": false, "supports_prompt_caching": false, "supports_tool_choice": false, "supports_reasoning": true, "supports_web_search": true, "model_id": "openrouter/google/gemini-3.1-flash-image", "model_name": "Gemini 3.1 Flash Image", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.5, "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": true, "supports_parallel_functions": false }, { "supports_function_calling": false, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 5e-7, "output_cost_per_token": 0.000003, "max_input_tokens": 65536, "max_output_tokens": 58982, "output_cost_per_image_token": 0.00006, "max_tokens": 58982, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": false, "supports_prompt_caching": false, "supports_tool_choice": false, "supports_reasoning": true, "supports_web_search": true, "model_id": "openrouter/google/gemini-3.1-flash-image-preview", "model_name": "Gemini 3.1 Flash Image Preview", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.5, "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": 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": 2.5e-7, "output_cost_per_token": 0.0000015, "max_input_tokens": 1048576, "max_output_tokens": 65536, "cache_read_input_audio_token_cost": 5e-8, "input_cost_per_audio_token": 5e-7, "max_tokens": 65536, "output_cost_per_reasoning_token": 0.0000015, "rpm": 2000, "source": "https://openrouter.ai/api/v1/models", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_audio_output": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_web_search": true, "tpm": 800000, "model_id": "openrouter/google/gemini-3.1-flash-lite", "model_name": "Gemini 3.1 Flash Lite", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.25, "output_cost_per_million": 1.5, "cache_read_cost_per_token": 2.5e-8, "cache_read_cost_per_million": 0.024999999999999998, "cache_write_cost_per_token": 8.33333333333333e-8, "cache_write_cost_per_million": 0.0833333333333333, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": false, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.0000015, "max_input_tokens": 65536, "max_output_tokens": 58982, "output_cost_per_image_token": 0.00003, "max_tokens": 58982, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": false, "supports_prompt_caching": false, "supports_tool_choice": false, "supports_reasoning": true, "supports_web_search": true, "model_id": "openrouter/google/gemini-3.1-flash-lite-image", "model_name": "Gemini 3.1 Flash Lite Image", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.25, "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_parallel_functions": false }, { "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": 0.0000015, "max_input_tokens": 1048576, "max_output_tokens": 65536, "cache_read_input_audio_token_cost": 5e-8, "input_cost_per_audio_token": 5e-7, "max_tokens": 65536, "output_cost_per_reasoning_token": 0.0000015, "rpm": 2000, "source": "https://openrouter.ai/api/v1/models", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_audio_output": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_web_search": true, "tpm": 800000, "model_id": "openrouter/google/gemini-3.1-flash-lite-preview", "model_name": "Gemini 3.1 Flash Lite Preview", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.25, "output_cost_per_million": 1.5, "cache_read_cost_per_token": 2.5e-8, "cache_read_cost_per_million": 0.024999999999999998, "cache_write_cost_per_token": 8.33333333333333e-8, "cache_write_cost_per_million": 0.0833333333333333, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 1.25e-7, "output_cost_per_token": 7.5e-7, "max_input_tokens": 1048576, "max_output_tokens": 65536, "cache_read_input_audio_token_cost": 2.5e-8, "input_cost_per_audio_token": 2.5e-7, "max_tokens": 65536, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "supports_video_input": true, "model_id": "openrouter/google/gemini-3.1-flash-lite:batch", "model_name": "Gemini 3.1 Flash Lite:batch", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.125, "output_cost_per_million": 0.75, "cache_read_cost_per_token": 1.25e-8, "cache_read_cost_per_million": 0.012499999999999999, "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_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000012, "max_input_tokens": 1048576, "max_output_tokens": 65536, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "cache_creation_input_token_cost_above_200k_tokens": 2.5e-7, "cache_read_input_audio_token_cost": 2e-7, "input_cost_per_audio_token": 0.000002, "input_cost_per_token_above_200k_tokens": 0.000004, "max_tokens": 65536, "output_cost_per_token_above_200k_tokens": 0.000018, "source": "https://openrouter.ai/api/v1/models", "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": 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_video_input": true, "model_id": "openrouter/google/gemini-3.1-pro-preview", "model_name": "Gemini 3.1 Pro Preview", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 2, "output_cost_per_million": 12, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 3.75e-7, "cache_write_cost_per_million": 0.375, "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": 0.000012, "max_input_tokens": 1048576, "max_output_tokens": 65536, "cache_read_input_audio_token_cost": 2e-7, "input_cost_per_audio_token": 0.000002, "input_cost_per_token_above_200k_tokens": 0.000004, "output_cost_per_token_above_200k_tokens": 0.000018, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "max_tokens": 65536, "source": "https://openrouter.ai/api/v1/models", "supports_tool_choice": true, "supports_reasoning": true, "supports_pdf_input": true, "supports_audio_input": true, "supports_prompt_caching": true, "supports_web_search": true, "supports_video_input": true, "model_id": "openrouter/google/gemini-3.1-pro-preview-customtools", "model_name": "Gemini 3.1 Pro Preview Customtools", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 2, "output_cost_per_million": 12, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 3.75e-7, "cache_write_cost_per_million": 0.375, "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": 0.000006, "max_input_tokens": 1048576, "max_output_tokens": 65536, "input_cost_per_audio_token": 0.000001, "input_cost_per_token_above_200k_tokens": 0.000002, "max_tokens": 65536, "output_cost_per_token_above_200k_tokens": 0.000009, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": true, "supports_pdf_input": true, "supports_prompt_caching": false, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "supports_video_input": true, "model_id": "openrouter/google/gemini-3.1-pro-preview:batch", "model_name": "Gemini 3.1 Pro Preview:batch", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 1, "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_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000015, "output_cost_per_token": 0.000009, "max_input_tokens": 1048576, "max_output_tokens": 65536, "cache_read_input_audio_token_cost": 3e-7, "max_tokens": 65536, "source": "https://openrouter.ai/api/v1/models", "supports_tool_choice": true, "supports_reasoning": true, "supports_pdf_input": true, "supports_audio_input": true, "input_cost_per_audio_token": 0.000003, "supports_prompt_caching": true, "supports_web_search": true, "supports_video_input": true, "model_id": "openrouter/google/gemini-3.5-flash", "model_name": "Gemini 3.5 Flash", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 1.5, "output_cost_per_million": 9, "cache_read_cost_per_token": 1.5e-7, "cache_read_cost_per_million": 0.15, "cache_write_cost_per_token": 8.33333333333333e-8, "cache_write_cost_per_million": 0.0833333333333333, "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": 3e-7, "output_cost_per_token": 0.0000025, "max_input_tokens": 1048576, "max_output_tokens": 65536, "cache_read_input_audio_token_cost": 3e-8, "max_tokens": 65536, "source": "https://openrouter.ai/api/v1/models", "supports_tool_choice": true, "supports_reasoning": true, "supports_pdf_input": true, "supports_audio_input": true, "input_cost_per_audio_token": 3e-7, "supports_prompt_caching": true, "supports_web_search": true, "supports_video_input": true, "model_id": "openrouter/google/gemini-3.5-flash-lite", "model_name": "Gemini 3.5 Flash Lite", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.3, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 3e-8, "cache_read_cost_per_million": 0.03, "cache_write_cost_per_token": 8.33333333333333e-8, "cache_write_cost_per_million": 0.0833333333333333, "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": 1.5e-7, "output_cost_per_token": 0.00000125, "max_input_tokens": 1048576, "max_output_tokens": 65536, "cache_read_input_audio_token_cost": 1.5e-8, "input_cost_per_audio_token": 1.5e-7, "max_tokens": 65536, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "supports_video_input": true, "model_id": "openrouter/google/gemini-3.5-flash-lite:batch", "model_name": "Gemini 3.5 Flash Lite:batch", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.15, "output_cost_per_million": 1.25, "cache_read_cost_per_token": 1.5e-8, "cache_read_cost_per_million": 0.015, "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_vision": true, "supports_response_schema": true, "input_cost_per_token": 7.5e-7, "output_cost_per_token": 0.0000045, "max_input_tokens": 1048576, "max_output_tokens": 65536, "cache_read_input_audio_token_cost": 1.5e-7, "input_cost_per_audio_token": 0.0000015, "max_tokens": 65536, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "supports_video_input": true, "model_id": "openrouter/google/gemini-3.5-flash:batch", "model_name": "Gemini 3.5 Flash:batch", "provider_id": "openrouter", "provider_name": "OpenRouter", "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": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 7.5e-7, "output_cost_per_token": 0.00000375, "max_input_tokens": 1048576, "max_output_tokens": 65536, "cache_read_input_audio_token_cost": 7.5e-8, "max_tokens": 65536, "source": "https://openrouter.ai/api/v1/models", "supports_tool_choice": true, "supports_reasoning": true, "supports_pdf_input": true, "supports_audio_input": true, "input_cost_per_audio_token": 7.5e-7, "supports_prompt_caching": true, "supports_web_search": true, "supports_video_input": true, "model_id": "openrouter/google/gemini-3.6-flash", "model_name": "Gemini 3.6 Flash", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.75, "output_cost_per_million": 3.75, "cache_read_cost_per_token": 7.5e-8, "cache_read_cost_per_million": 0.075, "cache_write_cost_per_token": 4.16666666666667e-8, "cache_write_cost_per_million": 0.0416666666666667, "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": 3.75e-7, "output_cost_per_token": 0.000001875, "max_input_tokens": 1048576, "max_output_tokens": 65536, "cache_read_input_audio_token_cost": 3.75e-8, "input_cost_per_audio_token": 3.75e-7, "max_tokens": 65536, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "supports_video_input": true, "model_id": "openrouter/google/gemini-3.6-flash:batch", "model_name": "Gemini 3.6 Flash:batch", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.375, "output_cost_per_million": 1.875, "cache_read_cost_per_token": 3.75e-8, "cache_read_cost_per_million": 0.0375, "cache_write_cost_per_token": 4.16666666666667e-8, "cache_write_cost_per_million": 0.0416666666666667, "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": 7.5e-7, "output_cost_per_token": 0.00000375, "max_input_tokens": 1048576, "max_output_tokens": 65536, "cache_read_input_audio_token_cost": 7.5e-8, "max_tokens": 65536, "source": "https://openrouter.ai/api/v1/models", "supports_tool_choice": true, "supports_reasoning": true, "supports_pdf_input": true, "supports_audio_input": true, "input_cost_per_audio_token": 7.5e-7, "supports_prompt_caching": true, "supports_web_search": true, "supports_video_input": true, "model_id": "openrouter/google/gemini-3.7-flash", "model_name": "Gemini 3.7 Flash", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.75, "output_cost_per_million": 3.75, "cache_read_cost_per_token": 7.5e-8, "cache_read_cost_per_million": 0.075, "cache_write_cost_per_token": 4.16666666666667e-8, "cache_write_cost_per_million": 0.0416666666666667, "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": 3.75e-7, "output_cost_per_token": 0.000001875, "max_input_tokens": 1048576, "max_output_tokens": 65536, "cache_read_input_audio_token_cost": 3.75e-8, "input_cost_per_audio_token": 3.75e-7, "max_tokens": 65536, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "supports_video_input": true, "model_id": "openrouter/google/gemini-3.7-flash:batch", "model_name": "Gemini 3.7 Flash:batch", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.375, "output_cost_per_million": 1.875, "cache_read_cost_per_token": 3.75e-8, "cache_read_cost_per_million": 0.0375, "cache_write_cost_per_token": 4.16666666666667e-8, "cache_write_cost_per_million": 0.0416666666666667, "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": 7.5e-7, "output_cost_per_token": 0.00000375, "max_input_tokens": 1048576, "max_output_tokens": 65536, "cache_read_input_audio_token_cost": 7.5e-8, "max_tokens": 65536, "source": "https://openrouter.ai/api/v1/models", "supports_tool_choice": true, "supports_reasoning": true, "supports_pdf_input": true, "supports_audio_input": true, "input_cost_per_audio_token": 7.5e-7, "supports_prompt_caching": true, "supports_web_search": true, "supports_video_input": true, "model_id": "openrouter/google/gemini-3.8-flash", "model_name": "Gemini 3.8 Flash", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.75, "output_cost_per_million": 3.75, "cache_read_cost_per_token": 7.5e-8, "cache_read_cost_per_million": 0.075, "cache_write_cost_per_token": 4.16666666666667e-8, "cache_write_cost_per_million": 0.0416666666666667, "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": 3.75e-7, "output_cost_per_token": 0.000001875, "max_input_tokens": 1048576, "max_output_tokens": 65536, "cache_read_input_audio_token_cost": 3.75e-8, "input_cost_per_audio_token": 3.75e-7, "max_tokens": 65536, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "supports_video_input": true, "model_id": "openrouter/google/gemini-3.8-flash:batch", "model_name": "Gemini 3.8 Flash:batch", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.375, "output_cost_per_million": 1.875, "cache_read_cost_per_token": 3.75e-8, "cache_read_cost_per_million": 0.0375, "cache_write_cost_per_token": 4.16666666666667e-8, "cache_write_cost_per_million": 0.0416666666666667, "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": 0.0000015, "output_cost_per_token": 0.0000075, "max_input_tokens": 65536, "max_output_tokens": 58982, "max_tokens": 58982, "output_cost_per_image_token": 0.00003, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": false, "supports_prompt_caching": false, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/google/gemini-nano-banana-2.1", "model_name": "Gemini Nano Banana 2.1", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 1.5, "output_cost_per_million": 7.5, "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_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00000425, "max_input_tokens": 1048576, "max_output_tokens": 943718, "max_tokens": 943718, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/meta/muse-spark-1.1", "model_name": "Muse Spark 1.1", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 1.25, "output_cost_per_million": 4.25, "cache_read_cost_per_token": 1.5e-7, "cache_read_cost_per_million": 0.15, "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_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00000425, "max_input_tokens": 1048576, "max_output_tokens": 943718, "max_tokens": 943718, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/meta/muse-spark-1.2", "model_name": "Muse Spark 1.2", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 1.25, "output_cost_per_million": 4.25, "cache_read_cost_per_token": 1.5e-7, "cache_read_cost_per_million": 0.15, "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_vision": true, "supports_response_schema": true, "input_cost_per_token": 1e-7, "output_cost_per_token": 2e-7, "max_input_tokens": 1048576, "max_output_tokens": 943718, "max_tokens": 943718, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/meta/muse-spark-1.2-contributor", "model_name": "Muse Spark 1.2 Contributor", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0.19999999999999998, "cache_read_cost_per_token": 2e-9, "cache_read_cost_per_million": 0.002, "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_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00000425, "max_input_tokens": 1048576, "max_output_tokens": 943718, "max_tokens": 943718, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/meta/muse-spark-1.3", "model_name": "Muse Spark 1.3", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 1.25, "output_cost_per_million": 4.25, "cache_read_cost_per_token": 1.5e-7, "cache_read_cost_per_million": 0.15, "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_vision": true, "supports_response_schema": true, "input_cost_per_token": 1e-7, "output_cost_per_token": 2e-7, "max_input_tokens": 1048576, "max_output_tokens": 943718, "max_tokens": 943718, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/meta/muse-spark-1.3-contributor", "model_name": "Muse Spark 1.3 Contributor", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0.19999999999999998, "cache_read_cost_per_token": 2e-9, "cache_read_cost_per_million": 0.002, "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_vision": false, "supports_response_schema": true, "input_cost_per_token": 2.5e-7, "output_cost_per_token": 7.5e-7, "max_input_tokens": 16385, "max_output_tokens": 4096, "max_tokens": 4096, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": false, "supports_prompt_caching": false, "supports_reasoning": false, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/openai/gpt-3.5-turbo:batch", "model_name": "GPT-3.5 Turbo:batch", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.25, "output_cost_per_million": 0.75, "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": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000015, "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": false, "supports_prompt_caching": false, "supports_reasoning": false, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/openai/gpt-4-turbo:batch", "model_name": "GPT-4 Turbo:batch", "provider_id": "openrouter", "provider_name": "OpenRouter", "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_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": 0.000002, "output_cost_per_token": 0.000008, "max_input_tokens": 1047576, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/openai/gpt-4.1", "model_name": "GPT-4.1", "provider_id": "openrouter", "provider_name": "OpenRouter", "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": 4e-7, "output_cost_per_token": 0.0000016, "max_input_tokens": 1047576, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/openai/gpt-4.1-mini", "model_name": "GPT-4.1 mini", "provider_id": "openrouter", "provider_name": "OpenRouter", "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_vision": true, "supports_response_schema": true, "input_cost_per_token": 2e-7, "output_cost_per_token": 8e-7, "max_input_tokens": 1047576, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": false, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/openai/gpt-4.1-mini:batch", "model_name": "GPT-4.1 Mini:batch", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.19999999999999998, "output_cost_per_million": 0.7999999999999999, "cache_read_cost_per_token": 5e-8, "cache_read_cost_per_million": 0.049999999999999996, "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": 1e-7, "output_cost_per_token": 4e-7, "max_input_tokens": 1047576, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/openai/gpt-4.1-nano", "model_name": "GPT-4.1 nano", "provider_id": "openrouter", "provider_name": "OpenRouter", "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_vision": true, "supports_response_schema": true, "input_cost_per_token": 5e-8, "output_cost_per_token": 2e-7, "max_input_tokens": 1047576, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": false, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/openai/gpt-4.1-nano:batch", "model_name": "GPT-4.1 Nano:batch", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.049999999999999996, "output_cost_per_million": 0.19999999999999998, "cache_read_cost_per_token": 1.25e-8, "cache_read_cost_per_million": 0.012499999999999999, "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_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000004, "max_input_tokens": 1047576, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": false, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/openai/gpt-4.1:batch", "model_name": "GPT-4.1:batch", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 1, "output_cost_per_million": 4, "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": 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, "max_tokens": 16384, "supports_tool_choice": true, "supports_prompt_caching": true, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_reasoning": false, "supports_web_search": true, "model_id": "openrouter/openai/gpt-4o", "model_name": "GPT-4o", "provider_id": "openrouter", "provider_name": "OpenRouter", "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, "supports_response_schema": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000015, "max_input_tokens": 128000, "max_output_tokens": 4096, "max_tokens": 4096, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_prompt_caching": false, "supports_reasoning": false, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/openai/gpt-4o-2024-05-13", "model_name": "GPT-4o (May 2024)", "provider_id": "openrouter", "provider_name": "OpenRouter", "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_json_mode": true, "supports_parallel_functions": true }, { "supports_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, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_tool_choice": true, "supports_web_search": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": false, "model_id": "openrouter/openai/gpt-4o-2024-08-06", "model_name": "GPT-4o (Aug 2024)", "provider_id": "openrouter", "provider_name": "OpenRouter", "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": false }, { "supports_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, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_tool_choice": true, "supports_web_search": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": false, "model_id": "openrouter/openai/gpt-4o-2024-11-20", "model_name": "GPT-4o (Nov 2024)", "provider_id": "openrouter", "provider_name": "OpenRouter", "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": false }, { "supports_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, "source": "https://openrouter.ai/api/v1/models", "supports_tool_choice": true, "supports_reasoning": false, "supports_pdf_input": true, "supports_audio_input": false, "supports_prompt_caching": true, "supports_web_search": true, "model_id": "openrouter/openai/gpt-4o-mini", "model_name": "GPT-4o mini", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.15, "output_cost_per_million": 0.6, "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": false }, { "supports_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, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_tool_choice": true, "supports_web_search": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": false, "model_id": "openrouter/openai/gpt-4o-mini-2024-07-18", "model_name": "GPT-4o mini (Jul 2024)", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.15, "output_cost_per_million": 0.6, "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": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 7.5e-8, "output_cost_per_token": 3e-7, "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": false, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/openai/gpt-4o-mini:batch", "model_name": "GPT-4o Mini:batch", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.075, "output_cost_per_million": 0.3, "cache_read_cost_per_token": 3.75e-8, "cache_read_cost_per_million": 0.0375, "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_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.000005, "max_input_tokens": 128000, "max_output_tokens": 16384, "max_tokens": 16384, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": false, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/openai/gpt-4o:batch", "model_name": "GPT-4o:batch", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 1.25, "output_cost_per_million": 5, "cache_read_cost_per_token": 6.25e-7, "cache_read_cost_per_million": 0.625, "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_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 400000, "max_output_tokens": 128000, "max_tokens": 128000, "source": "https://openrouter.ai/api/v1/models", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_audio_input": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/openai/gpt-5", "model_name": "GPT-5", "provider_id": "openrouter", "provider_name": "OpenRouter", "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": false, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00001, "output_cost_per_token": 0.00001, "max_input_tokens": 400000, "max_output_tokens": 128000, "max_tokens": 128000, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": false, "supports_web_search": true, "model_id": "openrouter/openai/gpt-5-image", "model_name": "GPT-5 Image", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 10, "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": false }, { "supports_function_calling": false, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.000002, "max_input_tokens": 400000, "max_output_tokens": 128000, "max_tokens": 128000, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": false, "supports_web_search": true, "model_id": "openrouter/openai/gpt-5-image-mini", "model_name": "GPT-5 Image Mini", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 2.5, "output_cost_per_million": 2, "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": false }, { "supports_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": 400000, "max_output_tokens": 128000, "max_tokens": 128000, "source": "https://openrouter.ai/api/v1/models", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_audio_input": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/openai/gpt-5-mini", "model_name": "GPT-5 Mini", "provider_id": "openrouter", "provider_name": "OpenRouter", "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": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 1.25e-7, "output_cost_per_token": 0.000001, "max_input_tokens": 400000, "max_output_tokens": 128000, "max_tokens": 128000, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/openai/gpt-5-mini:batch", "model_name": "GPT-5 Mini:batch", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.125, "output_cost_per_million": 1, "cache_read_cost_per_token": 1.25e-8, "cache_read_cost_per_million": 0.012499999999999999, "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_vision": true, "supports_response_schema": true, "input_cost_per_token": 5e-8, "output_cost_per_token": 4e-7, "max_input_tokens": 400000, "max_output_tokens": 128000, "max_tokens": 128000, "source": "https://openrouter.ai/api/v1/models", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_audio_input": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/openai/gpt-5-nano", "model_name": "GPT-5 Nano", "provider_id": "openrouter", "provider_name": "OpenRouter", "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": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2.5e-8, "output_cost_per_token": 2e-7, "max_input_tokens": 400000, "max_output_tokens": 128000, "max_tokens": 128000, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/openai/gpt-5-nano:batch", "model_name": "GPT-5 Nano:batch", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.024999999999999998, "output_cost_per_million": 0.19999999999999998, "cache_read_cost_per_token": 2.5e-9, "cache_read_cost_per_million": 0.0025, "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_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000015, "output_cost_per_token": 0.00012, "max_input_tokens": 400000, "max_output_tokens": 128000, "max_tokens": 128000, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_tool_choice": true, "supports_reasoning": true, "supports_pdf_input": true, "supports_prompt_caching": false, "supports_web_search": true, "model_id": "openrouter/openai/gpt-5-pro", "model_name": "GPT-5 Pro", "provider_id": "openrouter", "provider_name": "OpenRouter", "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": "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": 0.0000075, "output_cost_per_token": 0.00006, "max_input_tokens": 400000, "max_output_tokens": 128000, "max_tokens": 128000, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_prompt_caching": false, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/openai/gpt-5-pro:batch", "model_name": "GPT-5 Pro:batch", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 7.5, "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_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 6.25e-7, "output_cost_per_token": 0.000005, "max_input_tokens": 400000, "max_output_tokens": 128000, "max_tokens": 128000, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/openai/gpt-5:batch", "model_name": "GPT-5:batch", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.625, "output_cost_per_million": 5, "cache_read_cost_per_token": 6.25e-8, "cache_read_cost_per_million": 0.0625, "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_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 400000, "max_output_tokens": 128000, "max_tokens": 128000, "source": "https://openrouter.ai/api/v1/models", "supports_tool_choice": true, "supports_reasoning": true, "supports_pdf_input": true, "supports_audio_input": false, "supports_prompt_caching": true, "supports_web_search": true, "model_id": "openrouter/openai/gpt-5.1", "model_name": "GPT-5.1", "provider_id": "openrouter", "provider_name": "OpenRouter", "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_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 400000, "max_output_tokens": 128000, "max_tokens": 128000, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": false, "supports_tool_choice": true, "supports_reasoning": true, "supports_prompt_caching": true, "supports_web_search": true, "model_id": "openrouter/openai/gpt-5.1-codex", "model_name": "GPT-5.1 Codex", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 1.25, "output_cost_per_million": 10, "cache_read_cost_per_token": 1.3e-7, "cache_read_cost_per_million": 0.13, "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_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 400000, "max_output_tokens": 128000, "max_tokens": 128000, "source": "https://openrouter.ai/api/v1/models", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_audio_input": false, "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/openai/gpt-5.1-codex-max", "model_name": "GPT-5.1 Codex Max", "provider_id": "openrouter", "provider_name": "OpenRouter", "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_vision": true, "supports_response_schema": true, "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.000002, "max_input_tokens": 400000, "max_output_tokens": 128000, "max_tokens": 128000, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": false, "supports_tool_choice": true, "supports_reasoning": true, "supports_prompt_caching": true, "supports_web_search": true, "model_id": "openrouter/openai/gpt-5.1-codex-mini", "model_name": "GPT-5.1 Codex Mini", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.25, "output_cost_per_million": 2, "cache_read_cost_per_token": 3e-8, "cache_read_cost_per_million": 0.03, "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_vision": true, "supports_response_schema": true, "input_cost_per_token": 6.25e-7, "output_cost_per_token": 0.000005, "max_input_tokens": 400000, "max_output_tokens": 128000, "max_tokens": 128000, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/openai/gpt-5.1:batch", "model_name": "GPT-5.1:batch", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.625, "output_cost_per_million": 5, "cache_read_cost_per_token": 6.25e-8, "cache_read_cost_per_million": 0.0625, "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_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000175, "output_cost_per_token": 0.000014, "max_input_tokens": 400000, "max_output_tokens": 128000, "input_cost_per_image": 0, "max_tokens": 128000, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/openai/gpt-5.2", "model_name": "GPT-5.2", "provider_id": "openrouter", "provider_name": "OpenRouter", "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": false }, { "supports_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": 32000, "input_cost_per_image": 0, "max_tokens": 32000, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": false, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/openai/gpt-5.2-chat", "model_name": "GPT-5.2 Chat", "provider_id": "openrouter", "provider_name": "OpenRouter", "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": false }, { "supports_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": 400000, "max_output_tokens": 128000, "max_tokens": 128000, "source": "https://openrouter.ai/api/v1/models", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_audio_input": false, "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/openai/gpt-5.2-codex", "model_name": "GPT-5.2 Codex", "provider_id": "openrouter", "provider_name": "OpenRouter", "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": false }, { "supports_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": 400000, "max_output_tokens": 128000, "input_cost_per_image": 0, "max_tokens": 128000, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_prompt_caching": false, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/openai/gpt-5.2-pro", "model_name": "GPT-5.2 Pro", "provider_id": "openrouter", "provider_name": "OpenRouter", "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": "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": 0.0000105, "output_cost_per_token": 0.000084, "max_input_tokens": 400000, "max_output_tokens": 128000, "max_tokens": 128000, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_prompt_caching": false, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/openai/gpt-5.2-pro:batch", "model_name": "GPT-5.2 Pro:batch", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 10.5, "output_cost_per_million": 84, "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": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 8.75e-7, "output_cost_per_token": 0.000007, "max_input_tokens": 400000, "max_output_tokens": 128000, "max_tokens": 128000, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/openai/gpt-5.2:batch", "model_name": "GPT-5.2:batch", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.875, "output_cost_per_million": 7, "cache_read_cost_per_token": 8.75e-8, "cache_read_cost_per_million": 0.0875, "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_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000175, "output_cost_per_token": 0.000014, "max_input_tokens": 400000, "max_output_tokens": 128000, "max_tokens": 128000, "source": "https://openrouter.ai/api/v1/models", "supports_tool_choice": true, "supports_reasoning": true, "supports_pdf_input": true, "supports_audio_input": false, "supports_prompt_caching": true, "supports_web_search": true, "model_id": "openrouter/openai/gpt-5.3-codex", "model_name": "GPT-5.3 Codex", "provider_id": "openrouter", "provider_name": "OpenRouter", "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": false }, { "supports_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, "max_tokens": 128000, "source": "https://openrouter.ai/api/v1/models", "supports_tool_choice": true, "supports_reasoning": true, "supports_pdf_input": true, "supports_audio_input": false, "cache_read_input_token_cost_above_272k_tokens": 5e-7, "input_cost_per_token_above_272k_tokens": 0.000005, "output_cost_per_token_above_272k_tokens": 0.0000225, "supports_prompt_caching": true, "supports_web_search": true, "model_id": "openrouter/openai/gpt-5.4", "model_name": "GPT-5.4", "provider_id": "openrouter", "provider_name": "OpenRouter", "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": false }, { "supports_function_calling": false, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000008, "output_cost_per_token": 0.000015, "max_input_tokens": 272000, "max_output_tokens": 128000, "max_tokens": 128000, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": false, "supports_web_search": true, "model_id": "openrouter/openai/gpt-5.4-image-2", "model_name": "GPT-5.4 Image 2", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 8, "output_cost_per_million": 15, "cache_read_cost_per_token": 0.000002, "cache_read_cost_per_million": 2, "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_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, "max_tokens": 128000, "source": "https://openrouter.ai/api/v1/models", "supports_tool_choice": true, "supports_reasoning": true, "supports_pdf_input": true, "supports_audio_input": false, "supports_prompt_caching": true, "supports_web_search": true, "model_id": "openrouter/openai/gpt-5.4-mini", "model_name": "GPT-5.4 Mini", "provider_id": "openrouter", "provider_name": "OpenRouter", "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": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 3.75e-7, "output_cost_per_token": 0.00000225, "max_input_tokens": 400000, "max_output_tokens": 128000, "max_tokens": 128000, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/openai/gpt-5.4-mini:batch", "model_name": "GPT-5.4 Mini:batch", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.375, "output_cost_per_million": 2.25, "cache_read_cost_per_token": 3.75e-8, "cache_read_cost_per_million": 0.0375, "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_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, "max_tokens": 128000, "source": "https://openrouter.ai/api/v1/models", "supports_tool_choice": true, "supports_reasoning": true, "supports_pdf_input": true, "supports_audio_input": false, "supports_prompt_caching": true, "supports_web_search": true, "model_id": "openrouter/openai/gpt-5.4-nano", "model_name": "GPT-5.4 Nano", "provider_id": "openrouter", "provider_name": "OpenRouter", "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": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 1e-7, "output_cost_per_token": 6.25e-7, "max_input_tokens": 400000, "max_output_tokens": 128000, "max_tokens": 128000, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/openai/gpt-5.4-nano:batch", "model_name": "GPT-5.4 Nano:batch", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0.625, "cache_read_cost_per_token": 1e-8, "cache_read_cost_per_million": 0.01, "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_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00003, "output_cost_per_token": 0.00018, "max_input_tokens": 1050000, "max_output_tokens": 128000, "input_cost_per_token_above_272k_tokens": 0.00006, "output_cost_per_token_above_272k_tokens": 0.00027, "max_tokens": 128000, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_tool_choice": true, "supports_reasoning": true, "supports_pdf_input": true, "supports_prompt_caching": false, "supports_web_search": true, "model_id": "openrouter/openai/gpt-5.4-pro", "model_name": "GPT-5.4 Pro", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 30, "output_cost_per_million": 180, "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": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000015, "output_cost_per_token": 0.00009, "max_input_tokens": 1050000, "max_output_tokens": 128000, "input_cost_per_token_above_272k_tokens": 0.00003, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.000135, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_prompt_caching": false, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/openai/gpt-5.4-pro:batch", "model_name": "GPT-5.4 Pro:batch", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 15, "output_cost_per_million": 90, "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": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.0000075, "max_input_tokens": 1050000, "max_output_tokens": 128000, "cache_read_input_token_cost_above_272k_tokens": 2.5e-7, "input_cost_per_token_above_272k_tokens": 0.0000025, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.00001125, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/openai/gpt-5.4:batch", "model_name": "GPT-5.4:batch", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 1.25, "output_cost_per_million": 7.5, "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_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, "max_tokens": 128000, "source": "https://openrouter.ai/api/v1/models", "supports_tool_choice": true, "supports_reasoning": true, "supports_pdf_input": true, "supports_audio_input": false, "cache_read_input_token_cost_above_272k_tokens": 0.000001, "input_cost_per_token_above_272k_tokens": 0.00001, "output_cost_per_token_above_272k_tokens": 0.000045, "supports_prompt_caching": true, "supports_web_search": true, "model_id": "openrouter/openai/gpt-5.5", "model_name": "GPT-5.5", "provider_id": "openrouter", "provider_name": "OpenRouter", "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": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00003, "output_cost_per_token": 0.00018, "max_input_tokens": 1050000, "max_output_tokens": 128000, "input_cost_per_token_above_272k_tokens": 0.00006, "output_cost_per_token_above_272k_tokens": 0.00027, "max_tokens": 128000, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_tool_choice": true, "supports_reasoning": true, "supports_pdf_input": true, "supports_prompt_caching": false, "supports_web_search": true, "model_id": "openrouter/openai/gpt-5.5-pro", "model_name": "GPT-5.5 Pro", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 30, "output_cost_per_million": 180, "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": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000015, "output_cost_per_token": 0.00009, "max_input_tokens": 1050000, "max_output_tokens": 128000, "input_cost_per_token_above_272k_tokens": 0.00003, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.000135, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_prompt_caching": false, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/openai/gpt-5.5-pro:batch", "model_name": "GPT-5.5 Pro:batch", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 15, "output_cost_per_million": 90, "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": false }, { "supports_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, "input_cost_per_token_above_272k_tokens": 0.000005, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.0000225, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/openai/gpt-5.5:batch", "model_name": "GPT-5.5:batch", "provider_id": "openrouter", "provider_name": "OpenRouter", "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": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2e-7, "output_cost_per_token": 0.0000012, "max_input_tokens": 1050000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_272k_tokens": 5e-7, "max_tokens": 128000, "source": "https://openrouter.ai/api/v1/models", "supports_tool_choice": true, "supports_reasoning": true, "supports_pdf_input": true, "supports_audio_input": false, "cache_read_input_token_cost_above_272k_tokens": 4e-8, "input_cost_per_token_above_272k_tokens": 4e-7, "output_cost_per_token_above_272k_tokens": 0.0000018, "supports_prompt_caching": true, "supports_web_search": true, "model_id": "openrouter/openai/gpt-5.6-luna", "model_name": "GPT-5.6 Luna", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.19999999999999998, "output_cost_per_million": 1.2, "cache_read_cost_per_token": 2e-8, "cache_read_cost_per_million": 0.02, "cache_write_cost_per_token": 2.5e-7, "cache_write_cost_per_million": 0.25, "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": 2e-7, "output_cost_per_token": 0.0000012, "max_input_tokens": 1050000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_272k_tokens": 5e-7, "input_cost_per_token_above_272k_tokens": 4e-7, "output_cost_per_token_above_272k_tokens": 0.0000018, "cache_read_input_token_cost_above_272k_tokens": 4e-8, "max_tokens": 128000, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_tool_choice": true, "supports_reasoning": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_web_search": true, "model_id": "openrouter/openai/gpt-5.6-luna-pro", "model_name": "GPT-5.6 Luna Pro", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.19999999999999998, "output_cost_per_million": 1.2, "cache_read_cost_per_token": 2e-8, "cache_read_cost_per_million": 0.02, "cache_write_cost_per_token": 2.5e-7, "cache_write_cost_per_million": 0.25, "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": 1e-7, "output_cost_per_token": 6e-7, "max_input_tokens": 1050000, "max_output_tokens": 128000, "cache_read_input_token_cost_above_272k_tokens": 2e-8, "input_cost_per_token_above_272k_tokens": 2e-7, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 9e-7, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/openai/gpt-5.6-luna-pro:batch", "model_name": "GPT-5.6 Luna Pro:batch", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0.6, "cache_read_cost_per_token": 1e-8, "cache_read_cost_per_million": 0.01, "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_vision": true, "supports_response_schema": true, "input_cost_per_token": 1e-7, "output_cost_per_token": 6e-7, "max_input_tokens": 1050000, "max_output_tokens": 128000, "cache_read_input_token_cost_above_272k_tokens": 2e-8, "input_cost_per_token_above_272k_tokens": 2e-7, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 9e-7, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/openai/gpt-5.6-luna:batch", "model_name": "GPT-5.6 Luna:batch", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0.6, "cache_read_cost_per_token": 1e-8, "cache_read_cost_per_million": 0.01, "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_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.00001, "max_input_tokens": 1050000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_272k_tokens": 0.000005, "cache_read_input_token_cost_above_272k_tokens": 4e-7, "default_reasoning_effort": "medium", "input_cost_per_token_above_272k_tokens": 0.000004, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.000015, "reasoning_effort_levels": [ "none", "low", "medium", "high", "xhigh", "max" ], "source": "https://openrouter.ai/api/v1/models", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_audio_input": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/openai/gpt-5.6-sol", "model_name": "GPT-5.6 Sol", "provider_id": "openrouter", "provider_name": "OpenRouter", "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 }, { "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": 1050000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_272k_tokens": 0.000005, "cache_read_input_token_cost_above_272k_tokens": 4e-7, "input_cost_per_token_above_272k_tokens": 0.000004, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.000015, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/openai/gpt-5.6-sol-pro", "model_name": "GPT-5.6 Sol Pro", "provider_id": "openrouter", "provider_name": "OpenRouter", "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 }, { "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": 1050000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_272k_tokens": 0.0000025, "cache_read_input_token_cost_above_272k_tokens": 2e-7, "input_cost_per_token_above_272k_tokens": 0.000002, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.0000075, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/openai/gpt-5.6-sol-pro:batch", "model_name": "GPT-5.6 Sol Pro:batch", "provider_id": "openrouter", "provider_name": "OpenRouter", "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": 0.000001, "output_cost_per_token": 0.000005, "max_input_tokens": 1050000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_272k_tokens": 0.0000025, "cache_read_input_token_cost_above_272k_tokens": 2e-7, "input_cost_per_token_above_272k_tokens": 0.000002, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.0000075, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/openai/gpt-5.6-sol:batch", "model_name": "GPT-5.6 Sol:batch", "provider_id": "openrouter", "provider_name": "OpenRouter", "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": 0.000002, "output_cost_per_token": 0.000012, "max_input_tokens": 1050000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_272k_tokens": 0.000005, "max_tokens": 128000, "source": "https://openrouter.ai/api/v1/models", "supports_tool_choice": true, "supports_reasoning": true, "supports_pdf_input": true, "supports_audio_input": false, "cache_read_input_token_cost_above_272k_tokens": 4e-7, "input_cost_per_token_above_272k_tokens": 0.000004, "output_cost_per_token_above_272k_tokens": 0.000018, "supports_prompt_caching": true, "supports_web_search": true, "model_id": "openrouter/openai/gpt-5.6-terra", "model_name": "GPT-5.6 Terra", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 2, "output_cost_per_million": 12, "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 }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000012, "max_input_tokens": 1050000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_272k_tokens": 0.000005, "input_cost_per_token_above_272k_tokens": 0.000004, "output_cost_per_token_above_272k_tokens": 0.000018, "cache_read_input_token_cost_above_272k_tokens": 4e-7, "max_tokens": 128000, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_tool_choice": true, "supports_reasoning": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_web_search": true, "model_id": "openrouter/openai/gpt-5.6-terra-pro", "model_name": "GPT-5.6 Terra Pro", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 2, "output_cost_per_million": 12, "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 }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000006, "max_input_tokens": 1050000, "max_output_tokens": 128000, "cache_read_input_token_cost_above_272k_tokens": 2e-7, "input_cost_per_token_above_272k_tokens": 0.000002, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.000009, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/openai/gpt-5.6-terra-pro:batch", "model_name": "GPT-5.6 Terra Pro:batch", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 1, "output_cost_per_million": 6, "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": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000006, "max_input_tokens": 1050000, "max_output_tokens": 128000, "cache_read_input_token_cost_above_272k_tokens": 2e-7, "input_cost_per_token_above_272k_tokens": 0.000002, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.000009, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/openai/gpt-5.6-terra:batch", "model_name": "GPT-5.6 Terra:batch", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 1, "output_cost_per_million": 6, "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": false }, { "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": 1050000, "max_output_tokens": 128000, "input_cost_per_token_above_272k_tokens": 0.00002, "output_cost_per_token_above_272k_tokens": 0.000075, "cache_read_input_token_cost_above_272k_tokens": 0.000002, "cache_creation_input_token_cost_above_272k_tokens": 0.000025, "max_tokens": 128000, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_tool_choice": true, "supports_reasoning": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_web_search": true, "model_id": "openrouter/openai/gpt-6-astra", "model_name": "GPT-6 Astra", "provider_id": "openrouter", "provider_name": "OpenRouter", "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": 0.00001, "output_cost_per_token": 0.00005, "max_input_tokens": 1050000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_272k_tokens": 0.000025, "input_cost_per_token_above_272k_tokens": 0.00002, "output_cost_per_token_above_272k_tokens": 0.000075, "cache_read_input_token_cost_above_272k_tokens": 0.000002, "max_tokens": 128000, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_tool_choice": true, "supports_reasoning": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_web_search": true, "model_id": "openrouter/openai/gpt-6-astra-pro", "model_name": "GPT-6 Astra Pro", "provider_id": "openrouter", "provider_name": "OpenRouter", "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": 0.000005, "output_cost_per_token": 0.000025, "max_input_tokens": 1050000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_272k_tokens": 0.0000125, "cache_read_input_token_cost_above_272k_tokens": 0.000001, "input_cost_per_token_above_272k_tokens": 0.00001, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.0000375, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/openai/gpt-6-astra-pro:batch", "model_name": "GPT-6 Astra Pro:batch", "provider_id": "openrouter", "provider_name": "OpenRouter", "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": 1050000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_272k_tokens": 0.0000125, "cache_read_input_token_cost_above_272k_tokens": 0.000001, "input_cost_per_token_above_272k_tokens": 0.00001, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.0000375, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/openai/gpt-6-astra:batch", "model_name": "GPT-6 Astra:batch", "provider_id": "openrouter", "provider_name": "OpenRouter", "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": 1e-7, "output_cost_per_token": 5e-7, "max_input_tokens": 1050000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_272k_tokens": 2.5e-7, "cache_read_input_token_cost_above_272k_tokens": 2e-8, "input_cost_per_token_above_272k_tokens": 2e-7, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 7.5e-7, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/openai/gpt-6-luna", "model_name": "GPT-6 Luna", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0.5, "cache_read_cost_per_token": 1e-8, "cache_read_cost_per_million": 0.01, "cache_write_cost_per_token": 1.25e-7, "cache_write_cost_per_million": 0.125, "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": 1e-7, "output_cost_per_token": 5e-7, "max_input_tokens": 1050000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_272k_tokens": 2.5e-7, "cache_read_input_token_cost_above_272k_tokens": 2e-8, "input_cost_per_token_above_272k_tokens": 2e-7, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 7.5e-7, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/openai/gpt-6-luna-pro", "model_name": "GPT-6 Luna Pro", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0.5, "cache_read_cost_per_token": 1e-8, "cache_read_cost_per_million": 0.01, "cache_write_cost_per_token": 1.25e-7, "cache_write_cost_per_million": 0.125, "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": 5e-8, "output_cost_per_token": 2.5e-7, "max_input_tokens": 1050000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_272k_tokens": 1.25e-7, "cache_read_input_token_cost_above_272k_tokens": 1e-8, "input_cost_per_token_above_272k_tokens": 1e-7, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 3.75e-7, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/openai/gpt-6-luna-pro:batch", "model_name": "GPT-6 Luna Pro:batch", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.049999999999999996, "output_cost_per_million": 0.25, "cache_read_cost_per_token": 5e-9, "cache_read_cost_per_million": 0.005, "cache_write_cost_per_token": 6.25e-8, "cache_write_cost_per_million": 0.0625, "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": 5e-8, "output_cost_per_token": 2.5e-7, "max_input_tokens": 1050000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_272k_tokens": 1.25e-7, "cache_read_input_token_cost_above_272k_tokens": 1e-8, "input_cost_per_token_above_272k_tokens": 1e-7, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 3.75e-7, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/openai/gpt-6-luna:batch", "model_name": "GPT-6 Luna:batch", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.049999999999999996, "output_cost_per_million": 0.25, "cache_read_cost_per_token": 5e-9, "cache_read_cost_per_million": 0.005, "cache_write_cost_per_token": 6.25e-8, "cache_write_cost_per_million": 0.0625, "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": 1050000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_272k_tokens": 0.000005, "cache_read_input_token_cost_above_272k_tokens": 4e-7, "input_cost_per_token_above_272k_tokens": 0.000004, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.000015, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/openai/gpt-6-sol", "model_name": "GPT-6 Sol", "provider_id": "openrouter", "provider_name": "OpenRouter", "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 }, { "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": 1050000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_272k_tokens": 0.000005, "cache_read_input_token_cost_above_272k_tokens": 4e-7, "input_cost_per_token_above_272k_tokens": 0.000004, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.000015, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/openai/gpt-6-sol-pro", "model_name": "GPT-6 Sol Pro", "provider_id": "openrouter", "provider_name": "OpenRouter", "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 }, { "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": 1050000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_272k_tokens": 0.0000025, "cache_read_input_token_cost_above_272k_tokens": 2e-7, "input_cost_per_token_above_272k_tokens": 0.000002, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.0000075, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/openai/gpt-6-sol-pro:batch", "model_name": "GPT-6 Sol Pro:batch", "provider_id": "openrouter", "provider_name": "OpenRouter", "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": 0.000001, "output_cost_per_token": 0.000005, "max_input_tokens": 1050000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_272k_tokens": 0.0000025, "cache_read_input_token_cost_above_272k_tokens": 2e-7, "input_cost_per_token_above_272k_tokens": 0.000002, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.0000075, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/openai/gpt-6-sol:batch", "model_name": "GPT-6 Sol:batch", "provider_id": "openrouter", "provider_name": "OpenRouter", "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": 0.000002, "output_cost_per_token": 0.00001, "max_input_tokens": 1050000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_272k_tokens": 0.000005, "cache_read_input_token_cost_above_272k_tokens": 2e-7, "input_cost_per_token_above_272k_tokens": 0.000004, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.000015, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/openai/gpt-6.1-sol", "model_name": "GPT-6.1 Sol", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 2, "output_cost_per_million": 10, "cache_read_cost_per_token": 1e-7, "cache_read_cost_per_million": 0.09999999999999999, "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 }, { "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": 1050000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_272k_tokens": 0.000005, "cache_read_input_token_cost_above_272k_tokens": 2e-7, "input_cost_per_token_above_272k_tokens": 0.000004, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.000015, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/openai/gpt-6.1-sol-pro", "model_name": "GPT-6.1 Sol Pro", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 2, "output_cost_per_million": 10, "cache_read_cost_per_token": 1e-7, "cache_read_cost_per_million": 0.09999999999999999, "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 }, { "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": 1050000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_272k_tokens": 0.0000025, "cache_read_input_token_cost_above_272k_tokens": 1e-7, "input_cost_per_token_above_272k_tokens": 0.000002, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.0000075, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/openai/gpt-6.1-sol-pro:batch", "model_name": "GPT-6.1 Sol Pro:batch", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 1, "output_cost_per_million": 5, "cache_read_cost_per_token": 5e-8, "cache_read_cost_per_million": 0.049999999999999996, "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": 0.000001, "output_cost_per_token": 0.000005, "max_input_tokens": 1050000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_272k_tokens": 0.0000025, "cache_read_input_token_cost_above_272k_tokens": 1e-7, "input_cost_per_token_above_272k_tokens": 0.000002, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.0000075, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/openai/gpt-6.1-sol:batch", "model_name": "GPT-6.1 Sol:batch", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 1, "output_cost_per_million": 5, "cache_read_cost_per_token": 5e-8, "cache_read_cost_per_million": 0.049999999999999996, "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": 0.000005, "output_cost_per_token": 0.00003, "max_input_tokens": 400000, "max_output_tokens": 128000, "max_tokens": 128000, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_tool_choice": true, "supports_reasoning": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_web_search": true, "model_id": "openrouter/openai/gpt-chat-latest", "model_name": "GPT Chat Latest", "provider_id": "openrouter", "provider_name": "OpenRouter", "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": false }, { "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": 0.00006, "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "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": "openrouter/openai/o1", "model_name": "o1", "provider_id": "openrouter", "provider_name": "OpenRouter", "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_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": false, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00015, "output_cost_per_token": 0.0006, "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_tool_choice": false, "supports_reasoning": true, "supports_pdf_input": true, "supports_prompt_caching": false, "supports_web_search": true, "model_id": "openrouter/openai/o1-pro", "model_name": "o1 Pro", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 150, "output_cost_per_million": 600, "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": false }, { "supports_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": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "source": "https://openrouter.ai/api/v1/models", "supports_tool_choice": true, "supports_reasoning": true, "supports_pdf_input": true, "supports_audio_input": false, "supports_prompt_caching": true, "supports_web_search": true, "model_id": "openrouter/openai/o3", "model_name": "o3", "provider_id": "openrouter", "provider_name": "OpenRouter", "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": 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_reasoning": true, "supports_tool_choice": true, "supports_prompt_caching": true, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_web_search": true, "model_id": "openrouter/openai/o3-mini", "model_name": "o3 mini", "provider_id": "openrouter", "provider_name": "OpenRouter", "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_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": 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_reasoning": true, "supports_tool_choice": true, "supports_prompt_caching": true, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_web_search": true, "model_id": "openrouter/openai/o3-mini-high", "model_name": "O3 Mini High", "provider_id": "openrouter", "provider_name": "OpenRouter", "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_parallel_functions": true }, { "supports_function_calling": true, "supports_vision": false, "supports_response_schema": true, "input_cost_per_token": 5.5e-7, "output_cost_per_token": 0.0000022, "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/openai/o3-mini:batch", "model_name": "O3 Mini:batch", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.55, "output_cost_per_million": 2.2, "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_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, "max_tokens": 100000, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_tool_choice": true, "supports_reasoning": true, "supports_pdf_input": true, "supports_prompt_caching": false, "supports_web_search": true, "model_id": "openrouter/openai/o3-pro", "model_name": "o3 Pro", "provider_id": "openrouter", "provider_name": "OpenRouter", "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": "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": 0.000004, "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/openai/o3:batch", "model_name": "O3:batch", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 1, "output_cost_per_million": 4, "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": false }, { "supports_function_calling": true, "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, "source": "https://openrouter.ai/api/v1/models", "supports_tool_choice": true, "supports_reasoning": true, "supports_pdf_input": true, "supports_audio_input": false, "supports_prompt_caching": true, "supports_web_search": true, "model_id": "openrouter/openai/o4-mini", "model_name": "o4 mini", "provider_id": "openrouter", "provider_name": "OpenRouter", "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_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, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_tool_choice": true, "supports_reasoning": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_web_search": true, "model_id": "openrouter/openai/o4-mini-high", "model_name": "O4 Mini High", "provider_id": "openrouter", "provider_name": "OpenRouter", "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_vision": true, "supports_response_schema": true, "input_cost_per_token": 5.5e-7, "output_cost_per_token": 0.0000022, "max_input_tokens": 200000, "max_output_tokens": 100000, "max_tokens": 100000, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/openai/o4-mini:batch", "model_name": "O4 Mini:batch", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.55, "output_cost_per_million": 2.2, "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": false }, { "supports_function_calling": false, "supports_vision": true, "supports_response_schema": false, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000001, "max_input_tokens": 127072, "max_output_tokens": 114364, "max_tokens": 114364, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": false, "supports_prompt_caching": false, "supports_reasoning": false, "supports_tool_choice": false, "supports_web_search": true, "model_id": "openrouter/perplexity/sonar", "model_name": "Sonar", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 1, "output_cost_per_million": 1, "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": false, "supports_vision": false, "supports_response_schema": false, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000008, "max_input_tokens": 128000, "max_output_tokens": 115200, "max_tokens": 115200, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": false, "supports_prompt_caching": false, "supports_reasoning": true, "supports_tool_choice": false, "supports_web_search": true, "model_id": "openrouter/perplexity/sonar-deep-research", "model_name": "Sonar Deep Research", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 2, "output_cost_per_million": 8, "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": false, "supports_vision": true, "supports_response_schema": false, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 200000, "max_output_tokens": 8000, "max_tokens": 8000, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": false, "supports_prompt_caching": false, "supports_reasoning": false, "supports_tool_choice": false, "supports_web_search": true, "model_id": "openrouter/perplexity/sonar-pro", "model_name": "Sonar Pro", "provider_id": "openrouter", "provider_name": "OpenRouter", "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_parallel_functions": false }, { "supports_function_calling": false, "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": 8000, "max_tokens": 8000, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": false, "supports_prompt_caching": false, "supports_reasoning": true, "supports_tool_choice": false, "supports_web_search": true, "model_id": "openrouter/perplexity/sonar-pro-search", "model_name": "Sonar Pro Search", "provider_id": "openrouter", "provider_name": "OpenRouter", "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_parallel_functions": false }, { "supports_function_calling": false, "supports_vision": true, "supports_response_schema": false, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000008, "max_input_tokens": 128000, "max_output_tokens": 115200, "max_tokens": 115200, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": false, "supports_prompt_caching": false, "supports_reasoning": true, "supports_tool_choice": false, "supports_web_search": true, "model_id": "openrouter/perplexity/sonar-reasoning-pro", "model_name": "Sonar Reasoning Pro", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 2, "output_cost_per_million": 8, "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, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000006, "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/sakana/fugu-max", "model_name": "Fugu Max", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 2, "output_cost_per_million": 6, "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": false }, { "supports_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": 1000000, "max_output_tokens": 128000, "cache_read_input_token_cost_above_272k_tokens": 0.000001, "input_cost_per_token_above_272k_tokens": 0.00001, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.000045, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": false, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/sakana/fugu-ultra", "model_name": "Fugu Ultra", "provider_id": "openrouter", "provider_name": "OpenRouter", "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": false }, { "supports_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": 1000000, "max_output_tokens": 128000, "cache_read_input_token_cost_above_272k_tokens": 0.000001, "input_cost_per_token_above_272k_tokens": 0.00001, "max_tokens": 128000, "output_cost_per_token_above_272k_tokens": 0.000045, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/sakana/fugu-ultra-v2", "model_name": "Fugu Ultra V2", "provider_id": "openrouter", "provider_name": "OpenRouter", "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": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 9.5e-7, "output_cost_per_token": 0.000004, "max_input_tokens": 262144, "max_output_tokens": 65536, "max_tokens": 65536, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/sakana/sakana-namazu", "model_name": "Sakana Namazu", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.95, "output_cost_per_million": 4, "cache_read_cost_per_token": 1.5e-7, "cache_read_cost_per_million": 0.15, "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, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 256000, "max_output_tokens": 256000, "max_tokens": 256000, "source": "https://openrouter.ai/x-ai/grok-4", "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/x-ai/grok-4", "model_name": "Grok 4", "provider_id": "openrouter", "provider_name": "OpenRouter", "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_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.0000025, "max_input_tokens": 2000000, "max_output_tokens": 1800000, "max_tokens": 1800000, "source": "https://openrouter.ai/api/v1/models", "supports_tool_choice": true, "supports_reasoning": true, "supports_pdf_input": true, "supports_audio_input": false, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000005, "supports_prompt_caching": true, "supports_web_search": true, "model_id": "openrouter/x-ai/grok-4.20", "model_name": "Grok 4.20", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 1.25, "output_cost_per_million": 2.5, "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": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": false, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.0000025, "max_input_tokens": 2000000, "max_output_tokens": 1800000, "max_tokens": 1800000, "source": "https://openrouter.ai/api/v1/models", "supports_tool_choice": false, "supports_reasoning": true, "supports_pdf_input": true, "supports_audio_input": false, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000005, "supports_prompt_caching": true, "supports_web_search": true, "model_id": "openrouter/x-ai/grok-4.20-multi-agent", "model_name": "Grok 4.20 Multi Agent", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 1.25, "output_cost_per_million": 2.5, "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": "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": 0.00000125, "output_cost_per_token": 0.0000025, "max_input_tokens": 1000000, "max_output_tokens": 900000, "max_tokens": 900000, "source": "https://openrouter.ai/api/v1/models", "supports_tool_choice": true, "supports_reasoning": true, "supports_pdf_input": true, "supports_audio_input": false, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000005, "supports_prompt_caching": true, "supports_web_search": true, "model_id": "openrouter/x-ai/grok-4.3", "model_name": "Grok 4.3", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 1.25, "output_cost_per_million": 2.5, "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": "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": 0.000002, "max_input_tokens": 1000000, "max_output_tokens": 900000, "cache_read_input_token_cost_above_200k_tokens": 3.2e-7, "input_cost_per_token_above_200k_tokens": 0.000002, "max_tokens": 900000, "output_cost_per_token_above_200k_tokens": 0.000004, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/x-ai/grok-4.3:batch", "model_name": "Grok 4.3:batch", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 1, "output_cost_per_million": 2, "cache_read_cost_per_token": 1.6e-7, "cache_read_cost_per_million": 0.16, "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_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000006, "max_input_tokens": 500000, "max_output_tokens": 450000, "max_tokens": 450000, "source": "https://openrouter.ai/api/v1/models", "supports_tool_choice": true, "supports_reasoning": true, "supports_pdf_input": true, "supports_audio_input": false, "cache_read_input_token_cost_above_200k_tokens": 6e-7, "input_cost_per_token_above_200k_tokens": 0.000004, "output_cost_per_token_above_200k_tokens": 0.000012, "supports_prompt_caching": true, "supports_web_search": true, "model_id": "openrouter/x-ai/grok-4.5", "model_name": "Grok 4.5", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 2, "output_cost_per_million": 6, "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_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": 0.000006, "max_input_tokens": 500000, "max_output_tokens": 450000, "max_tokens": 450000, "source": "https://openrouter.ai/api/v1/models", "supports_tool_choice": true, "supports_reasoning": true, "supports_pdf_input": true, "supports_audio_input": false, "cache_read_input_token_cost_above_200k_tokens": 0.000001, "input_cost_per_token_above_200k_tokens": 0.000004, "output_cost_per_token_above_200k_tokens": 0.000012, "supports_prompt_caching": true, "supports_web_search": true, "model_id": "openrouter/x-ai/grok-4.6", "model_name": "Grok 4.6", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 2, "output_cost_per_million": 6, "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_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000006, "max_input_tokens": 500000, "max_output_tokens": 450000, "cache_read_input_token_cost_above_200k_tokens": 0.000001, "input_cost_per_token_above_200k_tokens": 0.000004, "max_tokens": 450000, "output_cost_per_token_above_200k_tokens": 0.000012, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "openrouter/x-ai/grok-4.7", "model_name": "Grok 4.7", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 2, "output_cost_per_million": 6, "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_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000002, "max_input_tokens": 256000, "max_output_tokens": 230400, "max_tokens": 230400, "source": "https://openrouter.ai/api/v1/models", "supports_tool_choice": true, "supports_reasoning": true, "supports_pdf_input": true, "supports_audio_input": false, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "input_cost_per_token_above_200k_tokens": 0.000002, "output_cost_per_token_above_200k_tokens": 0.000004, "supports_prompt_caching": true, "supports_web_search": true, "model_id": "openrouter/x-ai/grok-build-0.1", "model_name": "Grok Build 0.1", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 1, "output_cost_per_million": 2, "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": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.00001, "output_cost_per_token": 0.00005, "supports_adaptive_thinking": true, "thinking_always_on": true, "supports_web_search": true, "source": "https://docs.perplexity.ai/docs/agent-api/models", "model_id": "anthropic/claude-fable-5", "model_name": "Claude Fable 5", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "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, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 1e-7, "output_cost_per_token": 5e-7, "supports_adaptive_thinking": true, "supports_web_search": true, "source": "https://docs.perplexity.ai/docs/agent-api/models", "model_id": "anthropic/claude-haiku-5-5", "model_name": "Claude Haiku 5 5", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0.5, "cache_read_cost_per_token": 1e-8, "cache_read_cost_per_million": 0.01, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025, "supports_web_search": true, "supports_reasoning": false, "supports_output_config": true, "source": "https://docs.perplexity.ai/docs/agent-api/models", "model_id": "anthropic/claude-opus-4-5", "model_name": "Claude Opus 4 5", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "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, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025, "supports_adaptive_thinking": true, "supports_legacy_thinking": true, "supports_web_search": true, "supports_reasoning": false, "supports_output_config": true, "source": "https://docs.perplexity.ai/docs/agent-api/models", "model_id": "anthropic/claude-opus-4-6", "model_name": "Claude Opus 4 6", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "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, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025, "supports_adaptive_thinking": true, "supports_web_search": true, "source": "https://docs.perplexity.ai/docs/agent-api/models", "model_id": "anthropic/claude-opus-4-8", "model_name": "Claude Opus 4 8", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "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, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025, "supports_adaptive_thinking": true, "prompt_cache_min_tokens": 512, "supports_web_search": true, "source": "https://docs.perplexity.ai/docs/agent-api/models", "model_id": "anthropic/claude-opus-5", "model_name": "Claude Opus 5", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "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, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "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": 0.000015, "supports_web_search": true, "supports_reasoning": false, "source": "https://docs.perplexity.ai/docs/agent-api/models", "model_id": "anthropic/claude-sonnet-4-5", "model_name": "Claude Sonnet 4 5", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "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, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "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": 0.000015, "supports_web_search": true, "source": "https://docs.perplexity.ai/docs/agent-api/models", "model_id": "anthropic/claude-sonnet-4-6", "model_name": "Claude Sonnet 4 6", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "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, "cache_write_cost_per_million": 0, "model_type": "responses", "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": 0.00001, "supports_adaptive_thinking": true, "supports_web_search": true, "source": "https://docs.perplexity.ai/docs/agent-api/models", "model_id": "anthropic/claude-sonnet-5", "model_name": "Claude Sonnet 5", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "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, "cache_write_cost_per_million": 0, "model_type": "responses", "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": 0.00001, "supports_adaptive_thinking": true, "supports_web_search": true, "source": "https://docs.perplexity.ai/docs/agent-api/models", "model_id": "anthropic/claude-sonnet-5-5", "model_name": "Claude Sonnet 5 5", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "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, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_web_search": true, "supports_reasoning": false, "model_id": "google/gemini-2.5-pro", "model_name": "Gemini 2.5 Pro", "provider_id": "perplexity", "provider_name": "Perplexity AI", "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": "responses", "deprecation_date": null, "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": 0.000003, "supports_web_search": true, "supports_reasoning": false, "source": "https://docs.perplexity.ai/docs/agent-api/models", "model_id": "google/gemini-3-flash-preview", "model_name": "Gemini 3 Flash Preview", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 0.5, "output_cost_per_million": 3, "cache_read_cost_per_token": 5e-8, "cache_read_cost_per_million": 0.049999999999999996, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_web_search": true, "supports_reasoning": false, "model_id": "google/gemini-3-pro-preview", "model_name": "Gemini 3 Pro Preview", "provider_id": "perplexity", "provider_name": "Perplexity AI", "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": "responses", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.0000015, "supports_web_search": true, "source": "https://docs.perplexity.ai/docs/agent-api/models", "model_id": "google/gemini-3.1-flash-lite", "model_name": "Gemini 3.1 Flash Lite", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 0.25, "output_cost_per_million": 1.5, "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_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000012, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 0.000004, "output_cost_per_token_above_200k_tokens": 0.000018, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "source": "https://docs.perplexity.ai/docs/agent-api/models", "model_id": "google/gemini-3.1-pro-preview", "model_name": "Gemini 3.1 Pro Preview", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 2, "output_cost_per_million": 12, "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": "responses", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.0000015, "output_cost_per_token": 0.000009, "supports_web_search": true, "source": "https://docs.perplexity.ai/docs/agent-api/models", "model_id": "google/gemini-3.5-flash", "model_name": "Gemini 3.5 Flash", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 1.5, "output_cost_per_million": 9, "cache_read_cost_per_token": 1.5e-7, "cache_read_cost_per_million": 0.15, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000025, "supports_web_search": true, "source": "https://docs.perplexity.ai/docs/agent-api/models", "model_id": "google/gemini-3.5-flash-lite", "model_name": "Gemini 3.5 Flash Lite", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 0.3, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 3e-8, "cache_read_cost_per_million": 0.03, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.0000015, "output_cost_per_token": 0.0000075, "supports_web_search": true, "source": "https://docs.perplexity.ai/docs/agent-api/models", "model_id": "google/gemini-3.6-flash", "model_name": "Gemini 3.6 Flash", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 1.5, "output_cost_per_million": 7.5, "cache_read_cost_per_token": 1.5e-7, "cache_read_cost_per_million": 0.15, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 7.5e-7, "output_cost_per_token": 0.00000375, "supports_web_search": true, "source": "https://docs.perplexity.ai/docs/agent-api/models", "model_id": "google/gemini-3.7-flash", "model_name": "Gemini 3.7 Flash", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 0.75, "output_cost_per_million": 3.75, "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": "responses", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "supports_web_search": true, "source": "https://docs.perplexity.ai/docs/agent-api/models", "model_id": "openai/gpt-5", "model_name": "GPT-5", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "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_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "supports_web_search": true, "supports_reasoning": false, "source": "https://docs.perplexity.ai/docs/agent-api/models", "model_id": "openai/gpt-5.1", "model_name": "GPT-5.1", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "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_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.00000175, "output_cost_per_token": 0.000014, "supports_web_search": true, "supports_reasoning": true, "source": "https://docs.perplexity.ai/docs/agent-api/models", "model_id": "openai/gpt-5.2", "model_name": "GPT-5.2", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "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_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.000015, "supports_web_search": true, "input_cost_per_token_above_272k_tokens": 0.000005, "output_cost_per_token_above_272k_tokens": 0.0000225, "source": "https://docs.perplexity.ai/docs/agent-api/models", "model_id": "openai/gpt-5.4", "model_name": "GPT-5.4", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "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": "responses", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 7.5e-7, "output_cost_per_token": 0.0000045, "supports_web_search": true, "source": "https://docs.perplexity.ai/docs/agent-api/models", "model_id": "openai/gpt-5.4-mini", "model_name": "GPT-5.4 Mini", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "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": "responses", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 2e-7, "output_cost_per_token": 0.00000125, "supports_web_search": true, "source": "https://docs.perplexity.ai/docs/agent-api/models", "model_id": "openai/gpt-5.4-nano", "model_name": "GPT-5.4 Nano", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "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": "responses", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.00003, "supports_web_search": true, "input_cost_per_token_above_272k_tokens": 0.00001, "output_cost_per_token_above_272k_tokens": 0.000045, "source": "https://docs.perplexity.ai/docs/agent-api/models", "model_id": "openai/gpt-5.5", "model_name": "GPT-5.5", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "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": "responses", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 2e-7, "output_cost_per_token": 0.0000012, "supports_web_search": true, "input_cost_per_token_above_272k_tokens": 4e-7, "output_cost_per_token_above_272k_tokens": 0.0000018, "cache_read_input_token_cost_above_272k_tokens": 4e-8, "source": "https://docs.perplexity.ai/docs/agent-api/models", "model_id": "openai/gpt-5.6-luna", "model_name": "GPT-5.6 Luna", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 0.19999999999999998, "output_cost_per_million": 1.2, "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": "responses", "deprecation_date": null, "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": 0.00002, "supports_web_search": true, "input_cost_per_token_above_272k_tokens": 0.000008, "output_cost_per_token_above_272k_tokens": 0.00003, "cache_read_input_token_cost_above_272k_tokens": 8e-7, "source": "https://docs.perplexity.ai/docs/agent-api/models", "model_id": "openai/gpt-5.6-sol", "model_name": "GPT-5.6 Sol", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 4, "output_cost_per_million": 20, "cache_read_cost_per_token": 4e-7, "cache_read_cost_per_million": 0.39999999999999997, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "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": 0.000012, "supports_web_search": true, "input_cost_per_token_above_272k_tokens": 0.000004, "output_cost_per_token_above_272k_tokens": 0.000018, "cache_read_input_token_cost_above_272k_tokens": 4e-7, "source": "https://docs.perplexity.ai/docs/agent-api/models", "model_id": "openai/gpt-5.6-terra", "model_name": "GPT-5.6 Terra", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 2, "output_cost_per_million": 12, "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": "responses", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 1.3e-7, "output_cost_per_token": 2.6e-7, "source": "https://docs.perplexity.ai/docs/agent-api/models", "supports_web_search": true, "supports_reasoning": true, "model_id": "perplexity/deepseek-v4-flash-0731", "model_name": "Deepseek V4 Flash 0731", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 0.13, "output_cost_per_million": 0.26, "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_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.0000014, "output_cost_per_token": 0.0000044, "source": "https://docs.perplexity.ai/docs/agent-api/models", "supports_web_search": true, "supports_reasoning": true, "model_id": "perplexity/glm-5.2", "model_name": "Glm 5.2", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 1.4, "output_cost_per_million": 4.4, "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_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.0000014, "output_cost_per_token": 0.0000044, "supports_web_search": true, "source": "https://docs.perplexity.ai/docs/agent-api/models", "model_id": "perplexity/glm-5.3", "model_name": "Glm 5.3", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 1.4, "output_cost_per_million": 4.4, "cache_read_cost_per_token": 2.6e-7, "cache_read_cost_per_million": 0.26, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "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": 5e-7, "supports_web_search": true, "source": "https://docs.perplexity.ai/docs/agent-api/models", "model_id": "perplexity/glm-5.3-flash", "model_name": "Glm 5.3 Flash", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 0.15, "output_cost_per_million": 0.5, "cache_read_cost_per_token": 3e-8, "cache_read_cost_per_million": 0.03, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 9.5e-7, "output_cost_per_token": 0.000004, "source": "https://docs.perplexity.ai/docs/agent-api/models", "supports_web_search": true, "supports_reasoning": false, "model_id": "perplexity/kimi-k2.7-code", "model_name": "Kimi K2.7 Code", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 0.95, "output_cost_per_million": 4, "cache_read_cost_per_token": 1.9e-7, "cache_read_cost_per_million": 0.19, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "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": 0.000015, "reasoning_effort_levels": [ "minimal", "low", "medium", "high", "xhigh", "max" ], "source": "https://docs.perplexity.ai/docs/agent-api/models", "supports_web_search": true, "supports_reasoning": true, "model_id": "perplexity/kimi-k3", "model_name": "Kimi K3", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "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, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.0000025, "supports_web_search": true, "supports_reasoning": true, "source": "https://docs.perplexity.ai/docs/agent-api/models", "model_id": "perplexity/nemotron-3-ultra-550b-a55b", "model_name": "Nemotron 3 Ultra 550B A55B", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 0.25, "output_cost_per_million": 2.5, "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": "responses", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 1.15e-8, "output_cost_per_token": 1.7e-7, "supports_web_search": true, "supports_reasoning": true, "source": "https://docs.perplexity.ai/docs/agent-api/models", "model_id": "perplexity/nemotron-3.5-lightning-30b-a3b", "model_name": "Nemotron 3.5 Lightning 30B A3B", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 0.0115, "output_cost_per_million": 0.16999999999999998, "cache_read_cost_per_token": 1.15e-9, "cache_read_cost_per_million": 0.00115, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.0000025, "supports_web_search": true, "supports_reasoning": false, "source": "https://docs.perplexity.ai/docs/agent-api/models", "model_id": "perplexity/sonar", "model_name": "Sonar", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 0.25, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 6.25e-8, "cache_read_cost_per_million": 0.0625, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "responses", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_web_search": true, "model_id": "preset/advanced-deep-research", "model_name": "Advanced Deep Research", "provider_id": "perplexity", "provider_name": "Perplexity AI", "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": "responses", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_web_search": true, "model_id": "preset/deep-research", "model_name": "Deep Research", "provider_id": "perplexity", "provider_name": "Perplexity AI", "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": "responses", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_web_search": true, "model_id": "preset/fast-search", "model_name": "Fast Search", "provider_id": "perplexity", "provider_name": "Perplexity AI", "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": "responses", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_web_search": true, "model_id": "preset/pro-search", "model_name": "Pro Search", "provider_id": "perplexity", "provider_name": "Perplexity AI", "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": "responses", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000001, "max_input_tokens": 128000, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.012, "search_context_size_low": 0.005, "search_context_size_medium": 0.008 }, "supports_web_search": true, "model_id": "sonar", "model_name": "Sonar", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_output_tokens": 0, "input_cost_per_million": 1, "output_cost_per_million": 1, "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": 0.000002, "output_cost_per_token": 0.000008, "max_input_tokens": 128000, "citation_cost_per_token": 0.000002, "max_tokens": 128000, "output_cost_per_reasoning_token": 0.000003, "search_context_cost_per_query": { "search_context_size_high": 0.005, "search_context_size_low": 0.005, "search_context_size_medium": 0.005 }, "supports_reasoning": true, "supports_web_search": true, "model_id": "sonar-deep-research", "model_name": "Sonar Deep Research", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_output_tokens": 0, "input_cost_per_million": 2, "output_cost_per_million": 8, "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": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 200000, "max_output_tokens": 8000, "max_tokens": 8000, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.006, "search_context_size_medium": 0.01 }, "supports_web_search": true, "model_id": "sonar-pro", "model_name": "Sonar Pro", "provider_id": "perplexity", "provider_name": "Perplexity AI", "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_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000005, "max_input_tokens": 128000, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.005, "search_context_size_medium": 0.008 }, "supports_reasoning": true, "supports_web_search": true, "model_id": "sonar-reasoning", "model_name": "Sonar Reasoning", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_output_tokens": 0, "input_cost_per_million": 1, "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": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000008, "max_input_tokens": 128000, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.014, "search_context_size_low": 0.006, "search_context_size_medium": 0.01 }, "supports_reasoning": true, "supports_web_search": true, "model_id": "sonar-reasoning-pro", "model_name": "Sonar Reasoning Pro", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_output_tokens": 0, "input_cost_per_million": 2, "output_cost_per_million": 8, "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_web_search": true, "supports_reasoning": false, "model_id": "xai/grok-4-1-fast-non-reasoning", "model_name": "Grok 4 1 Fast Non Reasoning", "provider_id": "perplexity", "provider_name": "Perplexity AI", "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": "responses", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.0000025, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000005, "source": "https://docs.perplexity.ai/docs/agent-api/models", "model_id": "xai/grok-4.20-multi-agent", "model_name": "Grok 4.20 Multi Agent", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 1.25, "output_cost_per_million": 2.5, "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": "responses", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.0000025, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000005, "source": "https://docs.perplexity.ai/docs/agent-api/models", "model_id": "xai/grok-4.20-non-reasoning", "model_name": "Grok 4.20 Non Reasoning", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 1.25, "output_cost_per_million": 2.5, "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": "responses", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.0000025, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000005, "source": "https://docs.perplexity.ai/docs/agent-api/models", "model_id": "xai/grok-4.20-reasoning", "model_name": "Grok 4.20 Reasoning", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 1.25, "output_cost_per_million": 2.5, "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": "responses", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.0000025, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000005, "source": "https://docs.perplexity.ai/docs/agent-api/models", "model_id": "xai/grok-4.3", "model_name": "Grok 4.3", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 1.25, "output_cost_per_million": 2.5, "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": "responses", "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, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 0.000004, "output_cost_per_token_above_200k_tokens": 0.000012, "cache_read_input_token_cost_above_200k_tokens": 6e-7, "source": "https://docs.perplexity.ai/docs/agent-api/models", "model_id": "xai/grok-4.5", "model_name": "Grok 4.5", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 2, "output_cost_per_million": 6, "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": "responses", "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, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 0.000004, "output_cost_per_token_above_200k_tokens": 0.000012, "cache_read_input_token_cost_above_200k_tokens": 0.000001, "source": "https://docs.perplexity.ai/docs/agent-api/models", "model_id": "xai/grok-4.6", "model_name": "Grok 4.6", "provider_id": "perplexity", "provider_name": "Perplexity AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 2, "output_cost_per_million": 6, "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": "responses", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 1.5e-7, "output_cost_per_token": 4.7e-7, "max_input_tokens": 991808, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://docs.modelstudio.console.alibabacloud.com/en/model-studio/model-pricing", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_video_input": true, "supports_web_search": true, "model_id": "qwen_ai_platform/qwen3.8-flash", "model_name": "Qwen3.8 Flash", "provider_id": "qwen", "provider_name": "Alibaba Cloud", "input_cost_per_million": 0.15, "output_cost_per_million": 0.47, "cache_read_cost_per_token": 1.6e-8, "cache_read_cost_per_million": 0.016, "cache_write_cost_per_token": 2e-7, "cache_write_cost_per_million": 0.19999999999999998, "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": 1.5e-7, "output_cost_per_token": 4.7e-7, "max_input_tokens": 991808, "max_output_tokens": 131072, "max_tokens": 131072, "source": "https://docs.modelstudio.console.alibabacloud.com/en/model-studio/model-pricing", "supports_audio_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_video_input": true, "supports_web_search": true, "model_id": "qwen_ai_platform/qwen3.8-omni-flash", "model_name": "Qwen3.8 Omni Flash", "provider_id": "qwen", "provider_name": "Alibaba Cloud", "input_cost_per_million": 0.15, "output_cost_per_million": 0.47, "cache_read_cost_per_token": 1.6e-8, "cache_read_cost_per_million": 0.016, "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_vision": true, "supports_response_schema": true, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000025, "max_input_tokens": 1000000, "max_output_tokens": 65536, "max_tokens": 65536, "supports_tool_choice": true, "supports_image_size": false, "supports_reasoning": true, "supports_pdf_input": true, "supports_web_search": true, "supports_prompt_caching": true, "model_id": "vercel_ai_gateway/google/gemini-2.5-flash", "model_name": "Gemini 2.5 Flash", "provider_id": "vercel", "provider_name": "Vercel", "input_cost_per_million": 0.3, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 3e-8, "cache_read_cost_per_million": 0.03, "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_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 1048576, "max_output_tokens": 65536, "max_tokens": 65536, "supports_tool_choice": true, "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000015, "cache_read_input_token_cost_above_200k_tokens": 2.5e-7, "supports_reasoning": true, "supports_pdf_input": true, "supports_web_search": true, "supports_prompt_caching": true, "model_id": "vercel_ai_gateway/google/gemini-2.5-pro", "model_name": "Gemini 2.5 Pro", "provider_id": "vercel", "provider_name": "Vercel", "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": 3e-7, "output_cost_per_token": 0.0000025, "max_input_tokens": 1048576, "max_output_tokens": 65535, "deprecation_date": "2026-10-20", "cache_read_input_audio_token_cost": 1e-7, "cache_read_input_token_cost_flex": 3e-8, "cache_read_input_token_cost_priority": 5.4e-8, "input_cost_per_audio_token": 0.000001, "max_tokens": 65535, "output_cost_per_reasoning_token": 0.0000025, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "google_maps_grounding_cost_per_query": 0.025, "input_cost_per_audio_token_batches": 5e-7, "input_cost_per_token_batches": 1.5e-7, "input_cost_per_token_flex": 1.5e-7, "input_cost_per_token_priority": 5.4e-7, "input_cost_per_audio_token_priority": 0.0000018, "output_cost_per_token_batches": 0.00000125, "output_cost_per_token_flex": 0.00000125, "output_cost_per_token_priority": 0.0000045, "supports_image_size": false, "model_id": "gemini-2.5-flash", "model_name": "Gemini 2.5 Flash", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.3, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 3e-8, "cache_read_cost_per_million": 0.03, "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": 1048576, "max_output_tokens": 65535, "deprecation_date": "2026-10-20", "cache_read_input_audio_token_cost": 3e-8, "cache_read_input_token_cost_flex": 1e-8, "cache_read_input_token_cost_priority": 1.8e-8, "input_cost_per_audio_token": 3e-7, "max_tokens": 65535, "output_cost_per_reasoning_token": 4e-7, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "google_maps_grounding_cost_per_query": 0.025, "input_cost_per_audio_token_batches": 5e-8, "input_cost_per_token_batches": 5e-8, "input_cost_per_token_flex": 5e-8, "input_cost_per_token_priority": 1.8e-7, "input_cost_per_audio_token_priority": 5.4e-7, "output_cost_per_token_batches": 2e-7, "output_cost_per_token_flex": 2e-7, "output_cost_per_token_priority": 7.2e-7, "supports_image_size": false, "model_id": "gemini-2.5-flash-lite", "model_name": "Gemini 2.5 Flash Lite", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0.39999999999999997, "cache_read_cost_per_token": 1e-8, "cache_read_cost_per_million": 0.01, "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": 1048576, "max_output_tokens": 65535, "input_cost_per_audio_token": 3e-7, "max_tokens": 65535, "output_cost_per_reasoning_token": 4e-7, "source": "https://developers.googleblog.com/en/continuing-to-bring-you-our-latest-models-with-an-improved-gemini-2-5-flash-and-flash-lite-release/", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "google_maps_grounding_cost_per_query": 0.025, "supports_image_size": false, "model_id": "gemini-2.5-flash-lite-preview-09-2025", "model_name": "Gemini 2.5 Flash Lite Preview 09 2025", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0.39999999999999997, "cache_read_cost_per_token": 1e-8, "cache_read_cost_per_million": 0.01, "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": 3e-7, "output_cost_per_token": 0.0000025, "max_input_tokens": 1048576, "max_output_tokens": 65535, "input_cost_per_audio_token": 0.000001, "max_tokens": 65535, "output_cost_per_reasoning_token": 0.0000025, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "google_maps_grounding_cost_per_query": 0.025, "supports_image_size": false, "model_id": "gemini-2.5-flash-preview-09-2025", "model_name": "Gemini 2.5 Flash Preview 09 2025", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.3, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 3e-8, "cache_read_cost_per_million": 0.03, "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_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 1048576, "max_output_tokens": 65535, "deprecation_date": "2026-10-20", "cache_read_input_token_cost_above_200k_tokens": 2.5e-7, "cache_creation_input_token_cost_above_200k_tokens": 2.5e-7, "cache_read_input_token_cost_above_200k_tokens_priority": 4.5e-7, "cache_read_input_token_cost_flex": 1.25e-7, "cache_read_input_token_cost_priority": 2.25e-7, "input_cost_per_token_above_200k_tokens": 0.0000025, "max_tokens": 65535, "output_cost_per_token_above_200k_tokens": 0.000015, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_pdf_input": true, "supports_prompt_caching": true, "prompt_cache_min_tokens": 2048, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_video_input": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "google_maps_grounding_cost_per_query": 0.025, "input_cost_per_token_above_200k_tokens_priority": 0.0000045, "input_cost_per_token_batches": 6.25e-7, "input_cost_per_token_flex": 6.25e-7, "input_cost_per_token_priority": 0.00000225, "output_cost_per_token_above_200k_tokens_priority": 0.000027, "output_cost_per_token_batches": 0.000005, "output_cost_per_token_flex": 0.000005, "output_cost_per_token_priority": 0.000018, "model_id": "gemini-2.5-pro", "model_name": "Gemini 2.5 Pro", "provider_id": "vertex", "provider_name": "Google Vertex AI", "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", "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": 0.000001, "output_cost_per_token": 0.00002, "max_input_tokens": 1048576, "max_output_tokens": 65535, "input_cost_per_audio_token": 7e-7, "input_cost_per_token_batches": 5e-7, "max_tokens": 65535, "output_cost_per_audio_token": 0.00002, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_modalities": [ "text" ], "supported_output_modalities": [ "audio" ], "supports_audio_output": false, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "model_id": "gemini-2.5-pro-preview-tts", "model_name": "Gemini 2.5 Pro Preview TTS", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 1, "output_cost_per_million": 20, "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": 5e-7, "output_cost_per_token": 0.000003, "max_input_tokens": 1048576, "max_output_tokens": 65535, "cache_read_input_audio_token_cost": 1e-7, "cache_read_input_token_cost_flex": 5e-8, "input_cost_per_audio_token": 0.000001, "max_tokens": 65535, "output_cost_per_reasoning_token": 0.000003, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_web_search": true, "supports_native_streaming": true, "input_cost_per_token_priority": 9e-7, "input_cost_per_audio_token_priority": 0.0000018, "output_cost_per_token_priority": 0.0000054, "cache_read_input_token_cost_priority": 9e-8, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_audio_token_batches": 5e-7, "input_cost_per_token_batches": 2.5e-7, "input_cost_per_token_flex": 2.5e-7, "output_cost_per_token_batches": 0.0000015, "output_cost_per_token_flex": 0.0000015, "model_id": "gemini-3-flash-preview", "model_name": "Gemini 3 Flash Preview", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.5, "output_cost_per_million": 3, "cache_read_cost_per_token": 5e-8, "cache_read_cost_per_million": 0.049999999999999996, "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_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000012, "max_input_tokens": 1048576, "max_output_tokens": 65535, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "cache_creation_input_token_cost_above_200k_tokens": 2.5e-7, "input_cost_per_token_above_200k_tokens": 0.000004, "input_cost_per_token_batches": 0.000001, "max_tokens": 65535, "output_cost_per_token_above_200k_tokens": 0.000018, "output_cost_per_token_batches": 0.000006, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_video_input": true, "supports_web_search": true, "supports_native_streaming": true, "input_cost_per_token_priority": 0.0000036, "input_cost_per_token_above_200k_tokens_priority": 0.0000072, "output_cost_per_token_priority": 0.0000216, "output_cost_per_token_above_200k_tokens_priority": 0.0000324, "cache_read_input_token_cost_priority": 3.6e-7, "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-7, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", "model_id": "gemini-3-pro-preview", "model_name": "Gemini 3 Pro Preview", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 2, "output_cost_per_million": 12, "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": "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": 2.5e-7, "output_cost_per_token": 0.0000015, "max_input_tokens": 1048576, "max_output_tokens": 65536, "deprecation_date": "2027-05-07", "cache_read_input_audio_token_cost": 5e-8, "cache_read_input_token_cost_batches": 1.25e-8, "cache_read_input_token_cost_flex": 1.25e-8, "cache_read_input_token_cost_priority": 4.5e-8, "input_cost_per_audio_token": 5e-7, "input_cost_per_token_batches": 1.25e-7, "input_cost_per_token_flex": 1.25e-7, "input_cost_per_token_priority": 4.5e-7, "input_cost_per_audio_token_priority": 9e-7, "max_tokens": 65536, "output_cost_per_reasoning_token": 0.0000015, "output_cost_per_token_batches": 7.5e-7, "output_cost_per_token_flex": 7.5e-7, "output_cost_per_token_priority": 0.0000027, "regional_endpoint_uplift_multiplier": 1.1, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_audio_output": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_web_search": true, "supports_native_streaming": true, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_audio_token_batches": 2.5e-7, "model_id": "gemini-3.1-flash-lite", "model_name": "Gemini 3.1 Flash Lite", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.25, "output_cost_per_million": 1.5, "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": 2.5e-7, "output_cost_per_token": 0.0000015, "max_input_tokens": 1048576, "max_output_tokens": 65536, "input_cost_per_audio_token": 5e-7, "max_tokens": 65536, "output_cost_per_reasoning_token": 0.0000015, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_audio_output": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_web_search": true, "supports_native_streaming": true, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "model_id": "gemini-3.1-flash-lite-preview", "model_name": "Gemini 3.1 Flash Lite Preview", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.25, "output_cost_per_million": 1.5, "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_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000012, "max_input_tokens": 1048576, "max_output_tokens": 65536, "prompt_cache_min_tokens": 4096, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "cache_creation_input_token_cost_above_200k_tokens": 2.5e-7, "input_cost_per_token_above_200k_tokens": 0.000004, "input_cost_per_token_batches": 0.000001, "max_tokens": 65536, "output_cost_per_token_above_200k_tokens": 0.000018, "output_cost_per_token_batches": 0.000006, "output_cost_per_image": 0.00012, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_video_input": true, "supports_web_search": true, "supports_url_context": true, "supports_native_streaming": true, "input_cost_per_token_priority": 0.0000036, "input_cost_per_token_above_200k_tokens_priority": 0.0000072, "output_cost_per_token_priority": 0.0000216, "output_cost_per_token_above_200k_tokens_priority": 0.0000324, "cache_read_input_token_cost_priority": 3.6e-7, "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-7, "cache_read_input_token_cost_flex": 2e-7, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_token_flex": 0.000001, "output_cost_per_token_flex": 0.000006, "model_id": "gemini-3.1-pro-preview", "model_name": "Gemini 3.1 Pro Preview", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 2, "output_cost_per_million": 12, "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": "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": 0.000012, "max_input_tokens": 1048576, "max_output_tokens": 65536, "prompt_cache_min_tokens": 4096, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "cache_creation_input_token_cost_above_200k_tokens": 2.5e-7, "input_cost_per_token_above_200k_tokens": 0.000004, "input_cost_per_token_batches": 0.000001, "max_tokens": 65536, "output_cost_per_token_above_200k_tokens": 0.000018, "output_cost_per_token_batches": 0.000006, "output_cost_per_image": 0.00012, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_video_input": true, "supports_web_search": true, "supports_url_context": true, "supports_native_streaming": true, "input_cost_per_token_priority": 0.0000036, "input_cost_per_token_above_200k_tokens_priority": 0.0000072, "output_cost_per_token_priority": 0.0000216, "output_cost_per_token_above_200k_tokens_priority": 0.0000324, "cache_read_input_token_cost_priority": 3.6e-7, "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-7, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "model_id": "gemini-3.1-pro-preview-customtools", "model_name": "Gemini 3.1 Pro Preview Customtools", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 2, "output_cost_per_million": 12, "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": "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": 0.0000015, "output_cost_per_token": 0.000009, "max_input_tokens": 1048576, "max_output_tokens": 65535, "deprecation_date": "2027-05-19", "prompt_cache_min_tokens": 4096, "cache_read_input_token_cost_batches": 7.5e-8, "input_cost_per_audio_token": 0.0000015, "max_tokens": 65535, "output_cost_per_reasoning_token": 0.000009, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_audio_input": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_web_search": true, "supports_native_streaming": true, "input_cost_per_token_priority": 0.0000027, "input_cost_per_audio_token_priority": 0.0000027, "output_cost_per_token_priority": 0.0000162, "cache_read_input_token_cost_priority": 2.7e-7, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "input_cost_per_token_batches": 7.5e-7, "output_cost_per_token_batches": 0.0000045, "input_cost_per_token_flex": 7.5e-7, "output_cost_per_token_flex": 0.0000045, "cache_read_input_token_cost_flex": 7.5e-8, "model_id": "gemini-3.5-flash", "model_name": "Gemini 3.5 Flash", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 1.5, "output_cost_per_million": 9, "cache_read_cost_per_token": 1.5e-7, "cache_read_cost_per_million": 0.15, "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": 3e-7, "output_cost_per_token": 0.0000025, "max_input_tokens": 1048576, "max_output_tokens": 65536, "deprecation_date": "2027-07-21", "cache_read_input_token_cost_batches": 1.5e-8, "cache_read_input_token_cost_flex": 1.5e-8, "cache_read_input_token_cost_priority": 5.4e-8, "input_cost_per_token_batches": 1.5e-7, "input_cost_per_token_flex": 1.5e-7, "input_cost_per_token_priority": 5.4e-7, "max_tokens": 65536, "output_cost_per_reasoning_token": 0.0000025, "output_cost_per_token_batches": 0.00000125, "output_cost_per_token_flex": 0.00000125, "output_cost_per_token_priority": 0.0000045, "regional_endpoint_uplift_multiplier": 1.1, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_audio_output": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_web_search": true, "supports_native_streaming": true, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "model_id": "gemini-3.5-flash-lite", "model_name": "Gemini 3.5 Flash Lite", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.3, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 3e-8, "cache_read_cost_per_million": 0.03, "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": 7.5e-7, "output_cost_per_token": 0.00000375, "max_input_tokens": 1048576, "max_output_tokens": 65536, "deprecation_date": "2026-11-19", "prompt_cache_min_tokens": 4096, "cache_read_input_token_cost_batches": 3.75e-8, "cache_read_input_token_cost_flex": 3.75e-8, "input_cost_per_token_batches": 3.75e-7, "input_cost_per_token_flex": 3.75e-7, "max_tokens": 65536, "output_cost_per_reasoning_token": 0.00000375, "output_cost_per_token_batches": 0.000001875, "output_cost_per_token_flex": 0.000001875, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_audio_input": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_web_search": true, "supports_native_streaming": true, "input_cost_per_token_priority": 0.00000135, "output_cost_per_token_priority": 0.00000675, "cache_read_input_token_cost_priority": 1.35e-7, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "model_id": "gemini-3.6-flash", "model_name": "Gemini 3.6 Flash", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.75, "output_cost_per_million": 3.75, "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", "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": 0.00000375, "max_input_tokens": 1048576, "max_output_tokens": 65536, "deprecation_date": "2027-01-28", "prompt_cache_min_tokens": 4096, "cache_read_input_token_cost_batches": 3.75e-8, "cache_read_input_token_cost_flex": 3.75e-8, "input_cost_per_token_batches": 3.75e-7, "input_cost_per_token_flex": 3.75e-7, "max_tokens": 65536, "output_cost_per_reasoning_token": 0.00000375, "output_cost_per_token_batches": 0.000001875, "output_cost_per_token_flex": 0.000001875, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_audio_input": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_minimal_reasoning_effort": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_web_search": true, "supports_native_streaming": true, "input_cost_per_token_priority": 0.00000135, "output_cost_per_token_priority": 0.00000675, "cache_read_input_token_cost_priority": 1.35e-7, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "model_id": "gemini-3.7-flash", "model_name": "Gemini 3.7 Flash", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.75, "output_cost_per_million": 3.75, "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", "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": 0.00000375, "max_input_tokens": 1048576, "max_output_tokens": 65536, "prompt_cache_min_tokens": 4096, "cache_read_input_token_cost_batches": 3.75e-8, "cache_read_input_token_cost_flex": 3.75e-8, "input_cost_per_token_batches": 3.75e-7, "input_cost_per_token_flex": 3.75e-7, "max_tokens": 65536, "output_cost_per_reasoning_token": 0.00000375, "output_cost_per_token_batches": 0.000001875, "output_cost_per_token_flex": 0.000001875, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_audio_input": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_minimal_reasoning_effort": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_web_search": true, "supports_native_streaming": true, "input_cost_per_token_priority": 0.00000135, "output_cost_per_token_priority": 0.00000675, "cache_read_input_token_cost_priority": 1.35e-7, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, "model_id": "gemini-3.8-flash", "model_name": "Gemini 3.8 Flash", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.75, "output_cost_per_million": 3.75, "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": false, "input_cost_per_token": 5e-7, "output_cost_per_token": 0.000002, "max_input_tokens": 131072, "max_output_tokens": 65536, "deprecation_date": "2026-12-13", "input_cost_per_audio_token": 0.000003, "max_tokens": 65536, "output_cost_per_audio_token": 0.000012, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/vertex_ai/live", "/v1/realtime" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_pdf_input": false, "supports_prompt_caching": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": false, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "gemini_native_audio": true, "input_cost_per_image_token": 0.000003, "input_cost_per_video_token": 0.000003, "model_id": "gemini-live-2.5-flash-native-audio", "model_name": "Gemini Live 2.5 Flash Native Audio", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.5, "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": "realtime", "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": 5e-7, "output_cost_per_token": 0.000002, "max_input_tokens": 1048576, "max_output_tokens": 65535, "input_cost_per_audio_token": 0.000003, "max_tokens": 65535, "output_cost_per_audio_token": 0.000012, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/vertex_ai/live" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_pdf_input": true, "supports_prompt_caching": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "gemini_native_audio": true, "input_cost_per_image_token": 0.000003, "model_id": "gemini-live-2.5-flash-preview-native-audio-09-2025", "model_name": "Gemini Live 2.5 Flash Preview Native Audio 09 2025", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.5, "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": "realtime", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": false, "supports_vision": true, "supports_response_schema": false, "input_cost_per_token": 0.0000015, "output_cost_per_token": 0.0000075, "max_input_tokens": 131072, "max_output_tokens": 32768, "cache_read_input_token_cost_batches": 7.5e-8, "cache_read_input_token_cost_priority": 2.7e-7, "input_cost_per_image": 0.00168, "input_cost_per_token_batches": 7.5e-7, "input_cost_per_token_priority": 0.0000027, "max_tokens": 32768, "output_cost_per_image": 0.0336, "output_cost_per_image_token": 0.00003, "output_cost_per_token_batches": 0.00000375, "output_cost_per_token_priority": 0.0000135, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/images/generations", "/v1/images/edits", "/v1/batch" ], "supported_modalities": [ "text", "image", "video" ], "supported_output_modalities": [ "text", "image" ], "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_video_input": true, "supports_web_search": true, "web_search_billing_unit": "per_query", "model_id": "gemini-nano-banana-2.1", "model_name": "Gemini Nano Banana 2.1", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 1.5, "output_cost_per_million": 7.5, "cache_read_cost_per_token": 1.5e-7, "cache_read_cost_per_million": 0.15, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "image", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000025, "max_input_tokens": 256000, "max_output_tokens": 256000, "deprecation_date": "2026-10-21", "max_tokens": 256000, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_tool_choice": true, "supports_web_search": true, "model_id": "moonshotai/kimi-k2-thinking-maas", "model_name": "Kimi K2 Thinking Maas", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.6, "output_cost_per_million": 2.5, "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", "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2e-7, "output_cost_per_token": 5e-7, "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_prompt_caching": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "xai/grok-4.1-fast-non-reasoning", "model_name": "Grok 4.1 Fast Non Reasoning", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.19999999999999998, "output_cost_per_million": 0.5, "cache_read_cost_per_token": 5e-8, "cache_read_cost_per_million": 0.049999999999999996, "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_vision": true, "supports_response_schema": true, "input_cost_per_token": 2e-7, "output_cost_per_token": 5e-7, "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "xai/grok-4.1-fast-reasoning", "model_name": "Grok 4.1 Fast Reasoning", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.19999999999999998, "output_cost_per_million": 0.5, "cache_read_cost_per_token": 5e-8, "cache_read_cost_per_million": 0.049999999999999996, "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_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.0000025, "max_input_tokens": 1000000, "max_output_tokens": 1000000, "cache_read_input_token_cost_batches": 1.6e-7, "input_cost_per_token_batches": 0.000001, "max_tokens": 1000000, "output_cost_per_token_batches": 0.000002, "source": "https://api.x.ai/v1/language-models", "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 0.0000025, "input_cost_per_token_above_200k_tokens_batches": 0.000002, "output_cost_per_token_above_200k_tokens": 0.000005, "output_cost_per_token_above_200k_tokens_batches": 0.000004, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-7, "input_cost_per_image_token": 0.00000125, "supports_prompt_caching": true, "model_id": "grok-4.20", "model_name": "Grok 4.20", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 1.25, "output_cost_per_million": 2.5, "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": "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": 0.00000125, "output_cost_per_token": 0.0000025, "max_input_tokens": 1000000, "max_output_tokens": 1000000, "cache_read_input_token_cost_batches": 1.6e-7, "input_cost_per_token_batches": 0.000001, "max_tokens": 1000000, "output_cost_per_token_batches": 0.000002, "source": "https://api.x.ai/v1/language-models", "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 0.0000025, "input_cost_per_token_above_200k_tokens_batches": 0.000002, "output_cost_per_token_above_200k_tokens": 0.000005, "output_cost_per_token_above_200k_tokens_batches": 0.000004, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-7, "input_cost_per_image_token": 0.00000125, "supports_prompt_caching": true, "model_id": "grok-4.20-0309", "model_name": "Grok 4.20 (Sep 2003)", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 1.25, "output_cost_per_million": 2.5, "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": "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": 0.00000125, "output_cost_per_token": 0.0000025, "max_input_tokens": 1000000, "max_output_tokens": 1000000, "cache_read_input_token_cost_batches": 1.6e-7, "input_cost_per_token_batches": 0.000001, "max_tokens": 1000000, "output_cost_per_token_batches": 0.000002, "source": "https://api.x.ai/v1/language-models", "supports_prompt_caching": true, "supports_tool_choice": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 0.0000025, "input_cost_per_token_above_200k_tokens_batches": 0.000002, "output_cost_per_token_above_200k_tokens": 0.000005, "output_cost_per_token_above_200k_tokens_batches": 0.000004, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-7, "input_cost_per_image_token": 0.00000125, "model_id": "grok-4.20-0309-non-reasoning", "model_name": "Grok 4.20 0309 Non Reasoning", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 1.25, "output_cost_per_million": 2.5, "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": "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": 0.00000125, "output_cost_per_token": 0.0000025, "max_input_tokens": 1000000, "max_output_tokens": 1000000, "cache_read_input_token_cost_batches": 1.6e-7, "input_cost_per_token_batches": 0.000001, "max_tokens": 1000000, "output_cost_per_token_batches": 0.000002, "source": "https://api.x.ai/v1/language-models", "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 0.0000025, "input_cost_per_token_above_200k_tokens_batches": 0.000002, "output_cost_per_token_above_200k_tokens": 0.000005, "output_cost_per_token_above_200k_tokens_batches": 0.000004, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-7, "input_cost_per_image_token": 0.00000125, "supports_prompt_caching": true, "model_id": "grok-4.20-0309-reasoning", "model_name": "Grok 4.20 0309 Reasoning", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 1.25, "output_cost_per_million": 2.5, "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": "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": 0.00000125, "output_cost_per_token": 0.0000025, "max_input_tokens": 1000000, "max_output_tokens": 1000000, "max_tokens": 1000000, "source": "https://api.x.ai/v1/language-models", "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000005, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "input_cost_per_image_token": 0.00000125, "supports_prompt_caching": true, "model_id": "grok-4.20-beta", "model_name": "Grok 4.20 Beta", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 1.25, "output_cost_per_million": 2.5, "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": "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": 0.00000125, "output_cost_per_token": 0.0000025, "max_input_tokens": 1000000, "max_output_tokens": 1000000, "max_tokens": 1000000, "source": "https://api.x.ai/v1/language-models", "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000005, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "input_cost_per_image_token": 0.00000125, "supports_prompt_caching": true, "model_id": "grok-4.20-beta-0309", "model_name": "Grok 4.20 Beta (Sep 2003)", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 1.25, "output_cost_per_million": 2.5, "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": "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": 0.00000125, "output_cost_per_token": 0.0000025, "max_input_tokens": 1000000, "max_output_tokens": 1000000, "max_tokens": 1000000, "source": "https://api.x.ai/v1/language-models", "supports_prompt_caching": true, "supports_tool_choice": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000005, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "input_cost_per_image_token": 0.00000125, "model_id": "grok-4.20-beta-0309-non-reasoning", "model_name": "Grok 4.20 Beta 0309 Non Reasoning", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 1.25, "output_cost_per_million": 2.5, "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": "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": 0.00000125, "output_cost_per_token": 0.0000025, "max_input_tokens": 1000000, "max_output_tokens": 1000000, "max_tokens": 1000000, "source": "https://api.x.ai/v1/language-models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000005, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "input_cost_per_image_token": 0.00000125, "model_id": "grok-4.20-beta-0309-reasoning", "model_name": "Grok 4.20 Beta 0309 Reasoning", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 1.25, "output_cost_per_million": 2.5, "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": "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": 0.00000125, "output_cost_per_token": 0.0000025, "max_input_tokens": 1000000, "max_output_tokens": 1000000, "max_tokens": 1000000, "source": "https://api.x.ai/v1/language-models", "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000005, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "input_cost_per_image_token": 0.00000125, "supports_prompt_caching": true, "model_id": "grok-4.20-beta-latest", "model_name": "Grok 4.20 Beta Latest", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 1.25, "output_cost_per_million": 2.5, "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": "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": 0.00000125, "output_cost_per_token": 0.0000025, "max_input_tokens": 1000000, "max_output_tokens": 1000000, "max_tokens": 1000000, "source": "https://api.x.ai/v1/language-models", "supports_prompt_caching": true, "supports_tool_choice": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000005, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "input_cost_per_image_token": 0.00000125, "model_id": "grok-4.20-beta-latest-non-reasoning", "model_name": "Grok 4.20 Beta Latest Non Reasoning", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 1.25, "output_cost_per_million": 2.5, "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": "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": 0.00000125, "output_cost_per_token": 0.0000025, "max_input_tokens": 1000000, "max_output_tokens": 1000000, "max_tokens": 1000000, "source": "https://api.x.ai/v1/language-models", "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000005, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "input_cost_per_image_token": 0.00000125, "supports_prompt_caching": true, "model_id": "grok-4.20-beta-latest-reasoning", "model_name": "Grok 4.20 Beta Latest Reasoning", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 1.25, "output_cost_per_million": 2.5, "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": "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": 0.00000125, "output_cost_per_token": 0.0000025, "max_input_tokens": 1000000, "max_output_tokens": 1000000, "max_tokens": 1000000, "source": "https://api.x.ai/v1/language-models", "supports_prompt_caching": true, "supports_tool_choice": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000005, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "input_cost_per_image_token": 0.00000125, "model_id": "grok-4.20-beta-non-reasoning", "model_name": "Grok 4.20 Beta Non Reasoning", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 1.25, "output_cost_per_million": 2.5, "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": "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": 0.00000125, "output_cost_per_token": 0.0000025, "max_input_tokens": 1000000, "max_output_tokens": 1000000, "max_tokens": 1000000, "source": "https://api.x.ai/v1/language-models", "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000005, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "input_cost_per_image_token": 0.00000125, "supports_prompt_caching": true, "model_id": "grok-4.20-beta-reasoning", "model_name": "Grok 4.20 Beta Reasoning", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 1.25, "output_cost_per_million": 2.5, "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": "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": 0.00000125, "output_cost_per_token": 0.0000025, "max_input_tokens": 1000000, "max_output_tokens": 1000000, "max_tokens": 1000000, "source": "https://api.x.ai/v1/language-models", "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000005, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "input_cost_per_image_token": 0.00000125, "supports_prompt_caching": true, "model_id": "grok-4.20-experimental-beta-0304", "model_name": "Grok 4.20 Experimental Beta (Apr 2003)", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 1.25, "output_cost_per_million": 2.5, "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": "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": 0.00000125, "output_cost_per_token": 0.0000025, "max_input_tokens": 1000000, "max_output_tokens": 1000000, "max_tokens": 1000000, "source": "https://api.x.ai/v1/language-models", "supports_prompt_caching": true, "supports_tool_choice": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000005, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "input_cost_per_image_token": 0.00000125, "model_id": "grok-4.20-experimental-beta-0304-non-reasoning", "model_name": "Grok 4.20 Experimental Beta 0304 Non Reasoning", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 1.25, "output_cost_per_million": 2.5, "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": "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": 0.00000125, "output_cost_per_token": 0.0000025, "max_input_tokens": 1000000, "max_output_tokens": 1000000, "max_tokens": 1000000, "source": "https://api.x.ai/v1/language-models", "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000005, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "input_cost_per_image_token": 0.00000125, "supports_prompt_caching": true, "model_id": "grok-4.20-experimental-beta-0304-reasoning", "model_name": "Grok 4.20 Experimental Beta 0304 Reasoning", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 1.25, "output_cost_per_million": 2.5, "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": "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": 0.00000125, "output_cost_per_token": 0.0000025, "max_input_tokens": 1000000, "max_output_tokens": 1000000, "max_tokens": 1000000, "source": "https://api.x.ai/v1/language-models", "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000005, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "input_cost_per_image_token": 0.00000125, "supports_prompt_caching": true, "model_id": "grok-4.20-experimental-beta-latest", "model_name": "Grok 4.20 Experimental Beta Latest", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 1.25, "output_cost_per_million": 2.5, "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": "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": 0.00000125, "output_cost_per_token": 0.0000025, "max_input_tokens": 1000000, "max_output_tokens": 1000000, "max_tokens": 1000000, "source": "https://api.x.ai/v1/language-models", "supports_prompt_caching": true, "supports_tool_choice": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000005, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "input_cost_per_image_token": 0.00000125, "model_id": "grok-4.20-experimental-beta-non-reasoning-latest", "model_name": "Grok 4.20 Experimental Beta Non Reasoning Latest", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 1.25, "output_cost_per_million": 2.5, "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": "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": 0.00000125, "output_cost_per_token": 0.0000025, "max_input_tokens": 1000000, "max_output_tokens": 1000000, "max_tokens": 1000000, "source": "https://api.x.ai/v1/language-models", "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000005, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "input_cost_per_image_token": 0.00000125, "supports_prompt_caching": true, "model_id": "grok-4.20-experimental-beta-reasoning-latest", "model_name": "Grok 4.20 Experimental Beta Reasoning Latest", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 1.25, "output_cost_per_million": 2.5, "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": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": false, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.0000025, "max_input_tokens": 1000000, "max_output_tokens": 1000000, "cache_read_input_token_cost_batches": 1.6e-7, "input_cost_per_token_batches": 0.000001, "max_tokens": 1000000, "output_cost_per_token_batches": 0.000002, "source": "https://api.x.ai/v1/language-models", "supported_endpoints": [ "/v1/responses" ], "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": false, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 0.0000025, "input_cost_per_token_above_200k_tokens_batches": 0.000002, "output_cost_per_token_above_200k_tokens": 0.000005, "output_cost_per_token_above_200k_tokens_batches": 0.000004, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-7, "input_cost_per_image_token": 0.00000125, "model_id": "grok-4.20-multi-agent", "model_name": "Grok 4.20 Multi Agent", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 1.25, "output_cost_per_million": 2.5, "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": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": false, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.0000025, "max_input_tokens": 1000000, "max_output_tokens": 1000000, "cache_read_input_token_cost_batches": 1.6e-7, "input_cost_per_token_batches": 0.000001, "max_tokens": 1000000, "output_cost_per_token_batches": 0.000002, "source": "https://api.x.ai/v1/language-models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": false, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 0.0000025, "input_cost_per_token_above_200k_tokens_batches": 0.000002, "output_cost_per_token_above_200k_tokens": 0.000005, "output_cost_per_token_above_200k_tokens_batches": 0.000004, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-7, "input_cost_per_image_token": 0.00000125, "supported_endpoints": [ "/v1/responses" ], "model_id": "grok-4.20-multi-agent-0309", "model_name": "Grok 4.20 Multi Agent (Sep 2003)", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 1.25, "output_cost_per_million": 2.5, "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": "responses", "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": 0.00000125, "output_cost_per_token": 0.0000025, "max_input_tokens": 1000000, "max_output_tokens": 1000000, "max_tokens": 1000000, "source": "https://api.x.ai/v1/language-models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000005, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "input_cost_per_image_token": 0.00000125, "supported_endpoints": [ "/v1/responses" ], "model_id": "grok-4.20-multi-agent-beta-0309", "model_name": "Grok 4.20 Multi Agent Beta (Sep 2003)", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 1.25, "output_cost_per_million": 2.5, "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": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": false, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.0000025, "max_input_tokens": 1000000, "max_output_tokens": 1000000, "max_tokens": 1000000, "source": "https://api.x.ai/v1/language-models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": false, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000005, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "input_cost_per_image_token": 0.00000125, "supported_endpoints": [ "/v1/responses" ], "model_id": "grok-4.20-multi-agent-beta-latest", "model_name": "Grok 4.20 Multi Agent Beta Latest", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 1.25, "output_cost_per_million": 2.5, "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": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": false, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.0000025, "max_input_tokens": 1000000, "max_output_tokens": 1000000, "max_tokens": 1000000, "source": "https://api.x.ai/v1/language-models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": false, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000005, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "input_cost_per_image_token": 0.00000125, "supported_endpoints": [ "/v1/responses" ], "model_id": "grok-4.20-multi-agent-experimental-beta-0304", "model_name": "Grok 4.20 Multi Agent Experimental Beta (Apr 2003)", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 1.25, "output_cost_per_million": 2.5, "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": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": false, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.0000025, "max_input_tokens": 1000000, "max_output_tokens": 1000000, "max_tokens": 1000000, "source": "https://api.x.ai/v1/language-models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": false, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000005, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "input_cost_per_image_token": 0.00000125, "supported_endpoints": [ "/v1/responses" ], "model_id": "grok-4.20-multi-agent-experimental-beta-latest", "model_name": "Grok 4.20 Multi Agent Experimental Beta Latest", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 1.25, "output_cost_per_million": 2.5, "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": "responses", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": false, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.0000025, "max_input_tokens": 1000000, "max_output_tokens": 1000000, "cache_read_input_token_cost_batches": 1.6e-7, "input_cost_per_token_batches": 0.000001, "max_tokens": 1000000, "output_cost_per_token_batches": 0.000002, "source": "https://api.x.ai/v1/language-models", "supported_endpoints": [ "/v1/responses" ], "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": false, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 0.0000025, "input_cost_per_token_above_200k_tokens_batches": 0.000002, "output_cost_per_token_above_200k_tokens": 0.000005, "output_cost_per_token_above_200k_tokens_batches": 0.000004, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-7, "input_cost_per_image_token": 0.00000125, "model_id": "grok-4.20-multi-agent-latest", "model_name": "Grok 4.20 Multi Agent Latest", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 1.25, "output_cost_per_million": 2.5, "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": "responses", "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": 0.00000125, "output_cost_per_token": 0.0000025, "max_input_tokens": 1000000, "max_output_tokens": 1000000, "cache_read_input_token_cost_batches": 1.6e-7, "input_cost_per_token_batches": 0.000001, "max_tokens": 1000000, "output_cost_per_token_batches": 0.000002, "source": "https://api.x.ai/v1/language-models", "supports_prompt_caching": true, "supports_tool_choice": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 0.0000025, "input_cost_per_token_above_200k_tokens_batches": 0.000002, "output_cost_per_token_above_200k_tokens": 0.000005, "output_cost_per_token_above_200k_tokens_batches": 0.000004, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-7, "input_cost_per_image_token": 0.00000125, "model_id": "grok-4.20-non-reasoning", "model_name": "Grok 4.20 Non Reasoning", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 1.25, "output_cost_per_million": 2.5, "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": "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": 0.00000125, "output_cost_per_token": 0.0000025, "max_input_tokens": 1000000, "max_output_tokens": 1000000, "max_tokens": 1000000, "source": "https://api.x.ai/v1/language-models", "supports_prompt_caching": true, "supports_tool_choice": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000005, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "input_cost_per_image_token": 0.00000125, "model_id": "grok-4.20-non-reasoning-gv2", "model_name": "Grok 4.20 Non Reasoning Gv2", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 1.25, "output_cost_per_million": 2.5, "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": "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": 0.00000125, "output_cost_per_token": 0.0000025, "max_input_tokens": 1000000, "max_output_tokens": 1000000, "cache_read_input_token_cost_batches": 1.6e-7, "input_cost_per_token_batches": 0.000001, "max_tokens": 1000000, "output_cost_per_token_batches": 0.000002, "source": "https://api.x.ai/v1/language-models", "supports_prompt_caching": true, "supports_tool_choice": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 0.0000025, "input_cost_per_token_above_200k_tokens_batches": 0.000002, "output_cost_per_token_above_200k_tokens": 0.000005, "output_cost_per_token_above_200k_tokens_batches": 0.000004, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-7, "input_cost_per_image_token": 0.00000125, "model_id": "grok-4.20-non-reasoning-latest", "model_name": "Grok 4.20 Non Reasoning Latest", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 1.25, "output_cost_per_million": 2.5, "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": "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": 0.00000125, "output_cost_per_token": 0.0000025, "max_input_tokens": 1000000, "max_output_tokens": 1000000, "cache_read_input_token_cost_batches": 1.6e-7, "input_cost_per_token_batches": 0.000001, "max_tokens": 1000000, "output_cost_per_token_batches": 0.000002, "source": "https://api.x.ai/v1/language-models", "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 0.0000025, "input_cost_per_token_above_200k_tokens_batches": 0.000002, "output_cost_per_token_above_200k_tokens": 0.000005, "output_cost_per_token_above_200k_tokens_batches": 0.000004, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-7, "input_cost_per_image_token": 0.00000125, "supports_prompt_caching": true, "model_id": "grok-4.20-reasoning", "model_name": "Grok 4.20 Reasoning", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 1.25, "output_cost_per_million": 2.5, "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": "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": 0.00000125, "output_cost_per_token": 0.0000025, "max_input_tokens": 1000000, "max_output_tokens": 1000000, "max_tokens": 1000000, "source": "https://api.x.ai/v1/language-models", "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 0.0000025, "output_cost_per_token_above_200k_tokens": 0.000005, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "input_cost_per_image_token": 0.00000125, "supports_prompt_caching": true, "model_id": "grok-4.20-reasoning-gv2", "model_name": "Grok 4.20 Reasoning Gv2", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 1.25, "output_cost_per_million": 2.5, "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": "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": 0.00000125, "output_cost_per_token": 0.0000025, "max_input_tokens": 1000000, "max_output_tokens": 1000000, "cache_read_input_token_cost_batches": 1.6e-7, "input_cost_per_token_batches": 0.000001, "max_tokens": 1000000, "output_cost_per_token_batches": 0.000002, "source": "https://api.x.ai/v1/language-models", "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "input_cost_per_token_above_200k_tokens": 0.0000025, "input_cost_per_token_above_200k_tokens_batches": 0.000002, "output_cost_per_token_above_200k_tokens": 0.000005, "output_cost_per_token_above_200k_tokens_batches": 0.000004, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-7, "input_cost_per_image_token": 0.00000125, "supports_prompt_caching": true, "model_id": "grok-4.20-reasoning-latest", "model_name": "Grok 4.20 Reasoning Latest", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 1.25, "output_cost_per_million": 2.5, "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": "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": 0.00000125, "output_cost_per_token": 0.0000025, "max_input_tokens": 1000000, "max_output_tokens": 1000000, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-7, "cache_read_input_token_cost_batches": 1.6e-7, "input_cost_per_image_token": 0.00000125, "input_cost_per_token_above_200k_tokens": 0.0000025, "input_cost_per_token_above_200k_tokens_batches": 0.000002, "input_cost_per_token_batches": 0.000001, "max_tokens": 1000000, "output_cost_per_token_above_200k_tokens": 0.000005, "output_cost_per_token_above_200k_tokens_batches": 0.000004, "output_cost_per_token_batches": 0.000002, "source": "https://api.x.ai/v1/language-models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "grok-4.3", "model_name": "Grok 4.3", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 1.25, "output_cost_per_million": 2.5, "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": "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": 0.00000125, "output_cost_per_token": 0.0000025, "max_input_tokens": 1000000, "max_output_tokens": 1000000, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "cache_read_input_token_cost_above_200k_tokens_batches": 3.2e-7, "cache_read_input_token_cost_batches": 1.6e-7, "input_cost_per_image_token": 0.00000125, "input_cost_per_token_above_200k_tokens": 0.0000025, "input_cost_per_token_above_200k_tokens_batches": 0.000002, "input_cost_per_token_batches": 0.000001, "max_tokens": 1000000, "output_cost_per_token_above_200k_tokens": 0.000005, "output_cost_per_token_above_200k_tokens_batches": 0.000004, "output_cost_per_token_batches": 0.000002, "source": "https://api.x.ai/v1/language-models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "grok-4.3-latest", "model_name": "Grok 4.3 Latest", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 1.25, "output_cost_per_million": 2.5, "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": "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": 0.000006, "max_input_tokens": 500000, "max_output_tokens": 500000, "cache_read_input_token_cost_above_200k_tokens": 6e-7, "input_cost_per_image_token": 0.000002, "input_cost_per_token_above_200k_tokens": 0.000004, "max_tokens": 500000, "output_cost_per_token_above_200k_tokens": 0.000012, "source": "https://api.x.ai/v1/language-models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "grok-4.5", "model_name": "Grok 4.5", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 2, "output_cost_per_million": 6, "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_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": 0.000006, "max_input_tokens": 500000, "max_output_tokens": 500000, "cache_read_input_token_cost_above_200k_tokens": 6e-7, "input_cost_per_image_token": 0.000002, "input_cost_per_token_above_200k_tokens": 0.000004, "max_tokens": 500000, "output_cost_per_token_above_200k_tokens": 0.000012, "source": "https://api.x.ai/v1/language-models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "grok-4.5-latest", "model_name": "Grok 4.5 Latest", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 2, "output_cost_per_million": 6, "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_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": 0.000006, "max_input_tokens": 500000, "max_output_tokens": 500000, "cache_read_input_token_cost_above_200k_tokens": 0.000001, "input_cost_per_image_token": 0.000002, "input_cost_per_token_above_200k_tokens": 0.000004, "max_tokens": 500000, "output_cost_per_token_above_200k_tokens": 0.000012, "source": "https://api.x.ai/v1/language-models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "grok-4.6", "model_name": "Grok 4.6", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 2, "output_cost_per_million": 6, "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_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000006, "max_input_tokens": 500000, "max_output_tokens": 500000, "cache_read_input_token_cost_above_200k_tokens": 0.000001, "input_cost_per_image_token": 0.000002, "input_cost_per_token_above_200k_tokens": 0.000004, "max_tokens": 500000, "output_cost_per_token_above_200k_tokens": 0.000012, "source": "https://api.x.ai/v1/language-models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "grok-4.7", "model_name": "Grok 4.7", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 2, "output_cost_per_million": 6, "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_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000006, "max_input_tokens": 500000, "max_output_tokens": 500000, "cache_read_input_token_cost_above_200k_tokens": 6e-7, "input_cost_per_image_token": 0.000002, "input_cost_per_token_above_200k_tokens": 0.000004, "max_tokens": 500000, "output_cost_per_token_above_200k_tokens": 0.000012, "source": "https://api.x.ai/v1/language-models", "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "grok-build-latest", "model_name": "Grok Build Latest", "provider_id": "xai", "provider_name": "xAI", "input_cost_per_million": 2, "output_cost_per_million": 6, "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_json_mode": true, "supports_parallel_functions": false } ]