[ { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 8e-8, "output_cost_per_token": 3.2e-7, "max_input_tokens": 131072, "max_output_tokens": 4096, "input_cost_per_audio_token": 0.000004, "max_tokens": 4096, "source": "https://techcommunity.microsoft.com/blog/Azure-AI-Services-blog/announcing-new-phi-pricing-empowering-your-business-with-small-language-models/4395112", "supports_audio_input": true, "model_id": "azure_ai/Phi-4-multimodal-instruct", "model_name": "Phi 4 Multimodal Instruct", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.08, "output_cost_per_million": 0.32, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 6.6e-7, "output_cost_per_token": 0.00000264, "max_input_tokens": 128000, "max_output_tokens": 4096, "cache_creation_input_audio_token_cost": 3.3e-7, "input_cost_per_audio_token": 0.000011, "max_tokens": 4096, "output_cost_per_audio_token": 0.000022, "supports_audio_input": true, "supports_audio_output": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/eu/gpt-4o-mini-realtime-preview-2024-12-17", "model_name": "GPT-4o Mini Realtime Preview (Dec 2024)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.66, "output_cost_per_million": 2.64, "cache_read_cost_per_token": 3.3e-7, "cache_read_cost_per_million": 0.33, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 0.0000055, "output_cost_per_token": 0.000022, "max_input_tokens": 128000, "max_output_tokens": 4096, "cache_creation_input_audio_token_cost": 0.000022, "input_cost_per_audio_token": 0.00011, "max_tokens": 4096, "output_cost_per_audio_token": 0.00022, "supports_audio_input": true, "supports_audio_output": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/eu/gpt-4o-realtime-preview-2024-10-01", "model_name": "GPT-4o Realtime Preview (Oct 2024)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 5.5, "output_cost_per_million": 22, "cache_read_cost_per_token": 0.00000275, "cache_read_cost_per_million": 2.75, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 0.0000055, "output_cost_per_token": 0.000022, "max_input_tokens": 128000, "max_output_tokens": 4096, "cache_read_input_audio_token_cost": 0.0000025, "input_cost_per_audio_token": 0.000044, "max_tokens": 4096, "output_cost_per_audio_token": 0.00008, "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/eu/gpt-4o-realtime-preview-2024-12-17", "model_name": "GPT-4o Realtime Preview (Dec 2024)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 5.5, "output_cost_per_million": 22, "cache_read_cost_per_token": 0.00000275, "cache_read_cost_per_million": 2.75, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000024, "max_input_tokens": 128000, "max_output_tokens": 4096, "cache_creation_input_audio_token_cost": 3e-7, "input_cost_per_audio_token": 0.00001, "max_tokens": 4096, "output_cost_per_audio_token": 0.00002, "supports_audio_input": true, "supports_audio_output": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/gpt-4o-mini-realtime-preview-2024-12-17", "model_name": "GPT-4o Mini Realtime Preview (Dec 2024)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.6, "output_cost_per_million": 2.4, "cache_read_cost_per_token": 3e-7, "cache_read_cost_per_million": 0.3, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.00002, "max_input_tokens": 128000, "max_output_tokens": 4096, "cache_creation_input_audio_token_cost": 0.00002, "input_cost_per_audio_token": 0.0001, "max_tokens": 4096, "output_cost_per_audio_token": 0.0002, "supports_audio_input": true, "supports_audio_output": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/gpt-4o-realtime-preview-2024-10-01", "model_name": "GPT-4o Realtime Preview (Oct 2024)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 5, "output_cost_per_million": 20, "cache_read_cost_per_token": 0.0000025, "cache_read_cost_per_million": 2.5, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.00002, "max_input_tokens": 128000, "max_output_tokens": 4096, "input_cost_per_audio_token": 0.00004, "max_tokens": 4096, "output_cost_per_audio_token": 0.00008, "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/gpt-4o-realtime-preview-2024-12-17", "model_name": "GPT-4o Realtime Preview (Dec 2024)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 5, "output_cost_per_million": 20, "cache_read_cost_per_token": 0.0000025, "cache_read_cost_per_million": 2.5, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 0.000004, "output_cost_per_token": 0.000016, "max_input_tokens": 32000, "max_output_tokens": 4096, "cache_creation_input_audio_token_cost": 0.000004, "input_cost_per_audio_token": 0.000032, "input_cost_per_image": 0.000005, "max_tokens": 4096, "output_cost_per_audio_token": 0.000064, "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "image", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/gpt-realtime-1.5-2026-02-23", "model_name": "GPT Realtime 1.5 (Feb 2026)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 4, "output_cost_per_million": 16, "cache_read_cost_per_token": 0.000004, "cache_read_cost_per_million": 4, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 0.000004, "output_cost_per_token": 0.000016, "max_input_tokens": 32000, "max_output_tokens": 4096, "cache_creation_input_audio_token_cost": 0.000004, "input_cost_per_audio_token": 0.000032, "input_cost_per_image": 0.000005, "max_tokens": 4096, "output_cost_per_audio_token": 0.000064, "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "image", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/gpt-realtime-2025-08-28", "model_name": "GPT Realtime (Aug 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 4, "output_cost_per_million": 16, "cache_read_cost_per_token": 0.000004, "cache_read_cost_per_million": 4, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000024, "max_input_tokens": 32000, "max_output_tokens": 4096, "cache_creation_input_audio_token_cost": 3e-7, "input_cost_per_audio_token": 0.00001, "input_cost_per_image": 8e-7, "max_tokens": 4096, "output_cost_per_audio_token": 0.00002, "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "image", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/gpt-realtime-mini-2025-10-06", "model_name": "GPT Realtime Mini (Oct 2025)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.6, "output_cost_per_million": 2.4, "cache_read_cost_per_token": 6e-8, "cache_read_cost_per_million": 0.06, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "input_cost_per_second": 0.0002833333333333333, "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/gpt-realtime-whisper", "supported_endpoints": [ "/v1/realtime", "/v1/realtime/transcription_sessions" ], "supported_modalities": [ "audio" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "model_id": "azure/gpt-realtime-whisper", "model_name": "GPT Realtime Whisper", "provider_id": "azure", "provider_name": "Microsoft Azure", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 6.6e-7, "output_cost_per_token": 0.00000264, "max_input_tokens": 128000, "max_output_tokens": 4096, "cache_creation_input_audio_token_cost": 3.3e-7, "input_cost_per_audio_token": 0.000011, "max_tokens": 4096, "output_cost_per_audio_token": 0.000022, "supports_audio_input": true, "supports_audio_output": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/us/gpt-4o-mini-realtime-preview-2024-12-17", "model_name": "GPT-4o Mini Realtime Preview (Dec 2024)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 0.66, "output_cost_per_million": 2.64, "cache_read_cost_per_token": 3.3e-7, "cache_read_cost_per_million": 0.33, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 0.0000055, "output_cost_per_token": 0.000022, "max_input_tokens": 128000, "max_output_tokens": 4096, "cache_creation_input_audio_token_cost": 0.000022, "input_cost_per_audio_token": 0.00011, "max_tokens": 4096, "output_cost_per_audio_token": 0.00022, "supports_audio_input": true, "supports_audio_output": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/us/gpt-4o-realtime-preview-2024-10-01", "model_name": "GPT-4o Realtime Preview (Oct 2024)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 5.5, "output_cost_per_million": 22, "cache_read_cost_per_token": 0.00000275, "cache_read_cost_per_million": 2.75, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 0.0000055, "output_cost_per_token": 0.000022, "max_input_tokens": 128000, "max_output_tokens": 4096, "cache_read_input_audio_token_cost": 0.0000025, "input_cost_per_audio_token": 0.000044, "max_tokens": 4096, "output_cost_per_audio_token": 0.00008, "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "azure/us/gpt-4o-realtime-preview-2024-12-17", "model_name": "GPT-4o Realtime Preview (Dec 2024)", "provider_id": "azure", "provider_name": "Microsoft Azure", "input_cost_per_million": 5.5, "output_cost_per_million": 22, "cache_read_cost_per_token": 0.00000275, "cache_read_cost_per_million": 2.75, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "input_cost_per_token": 1.35e-7, "output_cost_per_token": 0, "max_input_tokens": 8172, "max_tokens": 8172, "input_cost_per_image": 0.00006, "input_cost_per_video_per_second": 0.0007, "input_cost_per_audio_per_second": 0.00014, "output_vector_size": 3072, "source": "https://us-east-1.console.aws.amazon.com/bedrock/home?region=us-east-1#/model-catalog/serverless/amazon.nova-2-multimodal-embeddings-v1:0", "supports_embedding_image_input": true, "supports_image_input": true, "supports_video_input": true, "supports_audio_input": true, "model_id": "amazon.nova-2-multimodal-embeddings-v1:0", "model_name": "Nova 2 Multimodal Embeddings", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "max_output_tokens": 0, "input_cost_per_million": 0.135, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 4e-8, "output_cost_per_token": 4e-8, "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "supports_audio_input": true, "supports_system_messages": true, "supports_native_structured_output": true, "model_id": "mistral.voxtral-mini-3b-2507", "model_name": "Voxtral Mini 3B (Jul 2025)", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.04, "output_cost_per_million": 0.04, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1e-7, "output_cost_per_token": 3e-7, "max_input_tokens": 128000, "max_output_tokens": 8192, "max_tokens": 8192, "supports_audio_input": true, "supports_system_messages": true, "supports_native_structured_output": true, "model_id": "mistral.voxtral-small-24b-2507", "model_name": "Voxtral Small 24B (Jul 2025)", "provider_id": "bedrock", "provider_name": "AWS Bedrock", "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0.3, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_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": 1e-7, "output_cost_per_token": 4e-7, "max_input_tokens": 1048576, "max_output_tokens": 8192, "deprecation_date": "2026-06-01", "input_cost_per_audio_token": 7e-7, "max_tokens": 8192, "rpm": 10000, "source": "https://ai.google.dev/pricing#2_0flash", "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text", "image" ], "supports_audio_input": true, "supports_audio_output": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_web_search": true, "tpm": 10000000, "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": "2.0-flash", "model_name": "2.0 Flash", "provider_id": "google", "provider_name": "Google", "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0.39999999999999997, "cache_read_cost_per_token": 2.5e-8, "cache_read_cost_per_million": 0.024999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000025, "max_input_tokens": 1048576, "max_output_tokens": 8192, "input_cost_per_audio_token": 0.000001, "max_tokens": 8192, "source": "https://ai.google.dev/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, "model_id": "2.5-flash-native-audio-latest", "model_name": "2.5 Flash Native Audio Latest", "provider_id": "google", "provider_name": "Google", "input_cost_per_million": 0.3, "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_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000025, "max_input_tokens": 1048576, "max_output_tokens": 8192, "input_cost_per_audio_token": 0.000001, "max_tokens": 8192, "source": "https://ai.google.dev/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, "model_id": "2.5-flash-native-audio-preview-09-2025", "model_name": "2.5 Flash Native Audio Preview 09 2025", "provider_id": "google", "provider_name": "Google", "input_cost_per_million": 0.3, "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_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000025, "max_input_tokens": 1048576, "max_output_tokens": 8192, "input_cost_per_audio_token": 0.000001, "max_tokens": 8192, "source": "https://ai.google.dev/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, "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": 0.3, "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_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": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 1048576, "max_output_tokens": 65535, "cache_read_input_token_cost_above_200k_tokens": 2.5e-7, "input_cost_per_token_above_200k_tokens": 0.0000025, "input_cost_per_token_priority": 0.00000125, "input_cost_per_token_above_200k_tokens_priority": 0.0000025, "max_tokens": 65535, "output_cost_per_token_above_200k_tokens": 0.000015, "output_cost_per_token_priority": 0.00001, "output_cost_per_token_above_200k_tokens_priority": 0.000015, "rpm": 2000, "source": "https://cloud.google.com/vertex-ai/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, "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 }, "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_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, "deprecation_date": "2026-03-09", "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": 65535, "output_cost_per_token_above_200k_tokens": 0.000018, "output_cost_per_token_batches": 0.000006, "rpm": 2000, "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, "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, "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-pro-preview", "model_name": "3 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", "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_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#gemini-3.1-flash-lite", "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", "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", "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": 0.0000015, "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, "rpm": 15, "source": "https://ai.google.dev/gemini-api/docs/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, "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", "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", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_vision": true, "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, "tpm": 250000, "rpm": 10, "gemini_audio_only_live": 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": "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": 0.000012, "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, "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/models#gemini-3.1-pro-preview", "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, "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-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, "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/models#gemini-3.1-pro-preview", "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, "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-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": 65535, "input_cost_per_audio_token": 0.000001, "max_tokens": 65535, "output_cost_per_reasoning_token": 0.000009, "rpm": 2000, "source": "https://ai.google.dev/pricing/gemini-3", "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": 0.0000018, "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", "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 }, { "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000025, "max_input_tokens": 1048576, "max_output_tokens": 8192, "input_cost_per_audio_token": 0.000001, "max_tokens": 8192, "source": "https://ai.google.dev/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, "model_id": "gemini-2.5-flash-native-audio-latest", "model_name": "Gemini 2.5 Flash Native Audio Latest", "provider_id": "google", "provider_name": "Google", "input_cost_per_million": 0.3, "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_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000025, "max_input_tokens": 1048576, "max_output_tokens": 8192, "input_cost_per_audio_token": 0.000001, "max_tokens": 8192, "source": "https://ai.google.dev/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, "model_id": "gemini-2.5-flash-native-audio-preview-09-2025", "model_name": "Gemini 2.5 Flash Native Audio Preview 09 2025", "provider_id": "google", "provider_name": "Google", "input_cost_per_million": 0.3, "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_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000025, "max_input_tokens": 1048576, "max_output_tokens": 8192, "input_cost_per_audio_token": 0.000001, "max_tokens": 8192, "source": "https://ai.google.dev/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, "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": 0.3, "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_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 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-3.1-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": "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": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 1048576, "max_output_tokens": 65535, "cache_read_input_token_cost_above_200k_tokens": 2.5e-7, "input_cost_per_token_above_200k_tokens": 0.0000025, "max_tokens": 65535, "output_cost_per_token_above_200k_tokens": 0.000015, "rpm": 2000, "source": "https://cloud.google.com/vertex-ai/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, "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 }, "model_id": "gemini-pro-latest", "model_name": "Gemini Pro Latest", "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": 3e-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": 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 }, "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": 0.3, "output_cost_per_million": 2, "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": "realtime", "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, "cache_read_input_token_cost_above_200k_tokens": 2.5e-7, "input_cost_per_token_above_200k_tokens": 0.0000025, "max_tokens": 65535, "output_cost_per_token_above_200k_tokens": 0.000015, "rpm": 2000, "source": "https://cloud.google.com/vertex-ai/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, "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 }, "model_id": "pro-latest", "model_name": "Pro Latest", "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": 2.5e-7, "output_cost_per_token": 9.7e-7, "max_input_tokens": 65536, "max_output_tokens": 16384, "max_tokens": 16384, "supports_tool_choice": true, "supports_system_messages": true, "supports_audio_input": true, "supports_audio_output": true, "model_id": "novita/qwen/qwen3-omni-30b-a3b-instruct", "model_name": "Qwen3 Omni 30B A3B Instruct", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.25, "output_cost_per_million": 0.9700000000000001, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2.5e-7, "output_cost_per_token": 9.7e-7, "max_input_tokens": 65536, "max_output_tokens": 16384, "max_tokens": 16384, "supports_tool_choice": true, "supports_system_messages": true, "supports_reasoning": true, "supports_audio_input": true, "model_id": "novita/qwen/qwen3-omni-30b-a3b-thinking", "model_name": "Qwen3 Omni 30B A3B Thinking", "provider_id": "novita", "provider_name": "Novita", "input_cost_per_million": 0.25, "output_cost_per_million": 0.9700000000000001, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.00001, "max_input_tokens": 128000, "max_output_tokens": 16384, "input_cost_per_audio_token": 0.00004, "max_tokens": 16384, "output_cost_per_audio_token": 0.00008, "supports_audio_input": true, "supports_audio_output": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "gpt-4o-audio-preview", "model_name": "GPT-4o Audio Preview", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 2.5, "output_cost_per_million": 10, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.00001, "max_input_tokens": 128000, "max_output_tokens": 16384, "input_cost_per_audio_token": 0.00004, "max_tokens": 16384, "output_cost_per_audio_token": 0.00008, "supports_audio_input": true, "supports_audio_output": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "gpt-4o-audio-preview-2024-12-17", "model_name": "GPT-4o Audio Preview (Dec 2024)", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 2.5, "output_cost_per_million": 10, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.00001, "max_input_tokens": 128000, "max_output_tokens": 16384, "input_cost_per_audio_token": 0.00004, "max_tokens": 16384, "output_cost_per_audio_token": 0.00008, "supports_audio_input": true, "supports_audio_output": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "gpt-4o-audio-preview-2025-06-03", "model_name": "GPT-4o Audio Preview (Jun 2025)", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 2.5, "output_cost_per_million": 10, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": 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_audio_token": 0.00001, "max_tokens": 16384, "output_cost_per_audio_token": 0.00002, "supports_audio_input": true, "supports_audio_output": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "gpt-4o-mini-audio-preview", "model_name": "GPT-4o Mini Audio Preview", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 0.15, "output_cost_per_million": 0.6, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": 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_audio_token": 0.00001, "max_tokens": 16384, "output_cost_per_audio_token": 0.00002, "supports_audio_input": true, "supports_audio_output": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "gpt-4o-mini-audio-preview-2024-12-17", "model_name": "GPT-4o Mini Audio Preview (Dec 2024)", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 0.15, "output_cost_per_million": 0.6, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000024, "max_input_tokens": 128000, "max_output_tokens": 4096, "cache_creation_input_audio_token_cost": 3e-7, "input_cost_per_audio_token": 0.00001, "max_tokens": 4096, "output_cost_per_audio_token": 0.00002, "supports_audio_input": true, "supports_audio_output": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "gpt-4o-mini-realtime-preview", "model_name": "GPT-4o Mini Realtime Preview", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 0.6, "output_cost_per_million": 2.4, "cache_read_cost_per_token": 3e-7, "cache_read_cost_per_million": 0.3, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000024, "max_input_tokens": 128000, "max_output_tokens": 4096, "cache_creation_input_audio_token_cost": 3e-7, "input_cost_per_audio_token": 0.00001, "max_tokens": 4096, "output_cost_per_audio_token": 0.00002, "supports_audio_input": true, "supports_audio_output": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "gpt-4o-mini-realtime-preview-2024-12-17", "model_name": "GPT-4o Mini Realtime Preview (Dec 2024)", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 0.6, "output_cost_per_million": 2.4, "cache_read_cost_per_token": 3e-7, "cache_read_cost_per_million": 0.3, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.00002, "max_input_tokens": 128000, "max_output_tokens": 4096, "input_cost_per_audio_token": 0.00004, "max_tokens": 4096, "output_cost_per_audio_token": 0.00008, "supports_audio_input": true, "supports_audio_output": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "gpt-4o-realtime-preview", "model_name": "GPT-4o Realtime Preview", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 5, "output_cost_per_million": 20, "cache_read_cost_per_token": 0.0000025, "cache_read_cost_per_million": 2.5, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.00002, "max_input_tokens": 128000, "max_output_tokens": 4096, "input_cost_per_audio_token": 0.00004, "max_tokens": 4096, "output_cost_per_audio_token": 0.00008, "supports_audio_input": true, "supports_audio_output": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "gpt-4o-realtime-preview-2024-12-17", "model_name": "GPT-4o Realtime Preview (Dec 2024)", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 5, "output_cost_per_million": 20, "cache_read_cost_per_token": 0.0000025, "cache_read_cost_per_million": 2.5, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.00002, "max_input_tokens": 128000, "max_output_tokens": 4096, "input_cost_per_audio_token": 0.00004, "max_tokens": 4096, "output_cost_per_audio_token": 0.00008, "supports_audio_input": true, "supports_audio_output": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "gpt-4o-realtime-preview-2025-06-03", "model_name": "GPT-4o Realtime Preview (Jun 2025)", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 5, "output_cost_per_million": 20, "cache_read_cost_per_token": 0.0000025, "cache_read_cost_per_million": 2.5, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": false, "supports_response_schema": false, "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.00001, "max_input_tokens": 128000, "max_output_tokens": 16384, "input_cost_per_audio_token": 0.000032, "max_tokens": 16384, "output_cost_per_audio_token": 0.000064, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/realtime", "/v1/batch" ], "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_native_streaming": true, "supports_prompt_caching": false, "supports_reasoning": false, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "gpt-audio", "model_name": "GPT Audio", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 2.5, "output_cost_per_million": 10, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": false, "supports_response_schema": false, "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.00001, "max_input_tokens": 128000, "max_output_tokens": 16384, "input_cost_per_audio_token": 0.000032, "max_tokens": 16384, "output_cost_per_audio_token": 0.000064, "supported_endpoints": [ "/v1/chat/completions" ], "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_native_streaming": true, "supports_prompt_caching": false, "supports_reasoning": false, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "gpt-audio-1.5", "model_name": "GPT Audio 1.5", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 2.5, "output_cost_per_million": 10, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": false, "supports_response_schema": false, "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.00001, "max_input_tokens": 128000, "max_output_tokens": 16384, "input_cost_per_audio_token": 0.000032, "max_tokens": 16384, "output_cost_per_audio_token": 0.000064, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/realtime", "/v1/batch" ], "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_native_streaming": true, "supports_prompt_caching": false, "supports_reasoning": false, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "gpt-audio-2025-08-28", "model_name": "GPT Audio (Aug 2025)", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 2.5, "output_cost_per_million": 10, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": false, "supports_response_schema": false, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000024, "max_input_tokens": 128000, "max_output_tokens": 16384, "input_cost_per_audio_token": 0.00001, "max_tokens": 16384, "output_cost_per_audio_token": 0.00002, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/realtime", "/v1/batch" ], "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_native_streaming": true, "supports_prompt_caching": false, "supports_reasoning": false, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "gpt-audio-mini", "model_name": "GPT Audio Mini", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 0.6, "output_cost_per_million": 2.4, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": false, "supports_response_schema": false, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000024, "max_input_tokens": 128000, "max_output_tokens": 16384, "input_cost_per_audio_token": 0.00001, "max_tokens": 16384, "output_cost_per_audio_token": 0.00002, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/realtime", "/v1/batch" ], "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_native_streaming": true, "supports_prompt_caching": false, "supports_reasoning": false, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "gpt-audio-mini-2025-10-06", "model_name": "GPT Audio Mini (Oct 2025)", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 0.6, "output_cost_per_million": 2.4, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": false, "supports_response_schema": false, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000024, "max_input_tokens": 128000, "max_output_tokens": 16384, "input_cost_per_audio_token": 0.00001, "max_tokens": 16384, "output_cost_per_audio_token": 0.00002, "supported_endpoints": [ "/v1/chat/completions", "/v1/responses", "/v1/realtime", "/v1/batch" ], "supported_modalities": [ "text", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_native_streaming": true, "supports_prompt_caching": false, "supports_reasoning": false, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "gpt-audio-mini-2025-12-15", "model_name": "GPT Audio Mini (Dec 2025)", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 0.6, "output_cost_per_million": 2.4, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 0.000004, "output_cost_per_token": 0.000016, "max_input_tokens": 32000, "max_output_tokens": 4096, "cache_creation_input_audio_token_cost": 4e-7, "input_cost_per_audio_token": 0.000032, "input_cost_per_image": 0.000005, "max_tokens": 4096, "output_cost_per_audio_token": 0.000064, "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "image", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "gpt-realtime", "model_name": "GPT Realtime", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 4, "output_cost_per_million": 16, "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": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 0.000004, "output_cost_per_token": 0.000016, "max_input_tokens": 32000, "max_output_tokens": 4096, "cache_creation_input_audio_token_cost": 4e-7, "input_cost_per_audio_token": 0.000032, "input_cost_per_image": 0.000005, "max_tokens": 4096, "output_cost_per_audio_token": 0.000064, "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "image", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "gpt-realtime-1.5", "model_name": "GPT Realtime 1.5", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 4, "output_cost_per_million": 16, "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": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 0.000004, "output_cost_per_token": 0.000016, "max_input_tokens": 32000, "max_output_tokens": 4096, "cache_creation_input_audio_token_cost": 4e-7, "input_cost_per_audio_token": 0.000032, "input_cost_per_image": 0.000005, "max_tokens": 4096, "output_cost_per_audio_token": 0.000064, "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "image", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "gpt-realtime-2", "model_name": "GPT Realtime 2", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 4, "output_cost_per_million": 16, "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": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 0.000004, "output_cost_per_token": 0.000024, "max_input_tokens": 128000, "max_output_tokens": 32000, "cache_creation_input_audio_token_cost": 4e-7, "cache_read_input_audio_token_cost": 4e-7, "input_cost_per_audio_token": 0.000032, "input_cost_per_image": 0.000005, "max_tokens": 32000, "output_cost_per_audio_token": 0.000064, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "image", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "gpt-realtime-2.1", "model_name": "GPT Realtime 2.1", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 4, "output_cost_per_million": 24, "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": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000024, "max_input_tokens": 128000, "max_output_tokens": 4096, "cache_creation_input_audio_token_cost": 3e-7, "cache_read_input_audio_token_cost": 3e-7, "input_cost_per_audio_token": 0.00001, "input_cost_per_image": 8e-7, "max_tokens": 4096, "output_cost_per_audio_token": 0.00002, "regional_processing_uplift_multiplier_eu": 1.1, "regional_processing_uplift_multiplier_us": 1.1, "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "image", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "gpt-realtime-2.1-mini", "model_name": "GPT Realtime 2.1 Mini", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 0.6, "output_cost_per_million": 2.4, "cache_read_cost_per_token": 6e-8, "cache_read_cost_per_million": 0.06, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 0.000004, "output_cost_per_token": 0.000016, "max_input_tokens": 32000, "max_output_tokens": 4096, "cache_creation_input_audio_token_cost": 4e-7, "input_cost_per_audio_token": 0.000032, "input_cost_per_image": 0.000005, "max_tokens": 4096, "output_cost_per_audio_token": 0.000064, "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "image", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "gpt-realtime-2025-08-28", "model_name": "GPT Realtime (Aug 2025)", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 4, "output_cost_per_million": 16, "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": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000024, "max_input_tokens": 128000, "max_output_tokens": 4096, "cache_creation_input_audio_token_cost": 3e-7, "cache_read_input_audio_token_cost": 3e-7, "input_cost_per_audio_token": 0.00001, "max_tokens": 4096, "output_cost_per_audio_token": 0.00002, "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "image", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "gpt-realtime-mini", "model_name": "GPT Realtime Mini", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 0.6, "output_cost_per_million": 2.4, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000024, "max_input_tokens": 128000, "max_output_tokens": 4096, "cache_creation_input_audio_token_cost": 3e-7, "cache_read_input_audio_token_cost": 3e-7, "input_cost_per_audio_token": 0.00001, "input_cost_per_image": 8e-7, "max_tokens": 4096, "output_cost_per_audio_token": 0.00002, "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "image", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "gpt-realtime-mini-2025-10-06", "model_name": "GPT Realtime Mini (Oct 2025)", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 0.6, "output_cost_per_million": 2.4, "cache_read_cost_per_token": 6e-8, "cache_read_cost_per_million": 0.06, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000024, "max_input_tokens": 128000, "max_output_tokens": 4096, "cache_creation_input_audio_token_cost": 3e-7, "cache_read_input_audio_token_cost": 3e-7, "input_cost_per_audio_token": 0.00001, "input_cost_per_image": 8e-7, "max_tokens": 4096, "output_cost_per_audio_token": 0.00002, "supported_endpoints": [ "/v1/realtime" ], "supported_modalities": [ "text", "image", "audio" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "gpt-realtime-mini-2025-12-15", "model_name": "GPT Realtime Mini (Dec 2025)", "provider_id": "openai", "provider_name": "OpenAI", "input_cost_per_million": 0.6, "output_cost_per_million": 2.4, "cache_read_cost_per_token": 6e-8, "cache_read_cost_per_million": 0.06, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_parallel_functions": true, "supports_vision": false, "supports_json_mode": false }, { "input_cost_per_second": 0.0002833333333333333, "source": "https://platform.openai.com/docs/models/gpt-realtime-whisper", "supported_endpoints": [ "/v1/realtime", "/v1/realtime/transcription_sessions" ], "supported_modalities": [ "audio" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "model_id": "gpt-realtime-whisper", "model_name": "GPT Realtime Whisper", "provider_id": "openai", "provider_name": "OpenAI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_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": 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, "rpm": 2000, "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-lite", "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": 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": 0.0000015, "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, "rpm": 2000, "source": "https://ai.google.dev/pricing/gemini-3", "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": 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, "cache_creation_input_token_cost_above_200k_tokens": 2.5e-7, "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/google/gemini-3.1-pro-preview", "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, "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": 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, "output_cost_per_token": 0, "max_input_tokens": 2000000, "max_tokens": 2000000, "supports_tool_choice": true, "supports_reasoning": true, "supports_audio_input": true, "supports_video_input": true, "model_id": "openrouter/openrouter/auto", "model_name": "Auto", "provider_id": "openrouter", "provider_name": "OpenRouter", "max_output_tokens": 0, "input_cost_per_million": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "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": 4e-7, "output_cost_per_token": 0.000002, "max_input_tokens": 1048576, "max_output_tokens": 131072, "max_tokens": 131072, "supports_tool_choice": true, "supports_reasoning": true, "supports_audio_input": true, "supports_video_input": true, "supports_prompt_caching": true, "model_id": "openrouter/xiaomi/mimo-v2.5", "model_name": "Mimo V2.5", "provider_id": "openrouter", "provider_name": "OpenRouter", "input_cost_per_million": 0.39999999999999997, "output_cost_per_million": 2, "cache_read_cost_per_token": 8e-8, "cache_read_cost_per_million": 0.08, "cache_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, "supports_system_messages": true, "supports_tool_choice": true, "supports_audio_input": true, "supports_audio_output": true, "model_id": "openai/gpt-4o", "model_name": "GPT-4o", "provider_id": "replicate", "provider_name": "Replicate", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 2.5, "output_cost_per_million": 10, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "input_cost_per_token": 5e-7, "output_cost_per_token": 0.0001, "max_input_tokens": 4096, "max_output_tokens": 4096, "deprecation_date": "2025-06-19", "max_tokens": 4096, "source": "https://cloud.sambanova.ai/plans/pricing", "supports_audio_input": true, "model_id": "sambanova/Qwen2-Audio-7B-Instruct", "model_name": "Qwen2 Audio 7B Instruct", "provider_id": "sambanova", "provider_name": "Sambanova", "input_cost_per_million": 0.5, "output_cost_per_million": 100, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1.5e-7, "output_cost_per_token": 3.5e-7, "max_input_tokens": 32000, "max_output_tokens": 16384, "input_cost_per_audio_token": 1.5e-7, "max_tokens": 16384, "supports_audio_input": true, "model_id": "scaleway/mistralai/voxtral-small-24b-2507", "model_name": "Voxtral Small 24B (Jul 2025)", "provider_id": "scaleway", "provider_name": "Scaleway", "input_cost_per_million": 0.15, "output_cost_per_million": 0.35, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "max_output_tokens": 8000, "max_tokens": 8000, "input_cost_per_second": 0, "output_cost_per_second": 0.0000277778, "source": "https://soniox.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ], "supports_audio_input": true, "model_id": "soniox/stt-async-v4", "model_name": "STT Async V4", "provider_id": "soniox", "provider_name": "Soniox", "max_input_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "max_output_tokens": 8000, "max_tokens": 8000, "input_cost_per_second": 0, "output_cost_per_second": 0.0000277778, "source": "https://soniox.com/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ], "supports_audio_input": true, "model_id": "soniox/stt-async-v5", "model_name": "STT Async V5", "provider_id": "soniox", "provider_name": "Soniox", "max_input_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 1e-7, "output_cost_per_token": 4e-7, "max_input_tokens": 1048576, "max_output_tokens": 8192, "deprecation_date": "2026-06-01", "input_cost_per_audio_token": 7e-7, "max_tokens": 8192, "source": "https://ai.google.dev/pricing#2_0flash", "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text", "image" ], "supports_audio_input": true, "supports_audio_output": true, "supports_prompt_caching": 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 }, "model_id": "gemini-2.0-flash", "model_name": "Gemini 2.0 Flash", "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": 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": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 1048576, "max_output_tokens": 65535, "cache_read_input_token_cost_above_200k_tokens": 2.5e-7, "cache_creation_input_token_cost_above_200k_tokens": 2.5e-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/vertex-ai/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, "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 }, "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", "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, "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, "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, "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", "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", "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": 0.0000015, "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", "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, "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", "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, "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", "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, "input_cost_per_audio_token": 0.000001, "max_tokens": 65535, "output_cost_per_reasoning_token": 0.000009, "source": "https://ai.google.dev/pricing/gemini-3", "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": 0.0000018, "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", "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", "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": 0.000002, "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://ai.google.dev/gemini-api/docs/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": 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 }, "gemini_native_audio": true, "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": 0.3, "output_cost_per_million": 2, "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": "realtime", "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": 5e-7, "max_input_tokens": 2000000, "max_output_tokens": 2000000, "input_cost_per_token_above_128k_tokens": 4e-7, "max_tokens": 2000000, "output_cost_per_token_above_128k_tokens": 0.000001, "source": "https://docs.x.ai/docs/models/grok-4-1-fast-reasoning", "supports_audio_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "grok-4-1-fast", "model_name": "Grok 4 1 Fast", "provider_id": "xai", "provider_name": "xAI", "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": 2000000, "max_output_tokens": 2000000, "deprecation_date": "2026-05-15", "input_cost_per_token_above_128k_tokens": 4e-7, "max_tokens": 2000000, "output_cost_per_token_above_128k_tokens": 0.000001, "source": "https://docs.x.ai/docs/models/grok-4-1-fast-non-reasoning", "supports_audio_input": true, "supports_prompt_caching": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "grok-4-1-fast-non-reasoning", "model_name": "Grok 4 1 Fast Non Reasoning", "provider_id": "xai", "provider_name": "xAI", "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", "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": 2000000, "max_output_tokens": 2000000, "deprecation_date": "2026-05-15", "input_cost_per_token_above_128k_tokens": 4e-7, "max_tokens": 2000000, "output_cost_per_token_above_128k_tokens": 0.000001, "source": "https://docs.x.ai/docs/models/grok-4-1-fast-non-reasoning", "supports_audio_input": true, "supports_prompt_caching": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "grok-4-1-fast-non-reasoning-latest", "model_name": "Grok 4 1 Fast Non Reasoning Latest", "provider_id": "xai", "provider_name": "xAI", "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", "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": 2000000, "max_output_tokens": 2000000, "deprecation_date": "2026-05-15", "input_cost_per_token_above_128k_tokens": 4e-7, "max_tokens": 2000000, "output_cost_per_token_above_128k_tokens": 0.000001, "source": "https://docs.x.ai/docs/models/grok-4-1-fast-reasoning", "supports_audio_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "grok-4-1-fast-reasoning", "model_name": "Grok 4 1 Fast Reasoning", "provider_id": "xai", "provider_name": "xAI", "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", "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": 2000000, "max_output_tokens": 2000000, "deprecation_date": "2026-05-15", "input_cost_per_token_above_128k_tokens": 4e-7, "max_tokens": 2000000, "output_cost_per_token_above_128k_tokens": 0.000001, "source": "https://docs.x.ai/docs/models/grok-4-1-fast-reasoning", "supports_audio_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "grok-4-1-fast-reasoning-latest", "model_name": "Grok 4 1 Fast Reasoning Latest", "provider_id": "xai", "provider_name": "xAI", "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", "supports_json_mode": true, "supports_parallel_functions": false } ]