commit 8ec0eaa6eb1af21775fd00625fc91792372e98ea Author: Richard Wang Date: Mon Nov 24 09:45:53 2025 +0000 Add pricing.json diff --git a/pricing.json b/pricing.json new file mode 100644 index 0000000..f5ce90e --- /dev/null +++ b/pricing.json @@ -0,0 +1,24870 @@ +{ + "1024-x-1024/50-steps/bedrock/amazon.nova-canvas-v1:0": { + "max_input_tokens": 2600, + "mode": "image_generation", + "output_cost_per_image": 0.06, + "provider": "bedrock" + }, + "1024-x-1024/50-steps/stability.stable-diffusion-xl-v1": { + "max_input_tokens": 77, + "max_tokens": 77, + "mode": "image_generation", + "output_cost_per_image": 0.04, + "provider": "bedrock" + }, + "1024-x-1024/dall-e-2": { + "input_cost_per_pixel": 1.9e-8, + "mode": "image_generation", + "output_cost_per_pixel": 0, + "provider": "openai" + }, + "1024-x-1024/max-steps/stability.stable-diffusion-xl-v1": { + "max_input_tokens": 77, + "max_tokens": 77, + "mode": "image_generation", + "output_cost_per_image": 0.08, + "provider": "bedrock" + }, + "256-x-256/dall-e-2": { + "input_cost_per_pixel": 2.4414e-7, + "mode": "image_generation", + "output_cost_per_pixel": 0, + "provider": "openai" + }, + "512-x-512/50-steps/stability.stable-diffusion-xl-v0": { + "max_input_tokens": 77, + "max_tokens": 77, + "mode": "image_generation", + "output_cost_per_image": 0.018, + "provider": "bedrock" + }, + "512-x-512/dall-e-2": { + "input_cost_per_pixel": 6.86e-8, + "mode": "image_generation", + "output_cost_per_pixel": 0, + "provider": "openai" + }, + "512-x-512/max-steps/stability.stable-diffusion-xl-v0": { + "max_input_tokens": 77, + "max_tokens": 77, + "mode": "image_generation", + "output_cost_per_image": 0.036, + "provider": "bedrock" + }, + "ai21.j2-mid-v1": { + "input_cost_per_token": 0.0000125, + "max_input_tokens": 8191, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 0.0000125, + "provider": "bedrock" + }, + "ai21.j2-ultra-v1": { + "input_cost_per_token": 0.0000188, + "max_input_tokens": 8191, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 0.0000188, + "provider": "bedrock" + }, + "ai21.jamba-1-5-large-v1:0": { + "input_cost_per_token": 0.000002, + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 0.000008, + "provider": "bedrock" + }, + "ai21.jamba-1-5-mini-v1:0": { + "input_cost_per_token": 2e-7, + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 4e-7, + "provider": "bedrock" + }, + "ai21.jamba-instruct-v1:0": { + "input_cost_per_token": 5e-7, + "max_input_tokens": 70000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 7e-7, + "supports_system_messages": true, + "provider": "bedrock" + }, + "aiml/dall-e-2": { + "metadata": { + "notes": "DALL-E 2 via AI/ML API - Reliable text-to-image generation" + }, + "mode": "image_generation", + "output_cost_per_image": 0.021, + "source": "https://docs.aimlapi.com/", + "supported_endpoints": ["/v1/images/generations"], + "provider": "aiml" + }, + "aiml/dall-e-3": { + "metadata": { + "notes": "DALL-E 3 via AI/ML API - High-quality text-to-image generation" + }, + "mode": "image_generation", + "output_cost_per_image": 0.042, + "source": "https://docs.aimlapi.com/", + "supported_endpoints": ["/v1/images/generations"], + "provider": "aiml" + }, + "aiml/flux-pro": { + "metadata": { + "notes": "Flux Dev - Development version optimized for experimentation" + }, + "mode": "image_generation", + "output_cost_per_image": 0.053, + "source": "https://docs.aimlapi.com/", + "supported_endpoints": ["/v1/images/generations"], + "provider": "aiml" + }, + "aiml/flux-pro/v1.1": { + "mode": "image_generation", + "output_cost_per_image": 0.042, + "supported_endpoints": ["/v1/images/generations"], + "provider": "aiml" + }, + "aiml/flux-pro/v1.1-ultra": { + "mode": "image_generation", + "output_cost_per_image": 0.063, + "supported_endpoints": ["/v1/images/generations"], + "provider": "aiml" + }, + "aiml/flux-realism": { + "metadata": { + "notes": "Flux Pro - Professional-grade image generation model" + }, + "mode": "image_generation", + "output_cost_per_image": 0.037, + "source": "https://docs.aimlapi.com/", + "supported_endpoints": ["/v1/images/generations"], + "provider": "aiml" + }, + "aiml/flux/dev": { + "metadata": { + "notes": "Flux Dev - Development version optimized for experimentation" + }, + "mode": "image_generation", + "output_cost_per_image": 0.026, + "source": "https://docs.aimlapi.com/", + "supported_endpoints": ["/v1/images/generations"], + "provider": "aiml" + }, + "aiml/flux/kontext-max/text-to-image": { + "metadata": { + "notes": "Flux Pro v1.1 - Enhanced version with improved capabilities and 6x faster inference speed" + }, + "mode": "image_generation", + "output_cost_per_image": 0.084, + "source": "https://docs.aimlapi.com/", + "supported_endpoints": ["/v1/images/generations"], + "provider": "aiml" + }, + "aiml/flux/kontext-pro/text-to-image": { + "metadata": { + "notes": "Flux Pro v1.1 - Enhanced version with improved capabilities and 6x faster inference speed" + }, + "mode": "image_generation", + "output_cost_per_image": 0.042, + "source": "https://docs.aimlapi.com/", + "supported_endpoints": ["/v1/images/generations"], + "provider": "aiml" + }, + "aiml/flux/schnell": { + "metadata": { + "notes": "Flux Schnell - Fast generation model optimized for speed" + }, + "mode": "image_generation", + "output_cost_per_image": 0.003, + "source": "https://docs.aimlapi.com/", + "supported_endpoints": ["/v1/images/generations"], + "provider": "aiml" + }, + "amazon.nova-lite-v1:0": { + "input_cost_per_token": 6e-8, + "max_input_tokens": 300000, + "max_output_tokens": 10000, + "max_tokens": 10000, + "mode": "chat", + "output_cost_per_token": 2.4e-7, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_vision": true, + "provider": "bedrock_converse" + }, + "amazon.nova-micro-v1:0": { + "input_cost_per_token": 3.5e-8, + "max_input_tokens": 128000, + "max_output_tokens": 10000, + "max_tokens": 10000, + "mode": "chat", + "output_cost_per_token": 1.4e-7, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "provider": "bedrock_converse" + }, + "amazon.nova-pro-v1:0": { + "input_cost_per_token": 8e-7, + "max_input_tokens": 300000, + "max_output_tokens": 10000, + "max_tokens": 10000, + "mode": "chat", + "output_cost_per_token": 0.0000032, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_vision": true, + "provider": "bedrock_converse" + }, + "amazon.rerank-v1:0": { + "input_cost_per_query": 0.001, + "input_cost_per_token": 0, + "max_document_chunks_per_query": 100, + "max_input_tokens": 32000, + "max_output_tokens": 32000, + "max_query_tokens": 32000, + "max_tokens": 32000, + "max_tokens_per_document_chunk": 512, + "mode": "rerank", + "output_cost_per_token": 0, + "provider": "bedrock" + }, + "amazon.titan-embed-image-v1": { + "input_cost_per_image": 0.00006, + "input_cost_per_token": 8e-7, + "max_input_tokens": 128, + "max_tokens": 128, + "metadata": { + "notes": "'supports_image_input' is a deprecated field. Use 'supports_embedding_image_input' instead." + }, + "mode": "embedding", + "output_cost_per_token": 0, + "output_vector_size": 1024, + "source": "https://us-east-1.console.aws.amazon.com/bedrock/home?region=us-east-1#/providers?model=amazon.titan-image-generator-v1", + "supports_embedding_image_input": true, + "supports_image_input": true, + "provider": "bedrock" + }, + "amazon.titan-embed-text-v1": { + "input_cost_per_token": 1e-7, + "max_input_tokens": 8192, + "max_tokens": 8192, + "mode": "embedding", + "output_cost_per_token": 0, + "output_vector_size": 1536, + "provider": "bedrock" + }, + "amazon.titan-embed-text-v2:0": { + "input_cost_per_token": 2e-7, + "max_input_tokens": 8192, + "max_tokens": 8192, + "mode": "embedding", + "output_cost_per_token": 0, + "output_vector_size": 1024, + "provider": "bedrock" + }, + "amazon.titan-image-generator-v1": { + "input_cost_per_image": 0, + "output_cost_per_image": 0.008, + "output_cost_per_image_premium_image": 0.01, + "output_cost_per_image_above_512_and_512_pixels": 0.01, + "output_cost_per_image_above_512_and_512_pixels_and_premium_image": 0.012, + "mode": "image_generation", + "provider": "bedrock" + }, + "amazon.titan-image-generator-v2": { + "input_cost_per_image": 0, + "output_cost_per_image": 0.008, + "output_cost_per_image_premium_image": 0.01, + "output_cost_per_image_above_1024_and_1024_pixels": 0.01, + "output_cost_per_image_above_1024_and_1024_pixels_and_premium_image": 0.012, + "mode": "image_generation", + "provider": "bedrock" + }, + "twelvelabs.marengo-embed-2-7-v1:0": { + "input_cost_per_token": 0.00007, + "max_input_tokens": 77, + "max_tokens": 77, + "mode": "embedding", + "output_cost_per_token": 0, + "output_vector_size": 1024, + "supports_embedding_image_input": true, + "supports_image_input": true, + "provider": "bedrock" + }, + "us.twelvelabs.marengo-embed-2-7-v1:0": { + "input_cost_per_token": 0.00007, + "input_cost_per_video_per_second": 0.0007, + "input_cost_per_audio_per_second": 0.00014, + "input_cost_per_image": 0.0001, + "max_input_tokens": 77, + "max_tokens": 77, + "mode": "embedding", + "output_cost_per_token": 0, + "output_vector_size": 1024, + "supports_embedding_image_input": true, + "supports_image_input": true, + "provider": "bedrock" + }, + "eu.twelvelabs.marengo-embed-2-7-v1:0": { + "input_cost_per_token": 0.00007, + "input_cost_per_video_per_second": 0.0007, + "input_cost_per_audio_per_second": 0.00014, + "input_cost_per_image": 0.0001, + "max_input_tokens": 77, + "max_tokens": 77, + "mode": "embedding", + "output_cost_per_token": 0, + "output_vector_size": 1024, + "supports_embedding_image_input": true, + "supports_image_input": true, + "provider": "bedrock" + }, + "twelvelabs.pegasus-1-2-v1:0": { + "input_cost_per_video_per_second": 0.00049, + "output_cost_per_token": 0.0000075, + "mode": "chat", + "supports_video_input": true, + "provider": "bedrock" + }, + "us.twelvelabs.pegasus-1-2-v1:0": { + "input_cost_per_video_per_second": 0.00049, + "output_cost_per_token": 0.0000075, + "mode": "chat", + "supports_video_input": true, + "provider": "bedrock" + }, + "eu.twelvelabs.pegasus-1-2-v1:0": { + "input_cost_per_video_per_second": 0.00049, + "output_cost_per_token": 0.0000075, + "mode": "chat", + "supports_video_input": true, + "provider": "bedrock" + }, + "amazon.titan-text-express-v1": { + "input_cost_per_token": 0.0000013, + "max_input_tokens": 42000, + "max_output_tokens": 8000, + "max_tokens": 8000, + "mode": "chat", + "output_cost_per_token": 0.0000017, + "provider": "bedrock" + }, + "amazon.titan-text-lite-v1": { + "input_cost_per_token": 3e-7, + "max_input_tokens": 42000, + "max_output_tokens": 4000, + "max_tokens": 4000, + "mode": "chat", + "output_cost_per_token": 4e-7, + "provider": "bedrock" + }, + "amazon.titan-text-premier-v1:0": { + "input_cost_per_token": 5e-7, + "max_input_tokens": 42000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 0.0000015, + "provider": "bedrock" + }, + "anthropic.claude-3-5-haiku-20241022-v1:0": { + "cache_creation_input_token_cost": 0.000001, + "cache_read_input_token_cost": 8e-8, + "input_cost_per_token": 8e-7, + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.000004, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "provider": "bedrock" + }, + "anthropic.claude-haiku-4-5-20251001-v1:0": { + "cache_creation_input_token_cost": 0.00000125, + "cache_read_input_token_cost": 1e-7, + "input_cost_per_token": 0.000001, + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 0.000005, + "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock", + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 346, + "provider": "bedrock_converse" + }, + "anthropic.claude-haiku-4-5@20251001": { + "cache_creation_input_token_cost": 0.00000125, + "cache_read_input_token_cost": 1e-7, + "input_cost_per_token": 0.000001, + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 0.000005, + "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock", + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 346, + "provider": "bedrock_converse" + }, + "anthropic.claude-3-5-sonnet-20240620-v1:0": { + "input_cost_per_token": 0.000003, + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.000015, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "bedrock" + }, + "anthropic.claude-3-5-sonnet-20241022-v2:0": { + "cache_creation_input_token_cost": 0.00000375, + "cache_read_input_token_cost": 3e-7, + "input_cost_per_token": 0.000003, + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.000015, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "bedrock" + }, + "anthropic.claude-3-7-sonnet-20240620-v1:0": { + "cache_creation_input_token_cost": 0.0000045, + "cache_read_input_token_cost": 3.6e-7, + "input_cost_per_token": 0.0000036, + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.000018, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "bedrock" + }, + "anthropic.claude-3-7-sonnet-20250219-v1:0": { + "cache_creation_input_token_cost": 0.00000375, + "cache_read_input_token_cost": 3e-7, + "input_cost_per_token": 0.000003, + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.000015, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "bedrock_converse" + }, + "anthropic.claude-3-haiku-20240307-v1:0": { + "input_cost_per_token": 2.5e-7, + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.00000125, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "bedrock" + }, + "anthropic.claude-3-opus-20240229-v1:0": { + "input_cost_per_token": 0.000015, + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.000075, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "bedrock" + }, + "anthropic.claude-3-sonnet-20240229-v1:0": { + "input_cost_per_token": 0.000003, + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.000015, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "bedrock" + }, + "anthropic.claude-instant-v1": { + "input_cost_per_token": 8e-7, + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 0.0000024, + "supports_tool_choice": true, + "provider": "bedrock" + }, + "anthropic.claude-opus-4-1-20250805-v1:0": { + "cache_creation_input_token_cost": 0.00001875, + "cache_read_input_token_cost": 0.0000015, + "input_cost_per_token": 0.000015, + "max_input_tokens": 200000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 0.000075, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159, + "provider": "bedrock_converse" + }, + "anthropic.claude-opus-4-20250514-v1:0": { + "cache_creation_input_token_cost": 0.00001875, + "cache_read_input_token_cost": 0.0000015, + "input_cost_per_token": 0.000015, + "max_input_tokens": 200000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 0.000075, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159, + "provider": "bedrock_converse" + }, + "anthropic.claude-sonnet-4-20250514-v1:0": { + "cache_creation_input_token_cost": 0.00000375, + "cache_read_input_token_cost": 3e-7, + "input_cost_per_token": 0.000003, + "input_cost_per_token_above_200k_tokens": 0.000006, + "output_cost_per_token_above_200k_tokens": 0.0000225, + "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, + "cache_read_input_token_cost_above_200k_tokens": 6e-7, + "max_input_tokens": 1000000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 0.000015, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159, + "provider": "bedrock_converse" + }, + "anthropic.claude-sonnet-4-5-20250929-v1:0": { + "cache_creation_input_token_cost": 0.00000375, + "cache_read_input_token_cost": 3e-7, + "input_cost_per_token": 0.000003, + "input_cost_per_token_above_200k_tokens": 0.000006, + "output_cost_per_token_above_200k_tokens": 0.0000225, + "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, + "cache_read_input_token_cost_above_200k_tokens": 6e-7, + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 0.000015, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159, + "provider": "bedrock_converse" + }, + "anthropic.claude-v1": { + "input_cost_per_token": 0.000008, + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 0.000024, + "provider": "bedrock" + }, + "anthropic.claude-v2:1": { + "input_cost_per_token": 0.000008, + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 0.000024, + "supports_tool_choice": true, + "provider": "bedrock" + }, + "anyscale/HuggingFaceH4/zephyr-7b-beta": { + "input_cost_per_token": 1.5e-7, + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.5e-7, + "provider": "anyscale" + }, + "anyscale/codellama/CodeLlama-34b-Instruct-hf": { + "input_cost_per_token": 0.000001, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.000001, + "provider": "anyscale" + }, + "anyscale/codellama/CodeLlama-70b-Instruct-hf": { + "input_cost_per_token": 0.000001, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.000001, + "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/codellama-CodeLlama-70b-Instruct-hf", + "provider": "anyscale" + }, + "anyscale/google/gemma-7b-it": { + "input_cost_per_token": 1.5e-7, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.5e-7, + "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/google-gemma-7b-it", + "provider": "anyscale" + }, + "anyscale/meta-llama/Llama-2-13b-chat-hf": { + "input_cost_per_token": 2.5e-7, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2.5e-7, + "provider": "anyscale" + }, + "anyscale/meta-llama/Llama-2-70b-chat-hf": { + "input_cost_per_token": 0.000001, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.000001, + "provider": "anyscale" + }, + "anyscale/meta-llama/Llama-2-7b-chat-hf": { + "input_cost_per_token": 1.5e-7, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.5e-7, + "provider": "anyscale" + }, + "anyscale/meta-llama/Meta-Llama-3-70B-Instruct": { + "input_cost_per_token": 0.000001, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.000001, + "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/meta-llama-Meta-Llama-3-70B-Instruct", + "provider": "anyscale" + }, + "anyscale/meta-llama/Meta-Llama-3-8B-Instruct": { + "input_cost_per_token": 1.5e-7, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.5e-7, + "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/meta-llama-Meta-Llama-3-8B-Instruct", + "provider": "anyscale" + }, + "anyscale/mistralai/Mistral-7B-Instruct-v0.1": { + "input_cost_per_token": 1.5e-7, + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.5e-7, + "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/mistralai-Mistral-7B-Instruct-v0.1", + "supports_function_calling": true, + "provider": "anyscale" + }, + "anyscale/mistralai/Mixtral-8x22B-Instruct-v0.1": { + "input_cost_per_token": 9e-7, + "max_input_tokens": 65536, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 9e-7, + "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/mistralai-Mixtral-8x22B-Instruct-v0.1", + "supports_function_calling": true, + "provider": "anyscale" + }, + "anyscale/mistralai/Mixtral-8x7B-Instruct-v0.1": { + "input_cost_per_token": 1.5e-7, + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.5e-7, + "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/mistralai-Mixtral-8x7B-Instruct-v0.1", + "supports_function_calling": true, + "provider": "anyscale" + }, + "apac.amazon.nova-lite-v1:0": { + "input_cost_per_token": 6.3e-8, + "max_input_tokens": 300000, + "max_output_tokens": 10000, + "max_tokens": 10000, + "mode": "chat", + "output_cost_per_token": 2.52e-7, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_vision": true, + "provider": "bedrock_converse" + }, + "apac.amazon.nova-micro-v1:0": { + "input_cost_per_token": 3.7e-8, + "max_input_tokens": 128000, + "max_output_tokens": 10000, + "max_tokens": 10000, + "mode": "chat", + "output_cost_per_token": 1.48e-7, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "provider": "bedrock_converse" + }, + "apac.amazon.nova-pro-v1:0": { + "input_cost_per_token": 8.4e-7, + "max_input_tokens": 300000, + "max_output_tokens": 10000, + "max_tokens": 10000, + "mode": "chat", + "output_cost_per_token": 0.00000336, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_vision": true, + "provider": "bedrock_converse" + }, + "apac.anthropic.claude-3-5-sonnet-20240620-v1:0": { + "input_cost_per_token": 0.000003, + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.000015, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "bedrock" + }, + "apac.anthropic.claude-3-5-sonnet-20241022-v2:0": { + "cache_creation_input_token_cost": 0.00000375, + "cache_read_input_token_cost": 3e-7, + "input_cost_per_token": 0.000003, + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.000015, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "bedrock" + }, + "apac.anthropic.claude-3-haiku-20240307-v1:0": { + "input_cost_per_token": 2.5e-7, + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.00000125, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "bedrock" + }, + "apac.anthropic.claude-haiku-4-5-20251001-v1:0": { + "cache_creation_input_token_cost": 0.000001375, + "cache_read_input_token_cost": 1.1e-7, + "input_cost_per_token": 0.0000011, + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 0.0000055, + "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock", + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 346, + "provider": "bedrock_converse" + }, + "apac.anthropic.claude-3-sonnet-20240229-v1:0": { + "input_cost_per_token": 0.000003, + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.000015, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "bedrock" + }, + "apac.anthropic.claude-sonnet-4-20250514-v1:0": { + "cache_creation_input_token_cost": 0.00000375, + "cache_read_input_token_cost": 3e-7, + "input_cost_per_token": 0.000003, + "input_cost_per_token_above_200k_tokens": 0.000006, + "output_cost_per_token_above_200k_tokens": 0.0000225, + "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, + "cache_read_input_token_cost_above_200k_tokens": 6e-7, + "max_input_tokens": 1000000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 0.000015, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159, + "provider": "bedrock_converse" + }, + "assemblyai/best": { + "input_cost_per_second": 0.00003333, + "mode": "audio_transcription", + "output_cost_per_second": 0, + "provider": "assemblyai" + }, + "assemblyai/nano": { + "input_cost_per_second": 0.00010278, + "mode": "audio_transcription", + "output_cost_per_second": 0, + "provider": "assemblyai" + }, + "au.anthropic.claude-sonnet-4-5-20250929-v1:0": { + "cache_creation_input_token_cost": 0.000004125, + "cache_read_input_token_cost": 3.3e-7, + "input_cost_per_token": 0.0000033, + "input_cost_per_token_above_200k_tokens": 0.0000066, + "output_cost_per_token_above_200k_tokens": 0.00002475, + "cache_creation_input_token_cost_above_200k_tokens": 0.00000825, + "cache_read_input_token_cost_above_200k_tokens": 6.6e-7, + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 0.0000165, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 346, + "provider": "bedrock_converse" + }, + "azure/ada": { + "input_cost_per_token": 1e-7, + "max_input_tokens": 8191, + "max_tokens": 8191, + "mode": "embedding", + "output_cost_per_token": 0, + "provider": "azure" + }, + "azure/codex-mini": { + "cache_read_input_token_cost": 3.75e-7, + "input_cost_per_token": 0.0000015, + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "responses", + "output_cost_per_token": 0.000006, + "supported_endpoints": ["/v1/responses"], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "azure" + }, + "azure/command-r-plus": { + "input_cost_per_token": 0.000003, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.000015, + "supports_function_calling": true, + "provider": "azure" + }, + "azure/computer-use-preview": { + "input_cost_per_token": 0.000003, + "max_input_tokens": 8192, + "max_output_tokens": 1024, + "max_tokens": 1024, + "mode": "chat", + "output_cost_per_token": 0.000012, + "supported_endpoints": ["/v1/responses"], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "azure" + }, + "azure/container": { + "code_interpreter_cost_per_session": 0.03, + "mode": "chat", + "provider": "azure" + }, + "azure/eu/gpt-4o-2024-08-06": { + "deprecation_date": "2026-02-27", + "cache_read_input_token_cost": 0.000001375, + "input_cost_per_token": 0.00000275, + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 0.000011, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "azure" + }, + "azure/eu/gpt-4o-2024-11-20": { + "deprecation_date": "2026-03-01", + "cache_creation_input_token_cost": 0.00000138, + "input_cost_per_token": 0.00000275, + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 0.000011, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "azure" + }, + "azure/eu/gpt-4o-mini-2024-07-18": { + "cache_read_input_token_cost": 8.3e-8, + "input_cost_per_token": 1.65e-7, + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 6.6e-7, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "azure" + }, + "azure/eu/gpt-4o-mini-realtime-preview-2024-12-17": { + "cache_creation_input_audio_token_cost": 3.3e-7, + "cache_read_input_token_cost": 3.3e-7, + "input_cost_per_audio_token": 0.000011, + "input_cost_per_token": 6.6e-7, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_audio_token": 0.000022, + "output_cost_per_token": 0.00000264, + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "azure" + }, + "azure/eu/gpt-4o-realtime-preview-2024-10-01": { + "cache_creation_input_audio_token_cost": 0.000022, + "cache_read_input_token_cost": 0.00000275, + "input_cost_per_audio_token": 0.00011, + "input_cost_per_token": 0.0000055, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_audio_token": 0.00022, + "output_cost_per_token": 0.000022, + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "azure" + }, + "azure/eu/gpt-4o-realtime-preview-2024-12-17": { + "cache_read_input_audio_token_cost": 0.0000025, + "cache_read_input_token_cost": 0.00000275, + "input_cost_per_audio_token": 0.000044, + "input_cost_per_token": 0.0000055, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_audio_token": 0.00008, + "output_cost_per_token": 0.000022, + "supported_modalities": ["text", "audio"], + "supported_output_modalities": ["text", "audio"], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "azure" + }, + "azure/eu/gpt-5-2025-08-07": { + "cache_read_input_token_cost": 1.375e-7, + "input_cost_per_token": 0.000001375, + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.000011, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "azure" + }, + "azure/eu/gpt-5-mini-2025-08-07": { + "cache_read_input_token_cost": 2.75e-8, + "input_cost_per_token": 2.75e-7, + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.0000022, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "azure" + }, + "azure/eu/gpt-5.1": { + "cache_read_input_token_cost": 1.4e-7, + "input_cost_per_token": 0.00000138, + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.000011, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text", "image"], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "azure" + }, + "azure/eu/gpt-5.1-chat": { + "cache_read_input_token_cost": 1.4e-7, + "input_cost_per_token": 0.00000138, + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.000011, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text", "image"], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "azure" + }, + "azure/eu/gpt-5.1-codex": { + "cache_read_input_token_cost": 1.4e-7, + "input_cost_per_token": 0.00000138, + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "responses", + "output_cost_per_token": 0.000011, + "supported_endpoints": ["/v1/responses"], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": false, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "azure" + }, + "azure/eu/gpt-5.1-codex-mini": { + "cache_read_input_token_cost": 2.8e-8, + "input_cost_per_token": 2.75e-7, + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "responses", + "output_cost_per_token": 0.0000022, + "supported_endpoints": ["/v1/responses"], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": false, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "azure" + }, + "azure/eu/gpt-5-nano-2025-08-07": { + "cache_read_input_token_cost": 5.5e-9, + "input_cost_per_token": 5.5e-8, + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4.4e-7, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "azure" + }, + "azure/eu/o1-2024-12-17": { + "cache_read_input_token_cost": 0.00000825, + "input_cost_per_token": 0.0000165, + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 0.000066, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "azure" + }, + "azure/eu/o1-mini-2024-09-12": { + "cache_read_input_token_cost": 6.05e-7, + "input_cost_per_token": 0.00000121, + "input_cost_per_token_batches": 6.05e-7, + "max_input_tokens": 128000, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 0.00000484, + "output_cost_per_token_batches": 0.00000242, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_vision": false, + "provider": "azure" + }, + "azure/eu/o1-preview-2024-09-12": { + "cache_read_input_token_cost": 0.00000825, + "input_cost_per_token": 0.0000165, + "max_input_tokens": 128000, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0.000066, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_vision": false, + "provider": "azure" + }, + "azure/eu/o3-mini-2025-01-31": { + "cache_read_input_token_cost": 6.05e-7, + "input_cost_per_token": 0.00000121, + "input_cost_per_token_batches": 6.05e-7, + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 0.00000484, + "output_cost_per_token_batches": 0.00000242, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false, + "provider": "azure" + }, + "azure/global-standard/gpt-4o-2024-08-06": { + "cache_read_input_token_cost": 0.00000125, + "deprecation_date": "2026-02-27", + "input_cost_per_token": 0.0000025, + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 0.00001, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "azure" + }, + "azure/global-standard/gpt-4o-2024-11-20": { + "cache_read_input_token_cost": 0.00000125, + "deprecation_date": "2026-03-01", + "input_cost_per_token": 0.0000025, + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 0.00001, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "azure" + }, + "azure/global-standard/gpt-4o-mini": { + "input_cost_per_token": 1.5e-7, + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 6e-7, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "azure" + }, + "azure/global/gpt-4o-2024-08-06": { + "deprecation_date": "2026-02-27", + "cache_read_input_token_cost": 0.00000125, + "input_cost_per_token": 0.0000025, + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 0.00001, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "azure" + }, + "azure/global/gpt-4o-2024-11-20": { + "deprecation_date": "2026-03-01", + "cache_read_input_token_cost": 0.00000125, + "input_cost_per_token": 0.0000025, + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 0.00001, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "azure" + }, + "azure/global/gpt-5.1": { + "cache_read_input_token_cost": 1.25e-7, + "input_cost_per_token": 0.00000125, + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.00001, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text", "image"], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "azure" + }, + "azure/global/gpt-5.1-chat": { + "cache_read_input_token_cost": 1.25e-7, + "input_cost_per_token": 0.00000125, + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.00001, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text", "image"], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "azure" + }, + "azure/global/gpt-5.1-codex": { + "cache_read_input_token_cost": 1.25e-7, + "input_cost_per_token": 0.00000125, + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "responses", + "output_cost_per_token": 0.00001, + "supported_endpoints": ["/v1/responses"], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": false, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "azure" + }, + "azure/global/gpt-5.1-codex-mini": { + "cache_read_input_token_cost": 2.5e-8, + "input_cost_per_token": 2.5e-7, + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "responses", + "output_cost_per_token": 0.000002, + "supported_endpoints": ["/v1/responses"], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": false, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "azure" + }, + "azure/gpt-3.5-turbo": { + "input_cost_per_token": 5e-7, + "max_input_tokens": 4097, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.0000015, + "supports_function_calling": true, + "supports_tool_choice": true, + "provider": "azure" + }, + "azure/gpt-3.5-turbo-0125": { + "deprecation_date": "2025-03-31", + "input_cost_per_token": 5e-7, + "max_input_tokens": 16384, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.0000015, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "provider": "azure" + }, + "azure/gpt-3.5-turbo-instruct-0914": { + "input_cost_per_token": 0.0000015, + "max_input_tokens": 4097, + "max_tokens": 4097, + "mode": "completion", + "output_cost_per_token": 0.000002, + "provider": "azure_text" + }, + "azure/gpt-35-turbo": { + "input_cost_per_token": 5e-7, + "max_input_tokens": 4097, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.0000015, + "supports_function_calling": true, + "supports_tool_choice": true, + "provider": "azure" + }, + "azure/gpt-35-turbo-0125": { + "deprecation_date": "2025-05-31", + "input_cost_per_token": 5e-7, + "max_input_tokens": 16384, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.0000015, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "provider": "azure" + }, + "azure/gpt-35-turbo-0301": { + "deprecation_date": "2025-02-13", + "input_cost_per_token": 2e-7, + "max_input_tokens": 4097, + "max_output_tokens": 4096, + "max_tokens": 4097, + "mode": "chat", + "output_cost_per_token": 0.000002, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "provider": "azure" + }, + "azure/gpt-35-turbo-0613": { + "deprecation_date": "2025-02-13", + "input_cost_per_token": 0.0000015, + "max_input_tokens": 4097, + "max_output_tokens": 4096, + "max_tokens": 4097, + "mode": "chat", + "output_cost_per_token": 0.000002, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "provider": "azure" + }, + "azure/gpt-35-turbo-1106": { + "deprecation_date": "2025-03-31", + "input_cost_per_token": 0.000001, + "max_input_tokens": 16384, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.000002, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "provider": "azure" + }, + "azure/gpt-35-turbo-16k": { + "input_cost_per_token": 0.000003, + "max_input_tokens": 16385, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.000004, + "supports_tool_choice": true, + "provider": "azure" + }, + "azure/gpt-35-turbo-16k-0613": { + "input_cost_per_token": 0.000003, + "max_input_tokens": 16385, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.000004, + "supports_function_calling": true, + "supports_tool_choice": true, + "provider": "azure" + }, + "azure/gpt-35-turbo-instruct": { + "input_cost_per_token": 0.0000015, + "max_input_tokens": 4097, + "max_tokens": 4097, + "mode": "completion", + "output_cost_per_token": 0.000002, + "provider": "azure_text" + }, + "azure/gpt-35-turbo-instruct-0914": { + "input_cost_per_token": 0.0000015, + "max_input_tokens": 4097, + "max_tokens": 4097, + "mode": "completion", + "output_cost_per_token": 0.000002, + "provider": "azure_text" + }, + "azure/gpt-4": { + "input_cost_per_token": 0.00003, + "max_input_tokens": 8192, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.00006, + "supports_function_calling": true, + "supports_tool_choice": true, + "provider": "azure" + }, + "azure/gpt-4-0125-preview": { + "input_cost_per_token": 0.00001, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.00003, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "provider": "azure" + }, + "azure/gpt-4-0613": { + "input_cost_per_token": 0.00003, + "max_input_tokens": 8192, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.00006, + "supports_function_calling": true, + "supports_tool_choice": true, + "provider": "azure" + }, + "azure/gpt-4-1106-preview": { + "input_cost_per_token": 0.00001, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.00003, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "provider": "azure" + }, + "azure/gpt-4-32k": { + "input_cost_per_token": 0.00006, + "max_input_tokens": 32768, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.00012, + "supports_tool_choice": true, + "provider": "azure" + }, + "azure/gpt-4-32k-0613": { + "input_cost_per_token": 0.00006, + "max_input_tokens": 32768, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.00012, + "supports_tool_choice": true, + "provider": "azure" + }, + "azure/gpt-4-turbo": { + "input_cost_per_token": 0.00001, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.00003, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "provider": "azure" + }, + "azure/gpt-4-turbo-2024-04-09": { + "input_cost_per_token": 0.00001, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.00003, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "azure" + }, + "azure/gpt-4-turbo-vision-preview": { + "input_cost_per_token": 0.00001, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.00003, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "azure" + }, + "azure/gpt-4.1": { + "cache_read_input_token_cost": 5e-7, + "input_cost_per_token": 0.000002, + "input_cost_per_token_batches": 0.000001, + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0.000008, + "output_cost_per_token_batches": 0.000004, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false, + "provider": "azure" + }, + "azure/gpt-4.1-2025-04-14": { + "deprecation_date": "2026-11-04", + "cache_read_input_token_cost": 5e-7, + "input_cost_per_token": 0.000002, + "input_cost_per_token_batches": 0.000001, + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0.000008, + "output_cost_per_token_batches": 0.000004, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false, + "provider": "azure" + }, + "azure/gpt-4.1-mini": { + "cache_read_input_token_cost": 1e-7, + "input_cost_per_token": 4e-7, + "input_cost_per_token_batches": 2e-7, + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0.0000016, + "output_cost_per_token_batches": 8e-7, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false, + "provider": "azure" + }, + "azure/gpt-4.1-mini-2025-04-14": { + "deprecation_date": "2026-11-04", + "cache_read_input_token_cost": 1e-7, + "input_cost_per_token": 4e-7, + "input_cost_per_token_batches": 2e-7, + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0.0000016, + "output_cost_per_token_batches": 8e-7, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false, + "provider": "azure" + }, + "azure/gpt-4.1-nano": { + "cache_read_input_token_cost": 2.5e-8, + "input_cost_per_token": 1e-7, + "input_cost_per_token_batches": 5e-8, + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 4e-7, + "output_cost_per_token_batches": 2e-7, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "azure" + }, + "azure/gpt-4.1-nano-2025-04-14": { + "deprecation_date": "2026-11-04", + "cache_read_input_token_cost": 2.5e-8, + "input_cost_per_token": 1e-7, + "input_cost_per_token_batches": 5e-8, + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 4e-7, + "output_cost_per_token_batches": 2e-7, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "azure" + }, + "azure/gpt-4.5-preview": { + "cache_read_input_token_cost": 0.0000375, + "input_cost_per_token": 0.000075, + "input_cost_per_token_batches": 0.0000375, + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 0.00015, + "output_cost_per_token_batches": 0.000075, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "azure" + }, + "azure/gpt-4o": { + "cache_read_input_token_cost": 0.00000125, + "input_cost_per_token": 0.0000025, + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 0.00001, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "azure" + }, + "azure/gpt-4o-2024-05-13": { + "input_cost_per_token": 0.000005, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.000015, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "azure" + }, + "azure/gpt-4o-2024-08-06": { + "deprecation_date": "2026-02-27", + "cache_read_input_token_cost": 0.00000125, + "input_cost_per_token": 0.0000025, + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 0.00001, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "azure" + }, + "azure/gpt-4o-2024-11-20": { + "deprecation_date": "2026-03-01", + "cache_read_input_token_cost": 0.00000125, + "input_cost_per_token": 0.00000275, + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 0.000011, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "azure" + }, + "azure/gpt-audio-2025-08-28": { + "input_cost_per_audio_token": 0.00004, + "input_cost_per_token": 0.0000025, + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_audio_token": 0.00008, + "output_cost_per_token": 0.00001, + "supported_endpoints": ["/v1/chat/completions"], + "supported_modalities": ["text", "audio"], + "supported_output_modalities": ["text", "audio"], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": false, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false, + "provider": "azure" + }, + "azure/gpt-audio-mini-2025-10-06": { + "input_cost_per_audio_token": 0.00001, + "input_cost_per_token": 6e-7, + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_audio_token": 0.00002, + "output_cost_per_token": 0.0000024, + "supported_endpoints": ["/v1/chat/completions"], + "supported_modalities": ["text", "audio"], + "supported_output_modalities": ["text", "audio"], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": false, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false, + "provider": "azure" + }, + "azure/gpt-4o-audio-preview-2024-12-17": { + "input_cost_per_audio_token": 0.00004, + "input_cost_per_token": 0.0000025, + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_audio_token": 0.00008, + "output_cost_per_token": 0.00001, + "supported_endpoints": ["/v1/chat/completions"], + "supported_modalities": ["text", "audio"], + "supported_output_modalities": ["text", "audio"], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": false, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false, + "provider": "azure" + }, + "azure/gpt-4o-mini": { + "cache_read_input_token_cost": 7.5e-8, + "input_cost_per_token": 1.65e-7, + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 6.6e-7, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "azure" + }, + "azure/gpt-4o-mini-2024-07-18": { + "cache_read_input_token_cost": 7.5e-8, + "input_cost_per_token": 1.65e-7, + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 6.6e-7, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "azure" + }, + "azure/gpt-4o-mini-audio-preview-2024-12-17": { + "input_cost_per_audio_token": 0.00004, + "input_cost_per_token": 0.0000025, + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_audio_token": 0.00008, + "output_cost_per_token": 0.00001, + "supported_endpoints": ["/v1/chat/completions"], + "supported_modalities": ["text", "audio"], + "supported_output_modalities": ["text", "audio"], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": false, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false, + "provider": "azure" + }, + "azure/gpt-4o-mini-realtime-preview-2024-12-17": { + "cache_creation_input_audio_token_cost": 3e-7, + "cache_read_input_token_cost": 3e-7, + "input_cost_per_audio_token": 0.00001, + "input_cost_per_token": 6e-7, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_audio_token": 0.00002, + "output_cost_per_token": 0.0000024, + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "azure" + }, + "azure/gpt-realtime-2025-08-28": { + "cache_creation_input_audio_token_cost": 0.000004, + "cache_read_input_token_cost": 0.000004, + "input_cost_per_audio_token": 0.000032, + "input_cost_per_image": 0.000005, + "input_cost_per_token": 0.000004, + "max_input_tokens": 32000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_audio_token": 0.000064, + "output_cost_per_token": 0.000016, + "supported_endpoints": ["/v1/realtime"], + "supported_modalities": ["text", "image", "audio"], + "supported_output_modalities": ["text", "audio"], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "azure" + }, + "azure/gpt-realtime-mini-2025-10-06": { + "cache_creation_input_audio_token_cost": 3e-7, + "cache_read_input_token_cost": 6e-8, + "input_cost_per_audio_token": 0.00001, + "input_cost_per_image": 8e-7, + "input_cost_per_token": 6e-7, + "max_input_tokens": 32000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_audio_token": 0.00002, + "output_cost_per_token": 0.0000024, + "supported_endpoints": ["/v1/realtime"], + "supported_modalities": ["text", "image", "audio"], + "supported_output_modalities": ["text", "audio"], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "azure" + }, + "azure/gpt-4o-mini-transcribe": { + "input_cost_per_audio_token": 0.000003, + "input_cost_per_token": 0.00000125, + "max_input_tokens": 16000, + "max_output_tokens": 2000, + "mode": "audio_transcription", + "output_cost_per_token": 0.000005, + "supported_endpoints": ["/v1/audio/transcriptions"], + "provider": "azure" + }, + "azure/gpt-4o-mini-tts": { + "input_cost_per_token": 0.0000025, + "mode": "audio_speech", + "output_cost_per_audio_token": 0.000012, + "output_cost_per_second": 0.00025, + "output_cost_per_token": 0.00001, + "supported_endpoints": ["/v1/audio/speech"], + "supported_modalities": ["text", "audio"], + "supported_output_modalities": ["audio"], + "provider": "azure" + }, + "azure/gpt-4o-realtime-preview-2024-10-01": { + "cache_creation_input_audio_token_cost": 0.00002, + "cache_read_input_token_cost": 0.0000025, + "input_cost_per_audio_token": 0.0001, + "input_cost_per_token": 0.000005, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_audio_token": 0.0002, + "output_cost_per_token": 0.00002, + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "azure" + }, + "azure/gpt-4o-realtime-preview-2024-12-17": { + "cache_read_input_token_cost": 0.0000025, + "input_cost_per_audio_token": 0.00004, + "input_cost_per_token": 0.000005, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_audio_token": 0.00008, + "output_cost_per_token": 0.00002, + "supported_modalities": ["text", "audio"], + "supported_output_modalities": ["text", "audio"], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "azure" + }, + "azure/gpt-4o-transcribe": { + "input_cost_per_audio_token": 0.000006, + "input_cost_per_token": 0.0000025, + "max_input_tokens": 16000, + "max_output_tokens": 2000, + "mode": "audio_transcription", + "output_cost_per_token": 0.00001, + "supported_endpoints": ["/v1/audio/transcriptions"], + "provider": "azure" + }, + "azure/gpt-4o-transcribe-diarize": { + "input_cost_per_audio_token": 0.000006, + "input_cost_per_token": 0.0000025, + "max_input_tokens": 16000, + "max_output_tokens": 2000, + "mode": "audio_transcription", + "output_cost_per_token": 0.00001, + "supported_endpoints": ["/v1/audio/transcriptions"], + "provider": "azure" + }, + "azure/gpt-5.1-2025-11-13": { + "cache_read_input_token_cost": 1.25e-7, + "cache_read_input_token_cost_priority": 2.5e-7, + "input_cost_per_token": 0.00000125, + "input_cost_per_token_priority": 0.0000025, + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.00001, + "output_cost_per_token_priority": 0.00002, + "supported_endpoints": ["/v1/chat/completions", "/v1/responses"], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text", "image"], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_service_tier": true, + "supports_vision": true, + "provider": "azure" + }, + "azure/gpt-5.1-chat-2025-11-13": { + "cache_read_input_token_cost": 1.25e-7, + "cache_read_input_token_cost_priority": 2.5e-7, + "input_cost_per_token": 0.00000125, + "input_cost_per_token_priority": 0.0000025, + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 0.00001, + "output_cost_per_token_priority": 0.00002, + "supported_endpoints": ["/v1/chat/completions", "/v1/responses"], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text", "image"], + "supports_function_calling": false, + "supports_native_streaming": true, + "supports_parallel_function_calling": false, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": false, + "supports_vision": true, + "provider": "azure" + }, + "azure/gpt-5.1-codex-2025-11-13": { + "cache_read_input_token_cost": 1.25e-7, + "cache_read_input_token_cost_priority": 2.5e-7, + "input_cost_per_token": 0.00000125, + "input_cost_per_token_priority": 0.0000025, + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "responses", + "output_cost_per_token": 0.00001, + "output_cost_per_token_priority": 0.00002, + "supported_endpoints": ["/v1/responses"], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": false, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "azure" + }, + "azure/gpt-5.1-codex-mini-2025-11-13": { + "cache_read_input_token_cost": 2.5e-8, + "cache_read_input_token_cost_priority": 4.5e-8, + "input_cost_per_token": 2.5e-7, + "input_cost_per_token_priority": 4.5e-7, + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "responses", + "output_cost_per_token": 0.000002, + "output_cost_per_token_priority": 0.0000036, + "supported_endpoints": ["/v1/responses"], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": false, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "azure" + }, + "azure/gpt-5": { + "cache_read_input_token_cost": 1.25e-7, + "input_cost_per_token": 0.00000125, + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.00001, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "azure" + }, + "azure/gpt-5-2025-08-07": { + "cache_read_input_token_cost": 1.25e-7, + "input_cost_per_token": 0.00000125, + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.00001, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "azure" + }, + "azure/gpt-5-chat": { + "cache_read_input_token_cost": 1.25e-7, + "input_cost_per_token": 0.00000125, + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.00001, + "source": "https://azure.microsoft.com/en-us/blog/gpt-5-in-azure-ai-foundry-the-future-of-ai-apps-and-agents-starts-here/", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": false, + "supports_vision": true, + "provider": "azure" + }, + "azure/gpt-5-chat-latest": { + "cache_read_input_token_cost": 1.25e-7, + "input_cost_per_token": 0.00000125, + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 0.00001, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": false, + "supports_vision": true, + "provider": "azure" + }, + "azure/gpt-5-codex": { + "cache_read_input_token_cost": 1.25e-7, + "input_cost_per_token": 0.00000125, + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "responses", + "output_cost_per_token": 0.00001, + "supported_endpoints": ["/v1/responses"], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "azure" + }, + "azure/gpt-5-mini": { + "cache_read_input_token_cost": 2.5e-8, + "input_cost_per_token": 2.5e-7, + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.000002, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "azure" + }, + "azure/gpt-5-mini-2025-08-07": { + "cache_read_input_token_cost": 2.5e-8, + "input_cost_per_token": 2.5e-7, + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.000002, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "azure" + }, + "azure/gpt-5-nano": { + "cache_read_input_token_cost": 5e-9, + "input_cost_per_token": 5e-8, + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4e-7, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "azure" + }, + "azure/gpt-5-nano-2025-08-07": { + "cache_read_input_token_cost": 5e-9, + "input_cost_per_token": 5e-8, + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4e-7, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "azure" + }, + "azure/gpt-5-pro": { + "input_cost_per_token": 0.000015, + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 400000, + "mode": "responses", + "output_cost_per_token": 0.00012, + "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/foundry-models/concepts/models-sold-directly-by-azure?pivots=azure-openai&tabs=global-standard-aoai%2Cstandard-chat-completions%2Cglobal-standard#gpt-5", + "supported_endpoints": ["/v1/responses"], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "azure" + }, + "azure/gpt-5.1": { + "cache_read_input_token_cost": 1.25e-7, + "input_cost_per_token": 0.00000125, + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.00001, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text", "image"], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "azure" + }, + "azure/gpt-5.1-chat": { + "cache_read_input_token_cost": 1.25e-7, + "input_cost_per_token": 0.00000125, + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.00001, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text", "image"], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "azure" + }, + "azure/gpt-5.1-codex": { + "cache_read_input_token_cost": 1.25e-7, + "input_cost_per_token": 0.00000125, + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "responses", + "output_cost_per_token": 0.00001, + "supported_endpoints": ["/v1/responses"], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": false, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "azure" + }, + "azure/gpt-5.1-codex-mini": { + "cache_read_input_token_cost": 2.5e-8, + "input_cost_per_token": 2.5e-7, + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "responses", + "output_cost_per_token": 0.000002, + "supported_endpoints": ["/v1/responses"], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": false, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "azure" + }, + "azure/gpt-image-1": { + "input_cost_per_pixel": 4.0054321e-8, + "mode": "image_generation", + "output_cost_per_pixel": 0, + "supported_endpoints": ["/v1/images/generations"], + "provider": "azure" + }, + "azure/hd/1024-x-1024/dall-e-3": { + "input_cost_per_pixel": 7.629e-8, + "mode": "image_generation", + "output_cost_per_token": 0, + "provider": "azure" + }, + "azure/hd/1024-x-1792/dall-e-3": { + "input_cost_per_pixel": 6.539e-8, + "mode": "image_generation", + "output_cost_per_token": 0, + "provider": "azure" + }, + "azure/hd/1792-x-1024/dall-e-3": { + "input_cost_per_pixel": 6.539e-8, + "mode": "image_generation", + "output_cost_per_token": 0, + "provider": "azure" + }, + "azure/high/1024-x-1024/gpt-image-1": { + "input_cost_per_pixel": 1.59263611e-7, + "mode": "image_generation", + "output_cost_per_pixel": 0, + "supported_endpoints": ["/v1/images/generations"], + "provider": "azure" + }, + "azure/high/1024-x-1536/gpt-image-1": { + "input_cost_per_pixel": 1.58945719e-7, + "mode": "image_generation", + "output_cost_per_pixel": 0, + "supported_endpoints": ["/v1/images/generations"], + "provider": "azure" + }, + "azure/high/1536-x-1024/gpt-image-1": { + "input_cost_per_pixel": 1.58945719e-7, + "mode": "image_generation", + "output_cost_per_pixel": 0, + "supported_endpoints": ["/v1/images/generations"], + "provider": "azure" + }, + "azure/low/1024-x-1024/gpt-image-1": { + "input_cost_per_pixel": 1.0490417e-8, + "mode": "image_generation", + "output_cost_per_pixel": 0, + "supported_endpoints": ["/v1/images/generations"], + "provider": "azure" + }, + "azure/low/1024-x-1536/gpt-image-1": { + "input_cost_per_pixel": 1.0172526e-8, + "mode": "image_generation", + "output_cost_per_pixel": 0, + "supported_endpoints": ["/v1/images/generations"], + "provider": "azure" + }, + "azure/low/1536-x-1024/gpt-image-1": { + "input_cost_per_pixel": 1.0172526e-8, + "mode": "image_generation", + "output_cost_per_pixel": 0, + "supported_endpoints": ["/v1/images/generations"], + "provider": "azure" + }, + "azure/medium/1024-x-1024/gpt-image-1": { + "input_cost_per_pixel": 4.0054321e-8, + "mode": "image_generation", + "output_cost_per_pixel": 0, + "supported_endpoints": ["/v1/images/generations"], + "provider": "azure" + }, + "azure/medium/1024-x-1536/gpt-image-1": { + "input_cost_per_pixel": 4.0054321e-8, + "mode": "image_generation", + "output_cost_per_pixel": 0, + "supported_endpoints": ["/v1/images/generations"], + "provider": "azure" + }, + "azure/medium/1536-x-1024/gpt-image-1": { + "input_cost_per_pixel": 4.0054321e-8, + "mode": "image_generation", + "output_cost_per_pixel": 0, + "supported_endpoints": ["/v1/images/generations"], + "provider": "azure" + }, + "azure/gpt-image-1-mini": { + "input_cost_per_pixel": 8.0566406e-9, + "mode": "image_generation", + "output_cost_per_pixel": 0, + "supported_endpoints": ["/v1/images/generations"], + "provider": "azure" + }, + "azure/low/1024-x-1024/gpt-image-1-mini": { + "input_cost_per_pixel": 2.0751953125e-9, + "mode": "image_generation", + "output_cost_per_pixel": 0, + "supported_endpoints": ["/v1/images/generations"], + "provider": "azure" + }, + "azure/low/1024-x-1536/gpt-image-1-mini": { + "input_cost_per_pixel": 2.0751953125e-9, + "mode": "image_generation", + "output_cost_per_pixel": 0, + "supported_endpoints": ["/v1/images/generations"], + "provider": "azure" + }, + "azure/low/1536-x-1024/gpt-image-1-mini": { + "input_cost_per_pixel": 2.0345052083e-9, + "mode": "image_generation", + "output_cost_per_pixel": 0, + "supported_endpoints": ["/v1/images/generations"], + "provider": "azure" + }, + "azure/medium/1024-x-1024/gpt-image-1-mini": { + "input_cost_per_pixel": 8.056640625e-9, + "mode": "image_generation", + "output_cost_per_pixel": 0, + "supported_endpoints": ["/v1/images/generations"], + "provider": "azure" + }, + "azure/medium/1024-x-1536/gpt-image-1-mini": { + "input_cost_per_pixel": 8.056640625e-9, + "mode": "image_generation", + "output_cost_per_pixel": 0, + "supported_endpoints": ["/v1/images/generations"], + "provider": "azure" + }, + "azure/medium/1536-x-1024/gpt-image-1-mini": { + "input_cost_per_pixel": 7.9752604167e-9, + "mode": "image_generation", + "output_cost_per_pixel": 0, + "supported_endpoints": ["/v1/images/generations"], + "provider": "azure" + }, + "azure/high/1024-x-1024/gpt-image-1-mini": { + "input_cost_per_pixel": 3.173828125e-8, + "mode": "image_generation", + "output_cost_per_pixel": 0, + "supported_endpoints": ["/v1/images/generations"], + "provider": "azure" + }, + "azure/high/1024-x-1536/gpt-image-1-mini": { + "input_cost_per_pixel": 3.173828125e-8, + "mode": "image_generation", + "output_cost_per_pixel": 0, + "supported_endpoints": ["/v1/images/generations"], + "provider": "azure" + }, + "azure/high/1536-x-1024/gpt-image-1-mini": { + "input_cost_per_pixel": 3.1575520833e-8, + "mode": "image_generation", + "output_cost_per_pixel": 0, + "supported_endpoints": ["/v1/images/generations"], + "provider": "azure" + }, + "azure/mistral-large-2402": { + "input_cost_per_token": 0.000008, + "max_input_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 0.000024, + "supports_function_calling": true, + "provider": "azure" + }, + "azure/mistral-large-latest": { + "input_cost_per_token": 0.000008, + "max_input_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 0.000024, + "supports_function_calling": true, + "provider": "azure" + }, + "azure/o1": { + "cache_read_input_token_cost": 0.0000075, + "input_cost_per_token": 0.000015, + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 0.00006, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "azure" + }, + "azure/o1-2024-12-17": { + "cache_read_input_token_cost": 0.0000075, + "input_cost_per_token": 0.000015, + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 0.00006, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "azure" + }, + "azure/o1-mini": { + "cache_read_input_token_cost": 6.05e-7, + "input_cost_per_token": 0.00000121, + "max_input_tokens": 128000, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 0.00000484, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_vision": false, + "provider": "azure" + }, + "azure/o1-mini-2024-09-12": { + "cache_read_input_token_cost": 5.5e-7, + "input_cost_per_token": 0.0000011, + "max_input_tokens": 128000, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 0.0000044, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_vision": false, + "provider": "azure" + }, + "azure/o1-preview": { + "cache_read_input_token_cost": 0.0000075, + "input_cost_per_token": 0.000015, + "max_input_tokens": 128000, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0.00006, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_vision": false, + "provider": "azure" + }, + "azure/o1-preview-2024-09-12": { + "cache_read_input_token_cost": 0.0000075, + "input_cost_per_token": 0.000015, + "max_input_tokens": 128000, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0.00006, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_vision": false, + "provider": "azure" + }, + "azure/o3": { + "cache_read_input_token_cost": 5e-7, + "input_cost_per_token": 0.000002, + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 0.000008, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], + "supports_function_calling": true, + "supports_parallel_function_calling": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "azure" + }, + "azure/o3-2025-04-16": { + "deprecation_date": "2026-04-16", + "cache_read_input_token_cost": 5e-7, + "input_cost_per_token": 0.000002, + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 0.000008, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], + "supports_function_calling": true, + "supports_parallel_function_calling": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "azure" + }, + "azure/o3-deep-research": { + "cache_read_input_token_cost": 0.0000025, + "input_cost_per_token": 0.00001, + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "responses", + "output_cost_per_token": 0.00004, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "provider": "azure" + }, + "azure/o3-mini": { + "cache_read_input_token_cost": 5.5e-7, + "input_cost_per_token": 0.0000011, + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 0.0000044, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "provider": "azure" + }, + "azure/o3-mini-2025-01-31": { + "cache_read_input_token_cost": 5.5e-7, + "input_cost_per_token": 0.0000011, + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 0.0000044, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false, + "provider": "azure" + }, + "azure/o3-pro": { + "input_cost_per_token": 0.00002, + "input_cost_per_token_batches": 0.00001, + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "responses", + "output_cost_per_token": 0.00008, + "output_cost_per_token_batches": 0.00004, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], + "supports_function_calling": true, + "supports_parallel_function_calling": false, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "azure" + }, + "azure/o3-pro-2025-06-10": { + "input_cost_per_token": 0.00002, + "input_cost_per_token_batches": 0.00001, + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "responses", + "output_cost_per_token": 0.00008, + "output_cost_per_token_batches": 0.00004, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], + "supports_function_calling": true, + "supports_parallel_function_calling": false, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "azure" + }, + "azure/o4-mini": { + "cache_read_input_token_cost": 2.75e-7, + "input_cost_per_token": 0.0000011, + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 0.0000044, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], + "supports_function_calling": true, + "supports_parallel_function_calling": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "azure" + }, + "azure/o4-mini-2025-04-16": { + "cache_read_input_token_cost": 2.75e-7, + "input_cost_per_token": 0.0000011, + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 0.0000044, + "supports_function_calling": true, + "supports_parallel_function_calling": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "azure" + }, + "azure/standard/1024-x-1024/dall-e-2": { + "input_cost_per_pixel": 0, + "mode": "image_generation", + "output_cost_per_token": 0, + "provider": "azure" + }, + "azure/standard/1024-x-1024/dall-e-3": { + "input_cost_per_pixel": 3.81469e-8, + "mode": "image_generation", + "output_cost_per_token": 0, + "provider": "azure" + }, + "azure/standard/1024-x-1792/dall-e-3": { + "input_cost_per_pixel": 4.359e-8, + "mode": "image_generation", + "output_cost_per_token": 0, + "provider": "azure" + }, + "azure/standard/1792-x-1024/dall-e-3": { + "input_cost_per_pixel": 4.359e-8, + "mode": "image_generation", + "output_cost_per_token": 0, + "provider": "azure" + }, + "azure/text-embedding-3-large": { + "input_cost_per_token": 1.3e-7, + "max_input_tokens": 8191, + "max_tokens": 8191, + "mode": "embedding", + "output_cost_per_token": 0, + "provider": "azure" + }, + "azure/text-embedding-3-small": { + "deprecation_date": "2026-04-30", + "input_cost_per_token": 2e-8, + "max_input_tokens": 8191, + "max_tokens": 8191, + "mode": "embedding", + "output_cost_per_token": 0, + "provider": "azure" + }, + "azure/text-embedding-ada-002": { + "input_cost_per_token": 1e-7, + "max_input_tokens": 8191, + "max_tokens": 8191, + "mode": "embedding", + "output_cost_per_token": 0, + "provider": "azure" + }, + "azure/speech/azure-tts": { + "input_cost_per_character": 0.000015, + "mode": "audio_speech", + "source": "https://azure.microsoft.com/en-us/pricing/calculator/", + "provider": "azure" + }, + "azure/speech/azure-tts-hd": { + "input_cost_per_character": 0.00003, + "mode": "audio_speech", + "source": "https://azure.microsoft.com/en-us/pricing/calculator/", + "provider": "azure" + }, + "azure/tts-1": { + "input_cost_per_character": 0.000015, + "mode": "audio_speech", + "provider": "azure" + }, + "azure/tts-1-hd": { + "input_cost_per_character": 0.00003, + "mode": "audio_speech", + "provider": "azure" + }, + "azure/us/gpt-4.1-2025-04-14": { + "deprecation_date": "2026-11-04", + "cache_read_input_token_cost": 5.5e-7, + "input_cost_per_token": 0.0000022, + "input_cost_per_token_batches": 0.0000011, + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0.0000088, + "output_cost_per_token_batches": 0.0000044, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false, + "provider": "azure" + }, + "azure/us/gpt-4.1-mini-2025-04-14": { + "deprecation_date": "2026-11-04", + "cache_read_input_token_cost": 1.1e-7, + "input_cost_per_token": 4.4e-7, + "input_cost_per_token_batches": 2.2e-7, + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0.00000176, + "output_cost_per_token_batches": 8.8e-7, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false, + "provider": "azure" + }, + "azure/us/gpt-4.1-nano-2025-04-14": { + "deprecation_date": "2026-11-04", + "cache_read_input_token_cost": 2.5e-8, + "input_cost_per_token": 1.1e-7, + "input_cost_per_token_batches": 6e-8, + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 4.4e-7, + "output_cost_per_token_batches": 2.2e-7, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "azure" + }, + "azure/us/gpt-4o-2024-08-06": { + "deprecation_date": "2026-02-27", + "cache_read_input_token_cost": 0.000001375, + "input_cost_per_token": 0.00000275, + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 0.000011, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "azure" + }, + "azure/us/gpt-4o-2024-11-20": { + "deprecation_date": "2026-03-01", + "cache_creation_input_token_cost": 0.00000138, + "input_cost_per_token": 0.00000275, + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 0.000011, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "azure" + }, + "azure/us/gpt-4o-mini-2024-07-18": { + "cache_read_input_token_cost": 8.3e-8, + "input_cost_per_token": 1.65e-7, + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 6.6e-7, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "azure" + }, + "azure/us/gpt-4o-mini-realtime-preview-2024-12-17": { + "cache_creation_input_audio_token_cost": 3.3e-7, + "cache_read_input_token_cost": 3.3e-7, + "input_cost_per_audio_token": 0.000011, + "input_cost_per_token": 6.6e-7, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_audio_token": 0.000022, + "output_cost_per_token": 0.00000264, + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "azure" + }, + "azure/us/gpt-4o-realtime-preview-2024-10-01": { + "cache_creation_input_audio_token_cost": 0.000022, + "cache_read_input_token_cost": 0.00000275, + "input_cost_per_audio_token": 0.00011, + "input_cost_per_token": 0.0000055, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_audio_token": 0.00022, + "output_cost_per_token": 0.000022, + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "azure" + }, + "azure/us/gpt-4o-realtime-preview-2024-12-17": { + "cache_read_input_audio_token_cost": 0.0000025, + "cache_read_input_token_cost": 0.00000275, + "input_cost_per_audio_token": 0.000044, + "input_cost_per_token": 0.0000055, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_audio_token": 0.00008, + "output_cost_per_token": 0.000022, + "supported_modalities": ["text", "audio"], + "supported_output_modalities": ["text", "audio"], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "azure" + }, + "azure/us/gpt-5-2025-08-07": { + "cache_read_input_token_cost": 1.375e-7, + "input_cost_per_token": 0.000001375, + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.000011, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "azure" + }, + "azure/us/gpt-5-mini-2025-08-07": { + "cache_read_input_token_cost": 2.75e-8, + "input_cost_per_token": 2.75e-7, + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.0000022, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "azure" + }, + "azure/us/gpt-5-nano-2025-08-07": { + "cache_read_input_token_cost": 5.5e-9, + "input_cost_per_token": 5.5e-8, + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4.4e-7, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "azure" + }, + "azure/us/gpt-5.1": { + "cache_read_input_token_cost": 1.4e-7, + "input_cost_per_token": 0.00000138, + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.000011, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text", "image"], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "azure" + }, + "azure/us/gpt-5.1-chat": { + "cache_read_input_token_cost": 1.4e-7, + "input_cost_per_token": 0.00000138, + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.000011, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text", "image"], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "azure" + }, + "azure/us/gpt-5.1-codex": { + "cache_read_input_token_cost": 1.4e-7, + "input_cost_per_token": 0.00000138, + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "responses", + "output_cost_per_token": 0.000011, + "supported_endpoints": ["/v1/responses"], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": false, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "azure" + }, + "azure/us/gpt-5.1-codex-mini": { + "cache_read_input_token_cost": 2.8e-8, + "input_cost_per_token": 2.75e-7, + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "responses", + "output_cost_per_token": 0.0000022, + "supported_endpoints": ["/v1/responses"], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": false, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "azure" + }, + "azure/us/o1-2024-12-17": { + "cache_read_input_token_cost": 0.00000825, + "input_cost_per_token": 0.0000165, + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 0.000066, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "azure" + }, + "azure/us/o1-mini-2024-09-12": { + "cache_read_input_token_cost": 6.05e-7, + "input_cost_per_token": 0.00000121, + "input_cost_per_token_batches": 6.05e-7, + "max_input_tokens": 128000, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 0.00000484, + "output_cost_per_token_batches": 0.00000242, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_vision": false, + "provider": "azure" + }, + "azure/us/o1-preview-2024-09-12": { + "cache_read_input_token_cost": 0.00000825, + "input_cost_per_token": 0.0000165, + "max_input_tokens": 128000, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0.000066, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_vision": false, + "provider": "azure" + }, + "azure/us/o3-2025-04-16": { + "deprecation_date": "2026-04-16", + "cache_read_input_token_cost": 5.5e-7, + "input_cost_per_token": 0.0000022, + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 0.0000088, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], + "supports_function_calling": true, + "supports_parallel_function_calling": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "azure" + }, + "azure/us/o3-mini-2025-01-31": { + "cache_read_input_token_cost": 6.05e-7, + "input_cost_per_token": 0.00000121, + "input_cost_per_token_batches": 6.05e-7, + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 0.00000484, + "output_cost_per_token_batches": 0.00000242, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false, + "provider": "azure" + }, + "azure/us/o4-mini-2025-04-16": { + "cache_read_input_token_cost": 3.1e-7, + "input_cost_per_token": 0.00000121, + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 0.00000484, + "supports_function_calling": true, + "supports_parallel_function_calling": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "azure" + }, + "azure/whisper-1": { + "input_cost_per_second": 0.0001, + "mode": "audio_transcription", + "output_cost_per_second": 0.0001, + "provider": "azure" + }, + "azure_ai/Cohere-embed-v3-english": { + "input_cost_per_token": 1e-7, + "max_input_tokens": 512, + "max_tokens": 512, + "mode": "embedding", + "output_cost_per_token": 0, + "output_vector_size": 1024, + "source": "https://azuremarketplace.microsoft.com/en-us/marketplace/apps/cohere.cohere-embed-v3-english-offer?tab=PlansAndPrice", + "supports_embedding_image_input": true, + "provider": "azure_ai" + }, + "azure_ai/Cohere-embed-v3-multilingual": { + "input_cost_per_token": 1e-7, + "max_input_tokens": 512, + "max_tokens": 512, + "mode": "embedding", + "output_cost_per_token": 0, + "output_vector_size": 1024, + "source": "https://azuremarketplace.microsoft.com/en-us/marketplace/apps/cohere.cohere-embed-v3-english-offer?tab=PlansAndPrice", + "supports_embedding_image_input": true, + "provider": "azure_ai" + }, + "azure_ai/FLUX-1.1-pro": { + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/black-forest-labs-flux-1-kontext-pro-and-flux1-1-pro-now-available-in-azure-ai-f/4434659", + "supported_endpoints": ["/v1/images/generations"], + "provider": "azure_ai" + }, + "azure_ai/FLUX.1-Kontext-pro": { + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://azuremarketplace.microsoft.com/pt-br/marketplace/apps/cohere.cohere-embed-4-offer?tab=PlansAndPrice", + "supported_endpoints": ["/v1/images/generations"], + "provider": "azure_ai" + }, + "azure_ai/Llama-3.2-11B-Vision-Instruct": { + "input_cost_per_token": 3.7e-7, + "max_input_tokens": 128000, + "max_output_tokens": 2048, + "max_tokens": 2048, + "mode": "chat", + "output_cost_per_token": 3.7e-7, + "source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/metagenai.meta-llama-3-2-11b-vision-instruct-offer?tab=Overview", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "azure_ai" + }, + "azure_ai/Llama-3.2-90B-Vision-Instruct": { + "input_cost_per_token": 0.00000204, + "max_input_tokens": 128000, + "max_output_tokens": 2048, + "max_tokens": 2048, + "mode": "chat", + "output_cost_per_token": 0.00000204, + "source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/metagenai.meta-llama-3-2-90b-vision-instruct-offer?tab=Overview", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "azure_ai" + }, + "azure_ai/Llama-3.3-70B-Instruct": { + "input_cost_per_token": 7.1e-7, + "max_input_tokens": 128000, + "max_output_tokens": 2048, + "max_tokens": 2048, + "mode": "chat", + "output_cost_per_token": 7.1e-7, + "source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/metagenai.llama-3-3-70b-instruct-offer?tab=Overview", + "supports_function_calling": true, + "supports_tool_choice": true, + "provider": "azure_ai" + }, + "azure_ai/Llama-4-Maverick-17B-128E-Instruct-FP8": { + "input_cost_per_token": 0.00000141, + "max_input_tokens": 1000000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 3.5e-7, + "source": "https://azure.microsoft.com/en-us/blog/introducing-the-llama-4-herd-in-azure-ai-foundry-and-azure-databricks/", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "azure_ai" + }, + "azure_ai/Llama-4-Scout-17B-16E-Instruct": { + "input_cost_per_token": 2e-7, + "max_input_tokens": 10000000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 7.8e-7, + "source": "https://azure.microsoft.com/en-us/blog/introducing-the-llama-4-herd-in-azure-ai-foundry-and-azure-databricks/", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "azure_ai" + }, + "azure_ai/Meta-Llama-3-70B-Instruct": { + "input_cost_per_token": 0.0000011, + "max_input_tokens": 8192, + "max_output_tokens": 2048, + "max_tokens": 2048, + "mode": "chat", + "output_cost_per_token": 3.7e-7, + "supports_tool_choice": true, + "provider": "azure_ai" + }, + "azure_ai/Meta-Llama-3.1-405B-Instruct": { + "input_cost_per_token": 0.00000533, + "max_input_tokens": 128000, + "max_output_tokens": 2048, + "max_tokens": 2048, + "mode": "chat", + "output_cost_per_token": 0.000016, + "source": "https://azuremarketplace.microsoft.com/en-us/marketplace/apps/metagenai.meta-llama-3-1-405b-instruct-offer?tab=PlansAndPrice", + "supports_tool_choice": true, + "provider": "azure_ai" + }, + "azure_ai/Meta-Llama-3.1-70B-Instruct": { + "input_cost_per_token": 0.00000268, + "max_input_tokens": 128000, + "max_output_tokens": 2048, + "max_tokens": 2048, + "mode": "chat", + "output_cost_per_token": 0.00000354, + "source": "https://azuremarketplace.microsoft.com/en-us/marketplace/apps/metagenai.meta-llama-3-1-70b-instruct-offer?tab=PlansAndPrice", + "supports_tool_choice": true, + "provider": "azure_ai" + }, + "azure_ai/Meta-Llama-3.1-8B-Instruct": { + "input_cost_per_token": 3e-7, + "max_input_tokens": 128000, + "max_output_tokens": 2048, + "max_tokens": 2048, + "mode": "chat", + "output_cost_per_token": 6.1e-7, + "source": "https://azuremarketplace.microsoft.com/en-us/marketplace/apps/metagenai.meta-llama-3-1-8b-instruct-offer?tab=PlansAndPrice", + "supports_tool_choice": true, + "provider": "azure_ai" + }, + "azure_ai/Phi-3-medium-128k-instruct": { + "input_cost_per_token": 1.7e-7, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 6.8e-7, + "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "supports_tool_choice": true, + "supports_vision": false, + "provider": "azure_ai" + }, + "azure_ai/Phi-3-medium-4k-instruct": { + "input_cost_per_token": 1.7e-7, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 6.8e-7, + "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "supports_tool_choice": true, + "supports_vision": false, + "provider": "azure_ai" + }, + "azure_ai/Phi-3-mini-128k-instruct": { + "input_cost_per_token": 1.3e-7, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 5.2e-7, + "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "supports_tool_choice": true, + "supports_vision": false, + "provider": "azure_ai" + }, + "azure_ai/Phi-3-mini-4k-instruct": { + "input_cost_per_token": 1.3e-7, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 5.2e-7, + "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "supports_tool_choice": true, + "supports_vision": false, + "provider": "azure_ai" + }, + "azure_ai/Phi-3-small-128k-instruct": { + "input_cost_per_token": 1.5e-7, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 6e-7, + "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "supports_tool_choice": true, + "supports_vision": false, + "provider": "azure_ai" + }, + "azure_ai/Phi-3-small-8k-instruct": { + "input_cost_per_token": 1.5e-7, + "max_input_tokens": 8192, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 6e-7, + "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "supports_tool_choice": true, + "supports_vision": false, + "provider": "azure_ai" + }, + "azure_ai/Phi-3.5-MoE-instruct": { + "input_cost_per_token": 1.6e-7, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 6.4e-7, + "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "supports_tool_choice": true, + "supports_vision": false, + "provider": "azure_ai" + }, + "azure_ai/Phi-3.5-mini-instruct": { + "input_cost_per_token": 1.3e-7, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 5.2e-7, + "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "supports_tool_choice": true, + "supports_vision": false, + "provider": "azure_ai" + }, + "azure_ai/Phi-3.5-vision-instruct": { + "input_cost_per_token": 1.3e-7, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 5.2e-7, + "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "supports_tool_choice": true, + "supports_vision": true, + "provider": "azure_ai" + }, + "azure_ai/Phi-4": { + "input_cost_per_token": 1.25e-7, + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 5e-7, + "source": "https://techcommunity.microsoft.com/blog/machinelearningblog/affordable-innovation-unveiling-the-pricing-of-phi-3-slms-on-models-as-a-service/4156495", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": false, + "provider": "azure_ai" + }, + "azure_ai/Phi-4-mini-instruct": { + "input_cost_per_token": 7.5e-8, + "max_input_tokens": 131072, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 3e-7, + "source": "https://techcommunity.microsoft.com/blog/Azure-AI-Services-blog/announcing-new-phi-pricing-empowering-your-business-with-small-language-models/4395112", + "supports_function_calling": true, + "provider": "azure_ai" + }, + "azure_ai/Phi-4-multimodal-instruct": { + "input_cost_per_audio_token": 0.000004, + "input_cost_per_token": 8e-8, + "max_input_tokens": 131072, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 3.2e-7, + "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, + "supports_function_calling": true, + "supports_vision": true, + "provider": "azure_ai" + }, + "azure_ai/Phi-4-mini-reasoning": { + "input_cost_per_token": 8e-8, + "max_input_tokens": 131072, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 3.2e-7, + "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/microsoft/", + "supports_function_calling": true, + "provider": "azure_ai" + }, + "azure_ai/Phi-4-reasoning": { + "input_cost_per_token": 1.25e-7, + "max_input_tokens": 32768, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 5e-7, + "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/microsoft/", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "provider": "azure_ai" + }, + "azure_ai/mistral-document-ai-2505": { + "ocr_cost_per_page": 0.003, + "mode": "ocr", + "supported_endpoints": ["/v1/ocr"], + "source": "https://devblogs.microsoft.com/foundry/whats-new-in-azure-ai-foundry-august-2025/#mistral-document-ai-(ocr)-%E2%80%94-serverless-in-foundry", + "provider": "azure_ai" + }, + "azure_ai/doc-intelligence/prebuilt-read": { + "ocr_cost_per_page": 0.0015, + "mode": "ocr", + "supported_endpoints": ["/v1/ocr"], + "source": "https://azure.microsoft.com/en-us/pricing/details/ai-document-intelligence/", + "provider": "azure_ai" + }, + "azure_ai/doc-intelligence/prebuilt-layout": { + "ocr_cost_per_page": 0.01, + "mode": "ocr", + "supported_endpoints": ["/v1/ocr"], + "source": "https://azure.microsoft.com/en-us/pricing/details/ai-document-intelligence/", + "provider": "azure_ai" + }, + "azure_ai/doc-intelligence/prebuilt-document": { + "ocr_cost_per_page": 0.01, + "mode": "ocr", + "supported_endpoints": ["/v1/ocr"], + "source": "https://azure.microsoft.com/en-us/pricing/details/ai-document-intelligence/", + "provider": "azure_ai" + }, + "azure_ai/MAI-DS-R1": { + "input_cost_per_token": 0.00000135, + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.0000054, + "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/microsoft/", + "supports_reasoning": true, + "supports_tool_choice": true, + "provider": "azure_ai" + }, + "azure_ai/cohere-rerank-v3-english": { + "input_cost_per_query": 0.002, + "input_cost_per_token": 0, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_query_tokens": 2048, + "max_tokens": 4096, + "mode": "rerank", + "output_cost_per_token": 0, + "provider": "azure_ai" + }, + "azure_ai/cohere-rerank-v3-multilingual": { + "input_cost_per_query": 0.002, + "input_cost_per_token": 0, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_query_tokens": 2048, + "max_tokens": 4096, + "mode": "rerank", + "output_cost_per_token": 0, + "provider": "azure_ai" + }, + "azure_ai/cohere-rerank-v3.5": { + "input_cost_per_query": 0.002, + "input_cost_per_token": 0, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_query_tokens": 2048, + "max_tokens": 4096, + "mode": "rerank", + "output_cost_per_token": 0, + "provider": "azure_ai" + }, + "azure_ai/deepseek-r1": { + "input_cost_per_token": 0.00000135, + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.0000054, + "source": "https://techcommunity.microsoft.com/blog/machinelearningblog/deepseek-r1-improved-performance-higher-limits-and-transparent-pricing/4386367", + "supports_reasoning": true, + "supports_tool_choice": true, + "provider": "azure_ai" + }, + "azure_ai/deepseek-v3": { + "input_cost_per_token": 0.00000114, + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.00000456, + "source": "https://techcommunity.microsoft.com/blog/machinelearningblog/announcing-deepseek-v3-on-azure-ai-foundry-and-github/4390438", + "supports_tool_choice": true, + "provider": "azure_ai" + }, + "azure_ai/deepseek-v3-0324": { + "input_cost_per_token": 0.00000114, + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.00000456, + "source": "https://techcommunity.microsoft.com/blog/machinelearningblog/announcing-deepseek-v3-on-azure-ai-foundry-and-github/4390438", + "supports_function_calling": true, + "supports_tool_choice": true, + "provider": "azure_ai" + }, + "azure_ai/embed-v-4-0": { + "input_cost_per_token": 1.2e-7, + "max_input_tokens": 128000, + "max_tokens": 128000, + "mode": "embedding", + "output_cost_per_token": 0, + "output_vector_size": 3072, + "source": "https://azuremarketplace.microsoft.com/pt-br/marketplace/apps/cohere.cohere-embed-4-offer?tab=PlansAndPrice", + "supported_endpoints": ["/v1/embeddings"], + "supported_modalities": ["text", "image"], + "supports_embedding_image_input": true, + "provider": "azure_ai" + }, + "azure_ai/global/grok-3": { + "input_cost_per_token": 0.000003, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 0.000015, + "source": "https://devblogs.microsoft.com/foundry/announcing-grok-3-and-grok-3-mini-on-azure-ai-foundry/", + "supports_function_calling": true, + "supports_response_schema": false, + "supports_tool_choice": true, + "supports_web_search": true, + "provider": "azure_ai" + }, + "azure_ai/global/grok-3-mini": { + "input_cost_per_token": 2.5e-7, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 0.00000127, + "source": "https://devblogs.microsoft.com/foundry/announcing-grok-3-and-grok-3-mini-on-azure-ai-foundry/", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_tool_choice": true, + "supports_web_search": true, + "provider": "azure_ai" + }, + "azure_ai/grok-3": { + "input_cost_per_token": 0.0000033, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 0.0000165, + "source": "https://devblogs.microsoft.com/foundry/announcing-grok-3-and-grok-3-mini-on-azure-ai-foundry/", + "supports_function_calling": true, + "supports_response_schema": false, + "supports_tool_choice": true, + "supports_web_search": true, + "provider": "azure_ai" + }, + "azure_ai/grok-3-mini": { + "input_cost_per_token": 2.75e-7, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 0.00000138, + "source": "https://devblogs.microsoft.com/foundry/announcing-grok-3-and-grok-3-mini-on-azure-ai-foundry/", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_tool_choice": true, + "supports_web_search": true, + "provider": "azure_ai" + }, + "azure_ai/grok-4": { + "input_cost_per_token": 0.0000055, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 0.0000275, + "source": "https://azure.microsoft.com/en-us/blog/grok-4-is-now-available-in-azure-ai-foundry-unlock-frontier-intelligence-and-business-ready-capabilities/", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_web_search": true, + "provider": "azure_ai" + }, + "azure_ai/grok-4-fast-non-reasoning": { + "input_cost_per_token": 4.3e-7, + "output_cost_per_token": 0.00000173, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_web_search": true, + "provider": "azure_ai" + }, + "azure_ai/grok-4-fast-reasoning": { + "input_cost_per_token": 4.3e-7, + "output_cost_per_token": 0.00000173, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/announcing-the-grok-4-fast-models-from-xai-now-available-in-azure-ai-foundry/4456701", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_web_search": true, + "provider": "azure_ai" + }, + "azure_ai/grok-code-fast-1": { + "input_cost_per_token": 0.0000035, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 0.0000175, + "source": "https://azure.microsoft.com/en-us/blog/grok-4-is-now-available-in-azure-ai-foundry-unlock-frontier-intelligence-and-business-ready-capabilities/", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_web_search": true, + "provider": "azure_ai" + }, + "azure_ai/jais-30b-chat": { + "input_cost_per_token": 0.0032, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.00971, + "source": "https://azure.microsoft.com/en-us/products/ai-services/ai-foundry/models/jais-30b-chat", + "provider": "azure_ai" + }, + "azure_ai/jamba-instruct": { + "input_cost_per_token": 5e-7, + "max_input_tokens": 70000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 7e-7, + "supports_tool_choice": true, + "provider": "azure_ai" + }, + "azure_ai/ministral-3b": { + "input_cost_per_token": 4e-8, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 4e-8, + "source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/000-000.ministral-3b-2410-offer?tab=Overview", + "supports_function_calling": true, + "supports_tool_choice": true, + "provider": "azure_ai" + }, + "azure_ai/mistral-large": { + "input_cost_per_token": 0.000004, + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 0.000012, + "supports_function_calling": true, + "supports_tool_choice": true, + "provider": "azure_ai" + }, + "azure_ai/mistral-large-2407": { + "input_cost_per_token": 0.000002, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.000006, + "source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/000-000.mistral-ai-large-2407-offer?tab=Overview", + "supports_function_calling": true, + "supports_tool_choice": true, + "provider": "azure_ai" + }, + "azure_ai/mistral-large-latest": { + "input_cost_per_token": 0.000002, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.000006, + "source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/000-000.mistral-ai-large-2407-offer?tab=Overview", + "supports_function_calling": true, + "supports_tool_choice": true, + "provider": "azure_ai" + }, + "azure_ai/mistral-medium-2505": { + "input_cost_per_token": 4e-7, + "max_input_tokens": 131072, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 0.000002, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "provider": "azure_ai" + }, + "azure_ai/mistral-nemo": { + "input_cost_per_token": 1.5e-7, + "max_input_tokens": 131072, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.5e-7, + "source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/000-000.mistral-nemo-12b-2407?tab=PlansAndPrice", + "supports_function_calling": true, + "provider": "azure_ai" + }, + "azure_ai/mistral-small": { + "input_cost_per_token": 0.000001, + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 0.000003, + "supports_function_calling": true, + "supports_tool_choice": true, + "provider": "azure_ai" + }, + "azure_ai/mistral-small-2503": { + "input_cost_per_token": 0.000001, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.000003, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "azure_ai" + }, + "babbage-002": { + "input_cost_per_token": 4e-7, + "max_input_tokens": 16384, + "max_output_tokens": 4096, + "max_tokens": 16384, + "mode": "completion", + "output_cost_per_token": 4e-7, + "provider": "text-completion-openai" + }, + "bedrock/*/1-month-commitment/cohere.command-light-text-v14": { + "input_cost_per_second": 0.001902, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_second": 0.001902, + "supports_tool_choice": true, + "provider": "bedrock" + }, + "bedrock/*/1-month-commitment/cohere.command-text-v14": { + "input_cost_per_second": 0.011, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_second": 0.011, + "supports_tool_choice": true, + "provider": "bedrock" + }, + "bedrock/*/6-month-commitment/cohere.command-light-text-v14": { + "input_cost_per_second": 0.0011416, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_second": 0.0011416, + "supports_tool_choice": true, + "provider": "bedrock" + }, + "bedrock/*/6-month-commitment/cohere.command-text-v14": { + "input_cost_per_second": 0.0066027, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_second": 0.0066027, + "supports_tool_choice": true, + "provider": "bedrock" + }, + "bedrock/ap-northeast-1/1-month-commitment/anthropic.claude-instant-v1": { + "input_cost_per_second": 0.01475, + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.01475, + "supports_tool_choice": true, + "provider": "bedrock" + }, + "bedrock/ap-northeast-1/1-month-commitment/anthropic.claude-v1": { + "input_cost_per_second": 0.0455, + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.0455, + "provider": "bedrock" + }, + "bedrock/ap-northeast-1/1-month-commitment/anthropic.claude-v2:1": { + "input_cost_per_second": 0.0455, + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.0455, + "supports_tool_choice": true, + "provider": "bedrock" + }, + "bedrock/ap-northeast-1/6-month-commitment/anthropic.claude-instant-v1": { + "input_cost_per_second": 0.008194, + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.008194, + "supports_tool_choice": true, + "provider": "bedrock" + }, + "bedrock/ap-northeast-1/6-month-commitment/anthropic.claude-v1": { + "input_cost_per_second": 0.02527, + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.02527, + "provider": "bedrock" + }, + "bedrock/ap-northeast-1/6-month-commitment/anthropic.claude-v2:1": { + "input_cost_per_second": 0.02527, + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.02527, + "supports_tool_choice": true, + "provider": "bedrock" + }, + "bedrock/ap-northeast-1/anthropic.claude-instant-v1": { + "input_cost_per_token": 0.00000223, + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 0.00000755, + "supports_tool_choice": true, + "provider": "bedrock" + }, + "bedrock/ap-northeast-1/anthropic.claude-v1": { + "input_cost_per_token": 0.000008, + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 0.000024, + "supports_tool_choice": true, + "provider": "bedrock" + }, + "bedrock/ap-northeast-1/anthropic.claude-v2:1": { + "input_cost_per_token": 0.000008, + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 0.000024, + "supports_tool_choice": true, + "provider": "bedrock" + }, + "bedrock/ap-south-1/meta.llama3-70b-instruct-v1:0": { + "input_cost_per_token": 0.00000318, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.0000042, + "provider": "bedrock" + }, + "bedrock/ap-south-1/meta.llama3-8b-instruct-v1:0": { + "input_cost_per_token": 3.6e-7, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 7.2e-7, + "provider": "bedrock" + }, + "bedrock/ca-central-1/meta.llama3-70b-instruct-v1:0": { + "input_cost_per_token": 0.00000305, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.00000403, + "provider": "bedrock" + }, + "bedrock/ca-central-1/meta.llama3-8b-instruct-v1:0": { + "input_cost_per_token": 3.5e-7, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 6.9e-7, + "provider": "bedrock" + }, + "bedrock/eu-central-1/1-month-commitment/anthropic.claude-instant-v1": { + "input_cost_per_second": 0.01635, + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.01635, + "supports_tool_choice": true, + "provider": "bedrock" + }, + "bedrock/eu-central-1/1-month-commitment/anthropic.claude-v1": { + "input_cost_per_second": 0.0415, + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.0415, + "provider": "bedrock" + }, + "bedrock/eu-central-1/1-month-commitment/anthropic.claude-v2:1": { + "input_cost_per_second": 0.0415, + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.0415, + "supports_tool_choice": true, + "provider": "bedrock" + }, + "bedrock/eu-central-1/6-month-commitment/anthropic.claude-instant-v1": { + "input_cost_per_second": 0.009083, + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.009083, + "supports_tool_choice": true, + "provider": "bedrock" + }, + "bedrock/eu-central-1/6-month-commitment/anthropic.claude-v1": { + "input_cost_per_second": 0.02305, + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.02305, + "provider": "bedrock" + }, + "bedrock/eu-central-1/6-month-commitment/anthropic.claude-v2:1": { + "input_cost_per_second": 0.02305, + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.02305, + "supports_tool_choice": true, + "provider": "bedrock" + }, + "bedrock/eu-central-1/anthropic.claude-instant-v1": { + "input_cost_per_token": 0.00000248, + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 0.00000838, + "supports_tool_choice": true, + "provider": "bedrock" + }, + "bedrock/eu-central-1/anthropic.claude-v1": { + "input_cost_per_token": 0.000008, + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 0.000024, + "provider": "bedrock" + }, + "bedrock/eu-central-1/anthropic.claude-v2:1": { + "input_cost_per_token": 0.000008, + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 0.000024, + "supports_tool_choice": true, + "provider": "bedrock" + }, + "bedrock/eu-west-1/meta.llama3-70b-instruct-v1:0": { + "input_cost_per_token": 0.00000286, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.00000378, + "provider": "bedrock" + }, + "bedrock/eu-west-1/meta.llama3-8b-instruct-v1:0": { + "input_cost_per_token": 3.2e-7, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 6.5e-7, + "provider": "bedrock" + }, + "bedrock/eu-west-2/meta.llama3-70b-instruct-v1:0": { + "input_cost_per_token": 0.00000345, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.00000455, + "provider": "bedrock" + }, + "bedrock/eu-west-2/meta.llama3-8b-instruct-v1:0": { + "input_cost_per_token": 3.9e-7, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 7.8e-7, + "provider": "bedrock" + }, + "bedrock/eu-west-3/mistral.mistral-7b-instruct-v0:2": { + "input_cost_per_token": 2e-7, + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 2.6e-7, + "supports_tool_choice": true, + "provider": "bedrock" + }, + "bedrock/eu-west-3/mistral.mistral-large-2402-v1:0": { + "input_cost_per_token": 0.0000104, + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 0.0000312, + "supports_function_calling": true, + "provider": "bedrock" + }, + "bedrock/eu-west-3/mistral.mixtral-8x7b-instruct-v0:1": { + "input_cost_per_token": 5.9e-7, + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 9.1e-7, + "supports_tool_choice": true, + "provider": "bedrock" + }, + "bedrock/invoke/anthropic.claude-3-5-sonnet-20240620-v1:0": { + "input_cost_per_token": 0.000003, + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "metadata": { + "notes": "Anthropic via Invoke route does not currently support pdf input." + }, + "mode": "chat", + "output_cost_per_token": 0.000015, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "bedrock" + }, + "bedrock/sa-east-1/meta.llama3-70b-instruct-v1:0": { + "input_cost_per_token": 0.00000445, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.00000588, + "provider": "bedrock" + }, + "bedrock/sa-east-1/meta.llama3-8b-instruct-v1:0": { + "input_cost_per_token": 5e-7, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.00000101, + "provider": "bedrock" + }, + "bedrock/us-east-1/1-month-commitment/anthropic.claude-instant-v1": { + "input_cost_per_second": 0.011, + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.011, + "supports_tool_choice": true, + "provider": "bedrock" + }, + "bedrock/us-east-1/1-month-commitment/anthropic.claude-v1": { + "input_cost_per_second": 0.0175, + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.0175, + "provider": "bedrock" + }, + "bedrock/us-east-1/1-month-commitment/anthropic.claude-v2:1": { + "input_cost_per_second": 0.0175, + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.0175, + "supports_tool_choice": true, + "provider": "bedrock" + }, + "bedrock/us-east-1/6-month-commitment/anthropic.claude-instant-v1": { + "input_cost_per_second": 0.00611, + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.00611, + "supports_tool_choice": true, + "provider": "bedrock" + }, + "bedrock/us-east-1/6-month-commitment/anthropic.claude-v1": { + "input_cost_per_second": 0.00972, + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.00972, + "provider": "bedrock" + }, + "bedrock/us-east-1/6-month-commitment/anthropic.claude-v2:1": { + "input_cost_per_second": 0.00972, + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.00972, + "supports_tool_choice": true, + "provider": "bedrock" + }, + "bedrock/us-east-1/anthropic.claude-instant-v1": { + "input_cost_per_token": 8e-7, + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 0.0000024, + "supports_tool_choice": true, + "provider": "bedrock" + }, + "bedrock/us-east-1/anthropic.claude-v1": { + "input_cost_per_token": 0.000008, + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 0.000024, + "supports_tool_choice": true, + "provider": "bedrock" + }, + "bedrock/us-east-1/anthropic.claude-v2:1": { + "input_cost_per_token": 0.000008, + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 0.000024, + "supports_tool_choice": true, + "provider": "bedrock" + }, + "bedrock/us-east-1/meta.llama3-70b-instruct-v1:0": { + "input_cost_per_token": 0.00000265, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.0000035, + "provider": "bedrock" + }, + "bedrock/us-east-1/meta.llama3-8b-instruct-v1:0": { + "input_cost_per_token": 3e-7, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 6e-7, + "provider": "bedrock" + }, + "bedrock/us-east-1/mistral.mistral-7b-instruct-v0:2": { + "input_cost_per_token": 1.5e-7, + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 2e-7, + "supports_tool_choice": true, + "provider": "bedrock" + }, + "bedrock/us-east-1/mistral.mistral-large-2402-v1:0": { + "input_cost_per_token": 0.000008, + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 0.000024, + "supports_function_calling": true, + "provider": "bedrock" + }, + "bedrock/us-east-1/mistral.mixtral-8x7b-instruct-v0:1": { + "input_cost_per_token": 4.5e-7, + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 7e-7, + "supports_tool_choice": true, + "provider": "bedrock" + }, + "bedrock/us-gov-east-1/amazon.nova-pro-v1:0": { + "input_cost_per_token": 9.6e-7, + "max_input_tokens": 300000, + "max_output_tokens": 10000, + "max_tokens": 10000, + "mode": "chat", + "output_cost_per_token": 0.00000384, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_vision": true, + "provider": "bedrock" + }, + "bedrock/us-gov-east-1/amazon.titan-embed-text-v1": { + "input_cost_per_token": 1e-7, + "max_input_tokens": 8192, + "max_tokens": 8192, + "mode": "embedding", + "output_cost_per_token": 0, + "output_vector_size": 1536, + "provider": "bedrock" + }, + "bedrock/us-gov-east-1/amazon.titan-embed-text-v2:0": { + "input_cost_per_token": 2e-7, + "max_input_tokens": 8192, + "max_tokens": 8192, + "mode": "embedding", + "output_cost_per_token": 0, + "output_vector_size": 1024, + "provider": "bedrock" + }, + "bedrock/us-gov-east-1/amazon.titan-text-express-v1": { + "input_cost_per_token": 0.0000013, + "max_input_tokens": 42000, + "max_output_tokens": 8000, + "max_tokens": 8000, + "mode": "chat", + "output_cost_per_token": 0.0000017, + "provider": "bedrock" + }, + "bedrock/us-gov-east-1/amazon.titan-text-lite-v1": { + "input_cost_per_token": 3e-7, + "max_input_tokens": 42000, + "max_output_tokens": 4000, + "max_tokens": 4000, + "mode": "chat", + "output_cost_per_token": 4e-7, + "provider": "bedrock" + }, + "bedrock/us-gov-east-1/amazon.titan-text-premier-v1:0": { + "input_cost_per_token": 5e-7, + "max_input_tokens": 42000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 0.0000015, + "provider": "bedrock" + }, + "bedrock/us-gov-east-1/anthropic.claude-3-5-sonnet-20240620-v1:0": { + "input_cost_per_token": 0.0000036, + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.000018, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "bedrock" + }, + "bedrock/us-gov-east-1/anthropic.claude-3-haiku-20240307-v1:0": { + "input_cost_per_token": 3e-7, + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.0000015, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "bedrock" + }, + "bedrock/us-gov-east-1/claude-sonnet-4-5-20250929-v1:0": { + "input_cost_per_token": 0.0000033, + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.0000165, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "bedrock" + }, + "bedrock/us-gov-east-1/meta.llama3-70b-instruct-v1:0": { + "input_cost_per_token": 0.00000265, + "max_input_tokens": 8000, + "max_output_tokens": 2048, + "max_tokens": 2048, + "mode": "chat", + "output_cost_per_token": 0.0000035, + "supports_pdf_input": true, + "provider": "bedrock" + }, + "bedrock/us-gov-east-1/meta.llama3-8b-instruct-v1:0": { + "input_cost_per_token": 3e-7, + "max_input_tokens": 8000, + "max_output_tokens": 2048, + "max_tokens": 2048, + "mode": "chat", + "output_cost_per_token": 0.00000265, + "supports_pdf_input": true, + "provider": "bedrock" + }, + "bedrock/us-gov-west-1/amazon.nova-pro-v1:0": { + "input_cost_per_token": 9.6e-7, + "max_input_tokens": 300000, + "max_output_tokens": 10000, + "max_tokens": 10000, + "mode": "chat", + "output_cost_per_token": 0.00000384, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_vision": true, + "provider": "bedrock" + }, + "bedrock/us-gov-west-1/amazon.titan-embed-text-v1": { + "input_cost_per_token": 1e-7, + "max_input_tokens": 8192, + "max_tokens": 8192, + "mode": "embedding", + "output_cost_per_token": 0, + "output_vector_size": 1536, + "provider": "bedrock" + }, + "bedrock/us-gov-west-1/amazon.titan-embed-text-v2:0": { + "input_cost_per_token": 2e-7, + "max_input_tokens": 8192, + "max_tokens": 8192, + "mode": "embedding", + "output_cost_per_token": 0, + "output_vector_size": 1024, + "provider": "bedrock" + }, + "bedrock/us-gov-west-1/amazon.titan-text-express-v1": { + "input_cost_per_token": 0.0000013, + "max_input_tokens": 42000, + "max_output_tokens": 8000, + "max_tokens": 8000, + "mode": "chat", + "output_cost_per_token": 0.0000017, + "provider": "bedrock" + }, + "bedrock/us-gov-west-1/amazon.titan-text-lite-v1": { + "input_cost_per_token": 3e-7, + "max_input_tokens": 42000, + "max_output_tokens": 4000, + "max_tokens": 4000, + "mode": "chat", + "output_cost_per_token": 4e-7, + "provider": "bedrock" + }, + "bedrock/us-gov-west-1/amazon.titan-text-premier-v1:0": { + "input_cost_per_token": 5e-7, + "max_input_tokens": 42000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 0.0000015, + "provider": "bedrock" + }, + "bedrock/us-gov-west-1/anthropic.claude-3-7-sonnet-20250219-v1:0": { + "cache_creation_input_token_cost": 0.0000045, + "cache_read_input_token_cost": 3.6e-7, + "input_cost_per_token": 0.0000036, + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.000018, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "bedrock" + }, + "bedrock/us-gov-west-1/anthropic.claude-3-5-sonnet-20240620-v1:0": { + "input_cost_per_token": 0.0000036, + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.000018, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "bedrock" + }, + "bedrock/us-gov-west-1/anthropic.claude-3-haiku-20240307-v1:0": { + "input_cost_per_token": 3e-7, + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.0000015, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "bedrock" + }, + "bedrock/us-gov-west-1/claude-sonnet-4-5-20250929-v1:0": { + "input_cost_per_token": 0.0000033, + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.0000165, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "bedrock" + }, + "bedrock/us-gov-west-1/meta.llama3-70b-instruct-v1:0": { + "input_cost_per_token": 0.00000265, + "max_input_tokens": 8000, + "max_output_tokens": 2048, + "max_tokens": 2048, + "mode": "chat", + "output_cost_per_token": 0.0000035, + "supports_pdf_input": true, + "provider": "bedrock" + }, + "bedrock/us-gov-west-1/meta.llama3-8b-instruct-v1:0": { + "input_cost_per_token": 3e-7, + "max_input_tokens": 8000, + "max_output_tokens": 2048, + "max_tokens": 2048, + "mode": "chat", + "output_cost_per_token": 0.00000265, + "supports_pdf_input": true, + "provider": "bedrock" + }, + "bedrock/us-west-1/meta.llama3-70b-instruct-v1:0": { + "input_cost_per_token": 0.00000265, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.0000035, + "provider": "bedrock" + }, + "bedrock/us-west-1/meta.llama3-8b-instruct-v1:0": { + "input_cost_per_token": 3e-7, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 6e-7, + "provider": "bedrock" + }, + "bedrock/us-west-2/1-month-commitment/anthropic.claude-instant-v1": { + "input_cost_per_second": 0.011, + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.011, + "supports_tool_choice": true, + "provider": "bedrock" + }, + "bedrock/us-west-2/1-month-commitment/anthropic.claude-v1": { + "input_cost_per_second": 0.0175, + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.0175, + "provider": "bedrock" + }, + "bedrock/us-west-2/1-month-commitment/anthropic.claude-v2:1": { + "input_cost_per_second": 0.0175, + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.0175, + "supports_tool_choice": true, + "provider": "bedrock" + }, + "bedrock/us-west-2/6-month-commitment/anthropic.claude-instant-v1": { + "input_cost_per_second": 0.00611, + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.00611, + "supports_tool_choice": true, + "provider": "bedrock" + }, + "bedrock/us-west-2/6-month-commitment/anthropic.claude-v1": { + "input_cost_per_second": 0.00972, + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.00972, + "provider": "bedrock" + }, + "bedrock/us-west-2/6-month-commitment/anthropic.claude-v2:1": { + "input_cost_per_second": 0.00972, + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.00972, + "supports_tool_choice": true, + "provider": "bedrock" + }, + "bedrock/us-west-2/anthropic.claude-instant-v1": { + "input_cost_per_token": 8e-7, + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 0.0000024, + "supports_tool_choice": true, + "provider": "bedrock" + }, + "bedrock/us-west-2/anthropic.claude-v1": { + "input_cost_per_token": 0.000008, + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 0.000024, + "supports_tool_choice": true, + "provider": "bedrock" + }, + "bedrock/us-west-2/anthropic.claude-v2:1": { + "input_cost_per_token": 0.000008, + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 0.000024, + "supports_tool_choice": true, + "provider": "bedrock" + }, + "bedrock/us-west-2/mistral.mistral-7b-instruct-v0:2": { + "input_cost_per_token": 1.5e-7, + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 2e-7, + "supports_tool_choice": true, + "provider": "bedrock" + }, + "bedrock/us-west-2/mistral.mistral-large-2402-v1:0": { + "input_cost_per_token": 0.000008, + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 0.000024, + "supports_function_calling": true, + "provider": "bedrock" + }, + "bedrock/us-west-2/mistral.mixtral-8x7b-instruct-v0:1": { + "input_cost_per_token": 4.5e-7, + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 7e-7, + "supports_tool_choice": true, + "provider": "bedrock" + }, + "bedrock/us.anthropic.claude-3-5-haiku-20241022-v1:0": { + "cache_creation_input_token_cost": 0.000001, + "cache_read_input_token_cost": 8e-8, + "input_cost_per_token": 8e-7, + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.000004, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "provider": "bedrock" + }, + "cerebras/llama-3.3-70b": { + "input_cost_per_token": 8.5e-7, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.0000012, + "supports_function_calling": true, + "supports_tool_choice": true, + "provider": "cerebras" + }, + "cerebras/llama3.1-70b": { + "input_cost_per_token": 6e-7, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-7, + "supports_function_calling": true, + "supports_tool_choice": true, + "provider": "cerebras" + }, + "cerebras/llama3.1-8b": { + "input_cost_per_token": 1e-7, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-7, + "supports_function_calling": true, + "supports_tool_choice": true, + "provider": "cerebras" + }, + "cerebras/gpt-oss-120b": { + "input_cost_per_token": 2.5e-7, + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 6.9e-7, + "source": "https://www.cerebras.ai/blog/openai-gpt-oss-120b-runs-fastest-on-cerebras", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "provider": "cerebras" + }, + "cerebras/qwen-3-32b": { + "input_cost_per_token": 4e-7, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 8e-7, + "source": "https://inference-docs.cerebras.ai/support/pricing", + "supports_function_calling": true, + "supports_tool_choice": true, + "provider": "cerebras" + }, + "chat-bison": { + "input_cost_per_character": 2.5e-7, + "input_cost_per_token": 1.25e-7, + "max_input_tokens": 8192, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_character": 5e-7, + "output_cost_per_token": 1.25e-7, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "supports_tool_choice": true, + "provider": "vertex_ai-chat-models" + }, + "chat-bison-32k": { + "input_cost_per_character": 2.5e-7, + "input_cost_per_token": 1.25e-7, + "max_input_tokens": 32000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_character": 5e-7, + "output_cost_per_token": 1.25e-7, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "supports_tool_choice": true, + "provider": "vertex_ai-chat-models" + }, + "chat-bison-32k@002": { + "input_cost_per_character": 2.5e-7, + "input_cost_per_token": 1.25e-7, + "max_input_tokens": 32000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_character": 5e-7, + "output_cost_per_token": 1.25e-7, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "supports_tool_choice": true, + "provider": "vertex_ai-chat-models" + }, + "chat-bison@001": { + "input_cost_per_character": 2.5e-7, + "input_cost_per_token": 1.25e-7, + "max_input_tokens": 8192, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_character": 5e-7, + "output_cost_per_token": 1.25e-7, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "supports_tool_choice": true, + "provider": "vertex_ai-chat-models" + }, + "chat-bison@002": { + "deprecation_date": "2025-04-09", + "input_cost_per_character": 2.5e-7, + "input_cost_per_token": 1.25e-7, + "max_input_tokens": 8192, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_character": 5e-7, + "output_cost_per_token": 1.25e-7, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "supports_tool_choice": true, + "provider": "vertex_ai-chat-models" + }, + "chatdolphin": { + "input_cost_per_token": 5e-7, + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 5e-7, + "provider": "nlp_cloud" + }, + "chatgpt-4o-latest": { + "input_cost_per_token": 0.000005, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.000015, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "openai" + }, + "claude-3-5-haiku-20241022": { + "cache_creation_input_token_cost": 0.000001, + "cache_creation_input_token_cost_above_1hr": 0.000006, + "cache_read_input_token_cost": 8e-8, + "deprecation_date": "2025-10-01", + "input_cost_per_token": 8e-7, + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.000004, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "tool_use_system_prompt_tokens": 264, + "provider": "anthropic" + }, + "claude-3-5-haiku-latest": { + "cache_creation_input_token_cost": 0.00000125, + "cache_creation_input_token_cost_above_1hr": 0.000006, + "cache_read_input_token_cost": 1e-7, + "deprecation_date": "2025-10-01", + "input_cost_per_token": 0.000001, + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.000005, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "tool_use_system_prompt_tokens": 264, + "provider": "anthropic" + }, + "claude-haiku-4-5-20251001": { + "cache_creation_input_token_cost": 0.00000125, + "cache_creation_input_token_cost_above_1hr": 0.000002, + "cache_read_input_token_cost": 1e-7, + "input_cost_per_token": 0.000001, + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 0.000005, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_computer_use": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "anthropic" + }, + "claude-haiku-4-5": { + "cache_creation_input_token_cost": 0.00000125, + "cache_creation_input_token_cost_above_1hr": 0.000002, + "cache_read_input_token_cost": 1e-7, + "input_cost_per_token": 0.000001, + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 0.000005, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_computer_use": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "anthropic" + }, + "claude-3-5-sonnet-20240620": { + "cache_creation_input_token_cost": 0.00000375, + "cache_creation_input_token_cost_above_1hr": 0.000006, + "cache_read_input_token_cost": 3e-7, + "deprecation_date": "2025-06-01", + "input_cost_per_token": 0.000003, + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.000015, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159, + "provider": "anthropic" + }, + "claude-3-5-sonnet-20241022": { + "cache_creation_input_token_cost": 0.00000375, + "cache_creation_input_token_cost_above_1hr": 0.000006, + "cache_read_input_token_cost": 3e-7, + "deprecation_date": "2025-10-01", + "input_cost_per_token": 0.000003, + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.000015, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "tool_use_system_prompt_tokens": 159, + "provider": "anthropic" + }, + "claude-3-5-sonnet-latest": { + "cache_creation_input_token_cost": 0.00000375, + "cache_creation_input_token_cost_above_1hr": 0.000006, + "cache_read_input_token_cost": 3e-7, + "deprecation_date": "2025-06-01", + "input_cost_per_token": 0.000003, + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.000015, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "tool_use_system_prompt_tokens": 159, + "provider": "anthropic" + }, + "claude-3-7-sonnet-20250219": { + "cache_creation_input_token_cost": 0.00000375, + "cache_creation_input_token_cost_above_1hr": 0.000006, + "cache_read_input_token_cost": 3e-7, + "deprecation_date": "2026-02-19", + "input_cost_per_token": 0.000003, + "max_input_tokens": 200000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.000015, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "tool_use_system_prompt_tokens": 159, + "provider": "anthropic" + }, + "claude-3-7-sonnet-latest": { + "cache_creation_input_token_cost": 0.00000375, + "cache_creation_input_token_cost_above_1hr": 0.000006, + "cache_read_input_token_cost": 3e-7, + "deprecation_date": "2025-06-01", + "input_cost_per_token": 0.000003, + "max_input_tokens": 200000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.000015, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159, + "provider": "anthropic" + }, + "claude-3-haiku-20240307": { + "cache_creation_input_token_cost": 3e-7, + "cache_creation_input_token_cost_above_1hr": 0.000006, + "cache_read_input_token_cost": 3e-8, + "input_cost_per_token": 2.5e-7, + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.00000125, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 264, + "provider": "anthropic" + }, + "claude-3-opus-20240229": { + "cache_creation_input_token_cost": 0.00001875, + "cache_creation_input_token_cost_above_1hr": 0.000006, + "cache_read_input_token_cost": 0.0000015, + "deprecation_date": "2026-05-01", + "input_cost_per_token": 0.000015, + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.000075, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 395, + "provider": "anthropic" + }, + "claude-3-opus-latest": { + "cache_creation_input_token_cost": 0.00001875, + "cache_creation_input_token_cost_above_1hr": 0.000006, + "cache_read_input_token_cost": 0.0000015, + "deprecation_date": "2025-03-01", + "input_cost_per_token": 0.000015, + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.000075, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 395, + "provider": "anthropic" + }, + "claude-4-opus-20250514": { + "cache_creation_input_token_cost": 0.00001875, + "cache_read_input_token_cost": 0.0000015, + "input_cost_per_token": 0.000015, + "max_input_tokens": 200000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 0.000075, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159, + "provider": "anthropic" + }, + "claude-4-sonnet-20250514": { + "cache_creation_input_token_cost": 0.00000375, + "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, + "cache_read_input_token_cost": 3e-7, + "cache_read_input_token_cost_above_200k_tokens": 6e-7, + "input_cost_per_token": 0.000003, + "input_cost_per_token_above_200k_tokens": 0.000006, + "max_input_tokens": 1000000, + "max_output_tokens": 64000, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 0.000015, + "output_cost_per_token_above_200k_tokens": 0.0000225, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159, + "provider": "anthropic" + }, + "claude-sonnet-4-5": { + "cache_creation_input_token_cost": 0.00000375, + "cache_read_input_token_cost": 3e-7, + "input_cost_per_token": 0.000003, + "input_cost_per_token_above_200k_tokens": 0.000006, + "output_cost_per_token_above_200k_tokens": 0.0000225, + "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, + "cache_read_input_token_cost_above_200k_tokens": 6e-7, + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 0.000015, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 346, + "provider": "anthropic" + }, + "claude-sonnet-4-5-20250929": { + "cache_creation_input_token_cost": 0.00000375, + "cache_read_input_token_cost": 3e-7, + "input_cost_per_token": 0.000003, + "input_cost_per_token_above_200k_tokens": 0.000006, + "output_cost_per_token_above_200k_tokens": 0.0000225, + "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, + "cache_read_input_token_cost_above_200k_tokens": 6e-7, + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 0.000015, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "tool_use_system_prompt_tokens": 346, + "provider": "anthropic" + }, + "claude-sonnet-4-5-20250929-v1:0": { + "cache_creation_input_token_cost": 0.00000375, + "cache_read_input_token_cost": 3e-7, + "input_cost_per_token": 0.000003, + "input_cost_per_token_above_200k_tokens": 0.000006, + "output_cost_per_token_above_200k_tokens": 0.0000225, + "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, + "cache_read_input_token_cost_above_200k_tokens": 6e-7, + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 0.000015, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159, + "provider": "bedrock" + }, + "claude-opus-4-1": { + "cache_creation_input_token_cost": 0.00001875, + "cache_creation_input_token_cost_above_1hr": 0.00003, + "cache_read_input_token_cost": 0.0000015, + "input_cost_per_token": 0.000015, + "max_input_tokens": 200000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 0.000075, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159, + "provider": "anthropic" + }, + "claude-opus-4-1-20250805": { + "cache_creation_input_token_cost": 0.00001875, + "cache_creation_input_token_cost_above_1hr": 0.00003, + "cache_read_input_token_cost": 0.0000015, + "input_cost_per_token": 0.000015, + "deprecation_date": "2026-08-05", + "max_input_tokens": 200000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 0.000075, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159, + "provider": "anthropic" + }, + "claude-opus-4-20250514": { + "cache_creation_input_token_cost": 0.00001875, + "cache_creation_input_token_cost_above_1hr": 0.00003, + "cache_read_input_token_cost": 0.0000015, + "input_cost_per_token": 0.000015, + "deprecation_date": "2026-05-14", + "max_input_tokens": 200000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 0.000075, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159, + "provider": "anthropic" + }, + "claude-sonnet-4-20250514": { + "deprecation_date": "2026-05-14", + "cache_creation_input_token_cost": 0.00000375, + "cache_creation_input_token_cost_above_1hr": 0.000006, + "cache_read_input_token_cost": 3e-7, + "input_cost_per_token": 0.000003, + "input_cost_per_token_above_200k_tokens": 0.000006, + "output_cost_per_token_above_200k_tokens": 0.0000225, + "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, + "cache_read_input_token_cost_above_200k_tokens": 6e-7, + "max_input_tokens": 1000000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 0.000015, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159, + "provider": "anthropic" + }, + "cloudflare/@cf/meta/llama-2-7b-chat-fp16": { + "input_cost_per_token": 0.000001923, + "max_input_tokens": 3072, + "max_output_tokens": 3072, + "max_tokens": 3072, + "mode": "chat", + "output_cost_per_token": 0.000001923, + "provider": "cloudflare" + }, + "cloudflare/@cf/meta/llama-2-7b-chat-int8": { + "input_cost_per_token": 0.000001923, + "max_input_tokens": 2048, + "max_output_tokens": 2048, + "max_tokens": 2048, + "mode": "chat", + "output_cost_per_token": 0.000001923, + "provider": "cloudflare" + }, + "cloudflare/@cf/mistral/mistral-7b-instruct-v0.1": { + "input_cost_per_token": 0.000001923, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.000001923, + "provider": "cloudflare" + }, + "cloudflare/@hf/thebloke/codellama-7b-instruct-awq": { + "input_cost_per_token": 0.000001923, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.000001923, + "provider": "cloudflare" + }, + "code-bison": { + "input_cost_per_character": 2.5e-7, + "input_cost_per_token": 1.25e-7, + "max_input_tokens": 6144, + "max_output_tokens": 1024, + "max_tokens": 1024, + "mode": "chat", + "output_cost_per_character": 5e-7, + "output_cost_per_token": 1.25e-7, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "supports_tool_choice": true, + "provider": "vertex_ai-code-text-models" + }, + "code-bison-32k@002": { + "input_cost_per_character": 2.5e-7, + "input_cost_per_token": 1.25e-7, + "max_input_tokens": 6144, + "max_output_tokens": 1024, + "max_tokens": 1024, + "mode": "completion", + "output_cost_per_character": 5e-7, + "output_cost_per_token": 1.25e-7, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "provider": "vertex_ai-code-text-models" + }, + "code-bison32k": { + "input_cost_per_character": 2.5e-7, + "input_cost_per_token": 1.25e-7, + "max_input_tokens": 6144, + "max_output_tokens": 1024, + "max_tokens": 1024, + "mode": "completion", + "output_cost_per_character": 5e-7, + "output_cost_per_token": 1.25e-7, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "provider": "vertex_ai-code-text-models" + }, + "code-bison@001": { + "input_cost_per_character": 2.5e-7, + "input_cost_per_token": 1.25e-7, + "max_input_tokens": 6144, + "max_output_tokens": 1024, + "max_tokens": 1024, + "mode": "completion", + "output_cost_per_character": 5e-7, + "output_cost_per_token": 1.25e-7, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "provider": "vertex_ai-code-text-models" + }, + "code-bison@002": { + "input_cost_per_character": 2.5e-7, + "input_cost_per_token": 1.25e-7, + "max_input_tokens": 6144, + "max_output_tokens": 1024, + "max_tokens": 1024, + "mode": "completion", + "output_cost_per_character": 5e-7, + "output_cost_per_token": 1.25e-7, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "provider": "vertex_ai-code-text-models" + }, + "code-gecko": { + "input_cost_per_token": 1.25e-7, + "max_input_tokens": 2048, + "max_output_tokens": 64, + "max_tokens": 64, + "mode": "completion", + "output_cost_per_token": 1.25e-7, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "provider": "vertex_ai-code-text-models" + }, + "code-gecko-latest": { + "input_cost_per_token": 1.25e-7, + "max_input_tokens": 2048, + "max_output_tokens": 64, + "max_tokens": 64, + "mode": "completion", + "output_cost_per_token": 1.25e-7, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "provider": "vertex_ai-code-text-models" + }, + "code-gecko@001": { + "input_cost_per_token": 1.25e-7, + "max_input_tokens": 2048, + "max_output_tokens": 64, + "max_tokens": 64, + "mode": "completion", + "output_cost_per_token": 1.25e-7, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "provider": "vertex_ai-code-text-models" + }, + "code-gecko@002": { + "input_cost_per_token": 1.25e-7, + "max_input_tokens": 2048, + "max_output_tokens": 64, + "max_tokens": 64, + "mode": "completion", + "output_cost_per_token": 1.25e-7, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "provider": "vertex_ai-code-text-models" + }, + "codechat-bison": { + "input_cost_per_character": 2.5e-7, + "input_cost_per_token": 1.25e-7, + "max_input_tokens": 6144, + "max_output_tokens": 1024, + "max_tokens": 1024, + "mode": "chat", + "output_cost_per_character": 5e-7, + "output_cost_per_token": 1.25e-7, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "supports_tool_choice": true, + "provider": "vertex_ai-code-chat-models" + }, + "codechat-bison-32k": { + "input_cost_per_character": 2.5e-7, + "input_cost_per_token": 1.25e-7, + "max_input_tokens": 32000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_character": 5e-7, + "output_cost_per_token": 1.25e-7, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "supports_tool_choice": true, + "provider": "vertex_ai-code-chat-models" + }, + "codechat-bison-32k@002": { + "input_cost_per_character": 2.5e-7, + "input_cost_per_token": 1.25e-7, + "max_input_tokens": 32000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_character": 5e-7, + "output_cost_per_token": 1.25e-7, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "supports_tool_choice": true, + "provider": "vertex_ai-code-chat-models" + }, + "codechat-bison@001": { + "input_cost_per_character": 2.5e-7, + "input_cost_per_token": 1.25e-7, + "max_input_tokens": 6144, + "max_output_tokens": 1024, + "max_tokens": 1024, + "mode": "chat", + "output_cost_per_character": 5e-7, + "output_cost_per_token": 1.25e-7, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "supports_tool_choice": true, + "provider": "vertex_ai-code-chat-models" + }, + "codechat-bison@002": { + "input_cost_per_character": 2.5e-7, + "input_cost_per_token": 1.25e-7, + "max_input_tokens": 6144, + "max_output_tokens": 1024, + "max_tokens": 1024, + "mode": "chat", + "output_cost_per_character": 5e-7, + "output_cost_per_token": 1.25e-7, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "supports_tool_choice": true, + "provider": "vertex_ai-code-chat-models" + }, + "codechat-bison@latest": { + "input_cost_per_character": 2.5e-7, + "input_cost_per_token": 1.25e-7, + "max_input_tokens": 6144, + "max_output_tokens": 1024, + "max_tokens": 1024, + "mode": "chat", + "output_cost_per_character": 5e-7, + "output_cost_per_token": 1.25e-7, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "supports_tool_choice": true, + "provider": "vertex_ai-code-chat-models" + }, + "codestral/codestral-2405": { + "input_cost_per_token": 0, + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 0, + "source": "https://docs.mistral.ai/capabilities/code_generation/", + "supports_assistant_prefill": true, + "supports_tool_choice": true, + "provider": "codestral" + }, + "codestral/codestral-latest": { + "input_cost_per_token": 0, + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 0, + "source": "https://docs.mistral.ai/capabilities/code_generation/", + "supports_assistant_prefill": true, + "supports_tool_choice": true, + "provider": "codestral" + }, + "codex-mini-latest": { + "cache_read_input_token_cost": 3.75e-7, + "input_cost_per_token": 0.0000015, + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "responses", + "output_cost_per_token": 0.000006, + "supported_endpoints": ["/v1/responses"], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "openai" + }, + "cohere.command-light-text-v14": { + "input_cost_per_token": 3e-7, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 6e-7, + "supports_tool_choice": true, + "provider": "bedrock" + }, + "cohere.command-r-plus-v1:0": { + "input_cost_per_token": 0.000003, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.000015, + "supports_tool_choice": true, + "provider": "bedrock" + }, + "cohere.command-r-v1:0": { + "input_cost_per_token": 5e-7, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.0000015, + "supports_tool_choice": true, + "provider": "bedrock" + }, + "cohere.command-text-v14": { + "input_cost_per_token": 0.0000015, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.000002, + "supports_tool_choice": true, + "provider": "bedrock" + }, + "cohere.embed-english-v3": { + "input_cost_per_token": 1e-7, + "max_input_tokens": 512, + "max_tokens": 512, + "mode": "embedding", + "output_cost_per_token": 0, + "supports_embedding_image_input": true, + "provider": "bedrock" + }, + "cohere.embed-multilingual-v3": { + "input_cost_per_token": 1e-7, + "max_input_tokens": 512, + "max_tokens": 512, + "mode": "embedding", + "output_cost_per_token": 0, + "supports_embedding_image_input": true, + "provider": "bedrock" + }, + "cohere.embed-v4:0": { + "input_cost_per_token": 1.2e-7, + "max_input_tokens": 128000, + "max_tokens": 128000, + "mode": "embedding", + "output_cost_per_token": 0, + "output_vector_size": 1536, + "supports_embedding_image_input": true, + "provider": "bedrock" + }, + "cohere/embed-v4.0": { + "input_cost_per_token": 1.2e-7, + "max_input_tokens": 128000, + "max_tokens": 128000, + "mode": "embedding", + "output_cost_per_token": 0, + "output_vector_size": 1536, + "supports_embedding_image_input": true, + "provider": "cohere" + }, + "cohere.rerank-v3-5:0": { + "input_cost_per_query": 0.002, + "input_cost_per_token": 0, + "max_document_chunks_per_query": 100, + "max_input_tokens": 32000, + "max_output_tokens": 32000, + "max_query_tokens": 32000, + "max_tokens": 32000, + "max_tokens_per_document_chunk": 512, + "mode": "rerank", + "output_cost_per_token": 0, + "provider": "bedrock" + }, + "command": { + "input_cost_per_token": 0.000001, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "completion", + "output_cost_per_token": 0.000002, + "provider": "cohere" + }, + "command-a-03-2025": { + "input_cost_per_token": 0.0000025, + "max_input_tokens": 256000, + "max_output_tokens": 8000, + "max_tokens": 8000, + "mode": "chat", + "output_cost_per_token": 0.00001, + "supports_function_calling": true, + "supports_tool_choice": true, + "provider": "cohere_chat" + }, + "command-light": { + "input_cost_per_token": 3e-7, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 6e-7, + "supports_tool_choice": true, + "provider": "cohere_chat" + }, + "command-nightly": { + "input_cost_per_token": 0.000001, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "completion", + "output_cost_per_token": 0.000002, + "provider": "cohere" + }, + "command-r": { + "input_cost_per_token": 1.5e-7, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 6e-7, + "supports_function_calling": true, + "supports_tool_choice": true, + "provider": "cohere_chat" + }, + "command-r-08-2024": { + "input_cost_per_token": 1.5e-7, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 6e-7, + "supports_function_calling": true, + "supports_tool_choice": true, + "provider": "cohere_chat" + }, + "command-r-plus": { + "input_cost_per_token": 0.0000025, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.00001, + "supports_function_calling": true, + "supports_tool_choice": true, + "provider": "cohere_chat" + }, + "command-r-plus-08-2024": { + "input_cost_per_token": 0.0000025, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.00001, + "supports_function_calling": true, + "supports_tool_choice": true, + "provider": "cohere_chat" + }, + "command-r7b-12-2024": { + "input_cost_per_token": 1.5e-7, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 3.75e-8, + "source": "https://docs.cohere.com/v2/docs/command-r7b", + "supports_function_calling": true, + "supports_tool_choice": true, + "provider": "cohere_chat" + }, + "computer-use-preview": { + "input_cost_per_token": 0.000003, + "max_input_tokens": 8192, + "max_output_tokens": 1024, + "max_tokens": 1024, + "mode": "chat", + "output_cost_per_token": 0.000012, + "supported_endpoints": ["/v1/responses"], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "azure" + }, + "deepseek-chat": { + "cache_read_input_token_cost": 6e-8, + "input_cost_per_token": 6e-7, + "max_input_tokens": 131072, + "max_output_tokens": 8192, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 0.0000017, + "source": "https://api-docs.deepseek.com/quick_start/pricing", + "supported_endpoints": ["/v1/chat/completions"], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "deepseek" + }, + "deepseek-reasoner": { + "cache_read_input_token_cost": 6e-8, + "input_cost_per_token": 6e-7, + "max_input_tokens": 131072, + "max_output_tokens": 65536, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 0.0000017, + "source": "https://api-docs.deepseek.com/quick_start/pricing", + "supported_endpoints": ["/v1/chat/completions"], + "supports_function_calling": false, + "supports_native_streaming": true, + "supports_parallel_function_calling": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": false, + "provider": "deepseek" + }, + "dashscope/qwen-coder": { + "input_cost_per_token": 3e-7, + "max_input_tokens": 1000000, + "max_output_tokens": 16384, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 0.0000015, + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "provider": "dashscope" + }, + "dashscope/qwen-flash": { + "max_input_tokens": 997952, + "max_output_tokens": 32768, + "max_tokens": 1000000, + "mode": "chat", + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "tiered_pricing": [ + { + "input_cost_per_token": 5e-8, + "output_cost_per_token": 4e-7, + "range": [0, 256000] + }, + { + "input_cost_per_token": 2.5e-7, + "output_cost_per_token": 0.000002, + "range": [256000, 1000000] + } + ], + "provider": "dashscope" + }, + "dashscope/qwen-flash-2025-07-28": { + "max_input_tokens": 997952, + "max_output_tokens": 32768, + "max_tokens": 1000000, + "mode": "chat", + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "tiered_pricing": [ + { + "input_cost_per_token": 5e-8, + "output_cost_per_token": 4e-7, + "range": [0, 256000] + }, + { + "input_cost_per_token": 2.5e-7, + "output_cost_per_token": 0.000002, + "range": [256000, 1000000] + } + ], + "provider": "dashscope" + }, + "dashscope/qwen-max": { + "input_cost_per_token": 0.0000016, + "max_input_tokens": 30720, + "max_output_tokens": 8192, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0.0000064, + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "provider": "dashscope" + }, + "dashscope/qwen-plus": { + "input_cost_per_token": 4e-7, + "max_input_tokens": 129024, + "max_output_tokens": 16384, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 0.0000012, + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "provider": "dashscope" + }, + "dashscope/qwen-plus-2025-01-25": { + "input_cost_per_token": 4e-7, + "max_input_tokens": 129024, + "max_output_tokens": 8192, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 0.0000012, + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "provider": "dashscope" + }, + "dashscope/qwen-plus-2025-04-28": { + "input_cost_per_token": 4e-7, + "max_input_tokens": 129024, + "max_output_tokens": 16384, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_reasoning_token": 0.000004, + "output_cost_per_token": 0.0000012, + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "provider": "dashscope" + }, + "dashscope/qwen-plus-2025-07-14": { + "input_cost_per_token": 4e-7, + "max_input_tokens": 129024, + "max_output_tokens": 16384, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_reasoning_token": 0.000004, + "output_cost_per_token": 0.0000012, + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "provider": "dashscope" + }, + "dashscope/qwen-plus-2025-07-28": { + "max_input_tokens": 997952, + "max_output_tokens": 32768, + "max_tokens": 1000000, + "mode": "chat", + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "tiered_pricing": [ + { + "input_cost_per_token": 4e-7, + "output_cost_per_reasoning_token": 0.000004, + "output_cost_per_token": 0.0000012, + "range": [0, 256000] + }, + { + "input_cost_per_token": 0.0000012, + "output_cost_per_reasoning_token": 0.000012, + "output_cost_per_token": 0.0000036, + "range": [256000, 1000000] + } + ], + "provider": "dashscope" + }, + "dashscope/qwen-plus-2025-09-11": { + "max_input_tokens": 997952, + "max_output_tokens": 32768, + "max_tokens": 1000000, + "mode": "chat", + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "tiered_pricing": [ + { + "input_cost_per_token": 4e-7, + "output_cost_per_reasoning_token": 0.000004, + "output_cost_per_token": 0.0000012, + "range": [0, 256000] + }, + { + "input_cost_per_token": 0.0000012, + "output_cost_per_reasoning_token": 0.000012, + "output_cost_per_token": 0.0000036, + "range": [256000, 1000000] + } + ], + "provider": "dashscope" + }, + "dashscope/qwen-plus-latest": { + "max_input_tokens": 997952, + "max_output_tokens": 32768, + "max_tokens": 1000000, + "mode": "chat", + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "tiered_pricing": [ + { + "input_cost_per_token": 4e-7, + "output_cost_per_reasoning_token": 0.000004, + "output_cost_per_token": 0.0000012, + "range": [0, 256000] + }, + { + "input_cost_per_token": 0.0000012, + "output_cost_per_reasoning_token": 0.000012, + "output_cost_per_token": 0.0000036, + "range": [256000, 1000000] + } + ], + "provider": "dashscope" + }, + "dashscope/qwen-turbo": { + "input_cost_per_token": 5e-8, + "max_input_tokens": 129024, + "max_output_tokens": 16384, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_reasoning_token": 5e-7, + "output_cost_per_token": 2e-7, + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "provider": "dashscope" + }, + "dashscope/qwen-turbo-2024-11-01": { + "input_cost_per_token": 5e-8, + "max_input_tokens": 1000000, + "max_output_tokens": 8192, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 2e-7, + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "provider": "dashscope" + }, + "dashscope/qwen-turbo-2025-04-28": { + "input_cost_per_token": 5e-8, + "max_input_tokens": 1000000, + "max_output_tokens": 16384, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_reasoning_token": 5e-7, + "output_cost_per_token": 2e-7, + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "provider": "dashscope" + }, + "dashscope/qwen-turbo-latest": { + "input_cost_per_token": 5e-8, + "max_input_tokens": 1000000, + "max_output_tokens": 16384, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_reasoning_token": 5e-7, + "output_cost_per_token": 2e-7, + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "provider": "dashscope" + }, + "dashscope/qwen3-30b-a3b": { + "max_input_tokens": 129024, + "max_output_tokens": 16384, + "max_tokens": 131072, + "mode": "chat", + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "provider": "dashscope" + }, + "dashscope/qwen3-coder-flash": { + "max_input_tokens": 997952, + "max_output_tokens": 65536, + "max_tokens": 1000000, + "mode": "chat", + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "tiered_pricing": [ + { + "cache_read_input_token_cost": 8e-8, + "input_cost_per_token": 3e-7, + "output_cost_per_token": 0.0000015, + "range": [0, 32000] + }, + { + "cache_read_input_token_cost": 1.2e-7, + "input_cost_per_token": 5e-7, + "output_cost_per_token": 0.0000025, + "range": [32000, 128000] + }, + { + "cache_read_input_token_cost": 2e-7, + "input_cost_per_token": 8e-7, + "output_cost_per_token": 0.000004, + "range": [128000, 256000] + }, + { + "cache_read_input_token_cost": 4e-7, + "input_cost_per_token": 0.0000016, + "output_cost_per_token": 0.0000096, + "range": [256000, 1000000] + } + ], + "provider": "dashscope" + }, + "dashscope/qwen3-coder-flash-2025-07-28": { + "max_input_tokens": 997952, + "max_output_tokens": 65536, + "max_tokens": 1000000, + "mode": "chat", + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "tiered_pricing": [ + { + "input_cost_per_token": 3e-7, + "output_cost_per_token": 0.0000015, + "range": [0, 32000] + }, + { + "input_cost_per_token": 5e-7, + "output_cost_per_token": 0.0000025, + "range": [32000, 128000] + }, + { + "input_cost_per_token": 8e-7, + "output_cost_per_token": 0.000004, + "range": [128000, 256000] + }, + { + "input_cost_per_token": 0.0000016, + "output_cost_per_token": 0.0000096, + "range": [256000, 1000000] + } + ], + "provider": "dashscope" + }, + "dashscope/qwen3-coder-plus": { + "max_input_tokens": 997952, + "max_output_tokens": 65536, + "max_tokens": 1000000, + "mode": "chat", + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "tiered_pricing": [ + { + "cache_read_input_token_cost": 1e-7, + "input_cost_per_token": 0.000001, + "output_cost_per_token": 0.000005, + "range": [0, 32000] + }, + { + "cache_read_input_token_cost": 1.8e-7, + "input_cost_per_token": 0.0000018, + "output_cost_per_token": 0.000009, + "range": [32000, 128000] + }, + { + "cache_read_input_token_cost": 3e-7, + "input_cost_per_token": 0.000003, + "output_cost_per_token": 0.000015, + "range": [128000, 256000] + }, + { + "cache_read_input_token_cost": 6e-7, + "input_cost_per_token": 0.000006, + "output_cost_per_token": 0.00006, + "range": [256000, 1000000] + } + ], + "provider": "dashscope" + }, + "dashscope/qwen3-coder-plus-2025-07-22": { + "max_input_tokens": 997952, + "max_output_tokens": 65536, + "max_tokens": 1000000, + "mode": "chat", + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "tiered_pricing": [ + { + "input_cost_per_token": 0.000001, + "output_cost_per_token": 0.000005, + "range": [0, 32000] + }, + { + "input_cost_per_token": 0.0000018, + "output_cost_per_token": 0.000009, + "range": [32000, 128000] + }, + { + "input_cost_per_token": 0.000003, + "output_cost_per_token": 0.000015, + "range": [128000, 256000] + }, + { + "input_cost_per_token": 0.000006, + "output_cost_per_token": 0.00006, + "range": [256000, 1000000] + } + ], + "provider": "dashscope" + }, + "dashscope/qwen3-max-preview": { + "max_input_tokens": 258048, + "max_output_tokens": 65536, + "max_tokens": 262144, + "mode": "chat", + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "tiered_pricing": [ + { + "input_cost_per_token": 0.0000012, + "output_cost_per_token": 0.000006, + "range": [0, 32000] + }, + { + "input_cost_per_token": 0.0000024, + "output_cost_per_token": 0.000012, + "range": [32000, 128000] + }, + { + "input_cost_per_token": 0.000003, + "output_cost_per_token": 0.000015, + "range": [128000, 252000] + } + ], + "provider": "dashscope" + }, + "dashscope/qwq-plus": { + "input_cost_per_token": 8e-7, + "max_input_tokens": 98304, + "max_output_tokens": 8192, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 0.0000024, + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "provider": "dashscope" + }, + "databricks/databricks-bge-large-en": { + "input_cost_per_token": 1.0003e-7, + "input_dbu_cost_per_token": 0.000001429, + "max_input_tokens": 512, + "max_tokens": 512, + "metadata": { + "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." + }, + "mode": "embedding", + "output_cost_per_token": 0, + "output_dbu_cost_per_token": 0, + "output_vector_size": 1024, + "source": "https://www.databricks.com/product/pricing/foundation-model-serving", + "provider": "databricks" + }, + "databricks/databricks-claude-3-7-sonnet": { + "input_cost_per_token": 0.0000025, + "input_dbu_cost_per_token": 0.00003571, + "max_input_tokens": 200000, + "max_output_tokens": 128000, + "max_tokens": 200000, + "metadata": { + "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Claude 3.7 conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." + }, + "mode": "chat", + "output_cost_per_token": 0.000017857, + "output_db_cost_per_token": 0.000214286, + "source": "https://www.databricks.com/product/pricing/foundation-model-serving", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "provider": "databricks" + }, + "databricks/databricks-gte-large-en": { + "input_cost_per_token": 1.2999e-7, + "input_dbu_cost_per_token": 0.000001857, + "max_input_tokens": 8192, + "max_tokens": 8192, + "metadata": { + "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." + }, + "mode": "embedding", + "output_cost_per_token": 0, + "output_dbu_cost_per_token": 0, + "output_vector_size": 1024, + "source": "https://www.databricks.com/product/pricing/foundation-model-serving", + "provider": "databricks" + }, + "databricks/databricks-llama-2-70b-chat": { + "input_cost_per_token": 5.0001e-7, + "input_dbu_cost_per_token": 0.000007143, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "metadata": { + "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." + }, + "mode": "chat", + "output_cost_per_token": 0.0000015, + "output_dbu_cost_per_token": 0.000021429, + "source": "https://www.databricks.com/product/pricing/foundation-model-serving", + "supports_tool_choice": true, + "provider": "databricks" + }, + "databricks/databricks-llama-4-maverick": { + "input_cost_per_token": 0.000005, + "input_dbu_cost_per_token": 0.00007143, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "metadata": { + "notes": "Databricks documentation now provides both DBU costs (_dbu_cost_per_token) and dollar costs(_cost_per_token)." + }, + "mode": "chat", + "output_cost_per_token": 0.000015, + "output_dbu_cost_per_token": 0.00021429, + "source": "https://www.databricks.com/product/pricing/foundation-model-serving", + "supports_tool_choice": true, + "provider": "databricks" + }, + "databricks/databricks-meta-llama-3-1-405b-instruct": { + "input_cost_per_token": 0.000005, + "input_dbu_cost_per_token": 0.000071429, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "metadata": { + "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." + }, + "mode": "chat", + "output_cost_per_token": 0.00001500002, + "output_db_cost_per_token": 0.000214286, + "source": "https://www.databricks.com/product/pricing/foundation-model-serving", + "supports_tool_choice": true, + "provider": "databricks" + }, + "databricks/databricks-meta-llama-3-3-70b-instruct": { + "input_cost_per_token": 0.00000100002, + "input_dbu_cost_per_token": 0.000014286, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "metadata": { + "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." + }, + "mode": "chat", + "output_cost_per_token": 0.00000299999, + "output_dbu_cost_per_token": 0.000042857, + "source": "https://www.databricks.com/product/pricing/foundation-model-serving", + "supports_tool_choice": true, + "provider": "databricks" + }, + "databricks/databricks-meta-llama-3-70b-instruct": { + "input_cost_per_token": 0.00000100002, + "input_dbu_cost_per_token": 0.000014286, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "metadata": { + "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." + }, + "mode": "chat", + "output_cost_per_token": 0.00000299999, + "output_dbu_cost_per_token": 0.000042857, + "source": "https://www.databricks.com/product/pricing/foundation-model-serving", + "supports_tool_choice": true, + "provider": "databricks" + }, + "databricks/databricks-mixtral-8x7b-instruct": { + "input_cost_per_token": 5.0001e-7, + "input_dbu_cost_per_token": 0.000007143, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "metadata": { + "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." + }, + "mode": "chat", + "output_cost_per_token": 9.9902e-7, + "output_dbu_cost_per_token": 0.000014286, + "source": "https://www.databricks.com/product/pricing/foundation-model-serving", + "supports_tool_choice": true, + "provider": "databricks" + }, + "databricks/databricks-mpt-30b-instruct": { + "input_cost_per_token": 9.9902e-7, + "input_dbu_cost_per_token": 0.000014286, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "metadata": { + "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." + }, + "mode": "chat", + "output_cost_per_token": 9.9902e-7, + "output_dbu_cost_per_token": 0.000014286, + "source": "https://www.databricks.com/product/pricing/foundation-model-serving", + "supports_tool_choice": true, + "provider": "databricks" + }, + "databricks/databricks-mpt-7b-instruct": { + "input_cost_per_token": 5.0001e-7, + "input_dbu_cost_per_token": 0.000007143, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "metadata": { + "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." + }, + "mode": "chat", + "output_cost_per_token": 0, + "output_dbu_cost_per_token": 0, + "source": "https://www.databricks.com/product/pricing/foundation-model-serving", + "supports_tool_choice": true, + "provider": "databricks" + }, + "dataforseo/search": { + "input_cost_per_query": 0.003, + "mode": "search", + "provider": "dataforseo" + }, + "davinci-002": { + "input_cost_per_token": 0.000002, + "max_input_tokens": 16384, + "max_output_tokens": 4096, + "max_tokens": 16384, + "mode": "completion", + "output_cost_per_token": 0.000002, + "provider": "text-completion-openai" + }, + "deepgram/base": { + "input_cost_per_second": 0.00020833, + "metadata": { + "calculation": "$0.0125/60 seconds = $0.00020833 per second", + "original_pricing_per_minute": 0.0125 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": ["/v1/audio/transcriptions"], + "provider": "deepgram" + }, + "deepgram/base-conversationalai": { + "input_cost_per_second": 0.00020833, + "metadata": { + "calculation": "$0.0125/60 seconds = $0.00020833 per second", + "original_pricing_per_minute": 0.0125 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": ["/v1/audio/transcriptions"], + "provider": "deepgram" + }, + "deepgram/base-finance": { + "input_cost_per_second": 0.00020833, + "metadata": { + "calculation": "$0.0125/60 seconds = $0.00020833 per second", + "original_pricing_per_minute": 0.0125 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": ["/v1/audio/transcriptions"], + "provider": "deepgram" + }, + "deepgram/base-general": { + "input_cost_per_second": 0.00020833, + "metadata": { + "calculation": "$0.0125/60 seconds = $0.00020833 per second", + "original_pricing_per_minute": 0.0125 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": ["/v1/audio/transcriptions"], + "provider": "deepgram" + }, + "deepgram/base-meeting": { + "input_cost_per_second": 0.00020833, + "metadata": { + "calculation": "$0.0125/60 seconds = $0.00020833 per second", + "original_pricing_per_minute": 0.0125 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": ["/v1/audio/transcriptions"], + "provider": "deepgram" + }, + "deepgram/base-phonecall": { + "input_cost_per_second": 0.00020833, + "metadata": { + "calculation": "$0.0125/60 seconds = $0.00020833 per second", + "original_pricing_per_minute": 0.0125 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": ["/v1/audio/transcriptions"], + "provider": "deepgram" + }, + "deepgram/base-video": { + "input_cost_per_second": 0.00020833, + "metadata": { + "calculation": "$0.0125/60 seconds = $0.00020833 per second", + "original_pricing_per_minute": 0.0125 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": ["/v1/audio/transcriptions"], + "provider": "deepgram" + }, + "deepgram/base-voicemail": { + "input_cost_per_second": 0.00020833, + "metadata": { + "calculation": "$0.0125/60 seconds = $0.00020833 per second", + "original_pricing_per_minute": 0.0125 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": ["/v1/audio/transcriptions"], + "provider": "deepgram" + }, + "deepgram/enhanced": { + "input_cost_per_second": 0.00024167, + "metadata": { + "calculation": "$0.0145/60 seconds = $0.00024167 per second", + "original_pricing_per_minute": 0.0145 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": ["/v1/audio/transcriptions"], + "provider": "deepgram" + }, + "deepgram/enhanced-finance": { + "input_cost_per_second": 0.00024167, + "metadata": { + "calculation": "$0.0145/60 seconds = $0.00024167 per second", + "original_pricing_per_minute": 0.0145 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": ["/v1/audio/transcriptions"], + "provider": "deepgram" + }, + "deepgram/enhanced-general": { + "input_cost_per_second": 0.00024167, + "metadata": { + "calculation": "$0.0145/60 seconds = $0.00024167 per second", + "original_pricing_per_minute": 0.0145 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": ["/v1/audio/transcriptions"], + "provider": "deepgram" + }, + "deepgram/enhanced-meeting": { + "input_cost_per_second": 0.00024167, + "metadata": { + "calculation": "$0.0145/60 seconds = $0.00024167 per second", + "original_pricing_per_minute": 0.0145 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": ["/v1/audio/transcriptions"], + "provider": "deepgram" + }, + "deepgram/enhanced-phonecall": { + "input_cost_per_second": 0.00024167, + "metadata": { + "calculation": "$0.0145/60 seconds = $0.00024167 per second", + "original_pricing_per_minute": 0.0145 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": ["/v1/audio/transcriptions"], + "provider": "deepgram" + }, + "deepgram/nova": { + "input_cost_per_second": 0.00007167, + "metadata": { + "calculation": "$0.0043/60 seconds = $0.00007167 per second", + "original_pricing_per_minute": 0.0043 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": ["/v1/audio/transcriptions"], + "provider": "deepgram" + }, + "deepgram/nova-2": { + "input_cost_per_second": 0.00007167, + "metadata": { + "calculation": "$0.0043/60 seconds = $0.00007167 per second", + "original_pricing_per_minute": 0.0043 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": ["/v1/audio/transcriptions"], + "provider": "deepgram" + }, + "deepgram/nova-2-atc": { + "input_cost_per_second": 0.00007167, + "metadata": { + "calculation": "$0.0043/60 seconds = $0.00007167 per second", + "original_pricing_per_minute": 0.0043 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": ["/v1/audio/transcriptions"], + "provider": "deepgram" + }, + "deepgram/nova-2-automotive": { + "input_cost_per_second": 0.00007167, + "metadata": { + "calculation": "$0.0043/60 seconds = $0.00007167 per second", + "original_pricing_per_minute": 0.0043 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": ["/v1/audio/transcriptions"], + "provider": "deepgram" + }, + "deepgram/nova-2-conversationalai": { + "input_cost_per_second": 0.00007167, + "metadata": { + "calculation": "$0.0043/60 seconds = $0.00007167 per second", + "original_pricing_per_minute": 0.0043 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": ["/v1/audio/transcriptions"], + "provider": "deepgram" + }, + "deepgram/nova-2-drivethru": { + "input_cost_per_second": 0.00007167, + "metadata": { + "calculation": "$0.0043/60 seconds = $0.00007167 per second", + "original_pricing_per_minute": 0.0043 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": ["/v1/audio/transcriptions"], + "provider": "deepgram" + }, + "deepgram/nova-2-finance": { + "input_cost_per_second": 0.00007167, + "metadata": { + "calculation": "$0.0043/60 seconds = $0.00007167 per second", + "original_pricing_per_minute": 0.0043 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": ["/v1/audio/transcriptions"], + "provider": "deepgram" + }, + "deepgram/nova-2-general": { + "input_cost_per_second": 0.00007167, + "metadata": { + "calculation": "$0.0043/60 seconds = $0.00007167 per second", + "original_pricing_per_minute": 0.0043 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": ["/v1/audio/transcriptions"], + "provider": "deepgram" + }, + "deepgram/nova-2-meeting": { + "input_cost_per_second": 0.00007167, + "metadata": { + "calculation": "$0.0043/60 seconds = $0.00007167 per second", + "original_pricing_per_minute": 0.0043 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": ["/v1/audio/transcriptions"], + "provider": "deepgram" + }, + "deepgram/nova-2-phonecall": { + "input_cost_per_second": 0.00007167, + "metadata": { + "calculation": "$0.0043/60 seconds = $0.00007167 per second", + "original_pricing_per_minute": 0.0043 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": ["/v1/audio/transcriptions"], + "provider": "deepgram" + }, + "deepgram/nova-2-video": { + "input_cost_per_second": 0.00007167, + "metadata": { + "calculation": "$0.0043/60 seconds = $0.00007167 per second", + "original_pricing_per_minute": 0.0043 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": ["/v1/audio/transcriptions"], + "provider": "deepgram" + }, + "deepgram/nova-2-voicemail": { + "input_cost_per_second": 0.00007167, + "metadata": { + "calculation": "$0.0043/60 seconds = $0.00007167 per second", + "original_pricing_per_minute": 0.0043 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": ["/v1/audio/transcriptions"], + "provider": "deepgram" + }, + "deepgram/nova-3": { + "input_cost_per_second": 0.00007167, + "metadata": { + "calculation": "$0.0043/60 seconds = $0.00007167 per second", + "original_pricing_per_minute": 0.0043 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": ["/v1/audio/transcriptions"], + "provider": "deepgram" + }, + "deepgram/nova-3-general": { + "input_cost_per_second": 0.00007167, + "metadata": { + "calculation": "$0.0043/60 seconds = $0.00007167 per second", + "original_pricing_per_minute": 0.0043 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": ["/v1/audio/transcriptions"], + "provider": "deepgram" + }, + "deepgram/nova-3-medical": { + "input_cost_per_second": 0.00008667, + "metadata": { + "calculation": "$0.0052/60 seconds = $0.00008667 per second (multilingual)", + "original_pricing_per_minute": 0.0052 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": ["/v1/audio/transcriptions"], + "provider": "deepgram" + }, + "deepgram/nova-general": { + "input_cost_per_second": 0.00007167, + "metadata": { + "calculation": "$0.0043/60 seconds = $0.00007167 per second", + "original_pricing_per_minute": 0.0043 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": ["/v1/audio/transcriptions"], + "provider": "deepgram" + }, + "deepgram/nova-phonecall": { + "input_cost_per_second": 0.00007167, + "metadata": { + "calculation": "$0.0043/60 seconds = $0.00007167 per second", + "original_pricing_per_minute": 0.0043 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": ["/v1/audio/transcriptions"], + "provider": "deepgram" + }, + "deepgram/whisper": { + "input_cost_per_second": 0.0001, + "metadata": { + "notes": "Deepgram's hosted OpenAI Whisper models - pricing may differ from native Deepgram models" + }, + "mode": "audio_transcription", + "output_cost_per_second": 0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": ["/v1/audio/transcriptions"], + "provider": "deepgram" + }, + "deepgram/whisper-base": { + "input_cost_per_second": 0.0001, + "metadata": { + "notes": "Deepgram's hosted OpenAI Whisper models - pricing may differ from native Deepgram models" + }, + "mode": "audio_transcription", + "output_cost_per_second": 0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": ["/v1/audio/transcriptions"], + "provider": "deepgram" + }, + "deepgram/whisper-large": { + "input_cost_per_second": 0.0001, + "metadata": { + "notes": "Deepgram's hosted OpenAI Whisper models - pricing may differ from native Deepgram models" + }, + "mode": "audio_transcription", + "output_cost_per_second": 0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": ["/v1/audio/transcriptions"], + "provider": "deepgram" + }, + "deepgram/whisper-medium": { + "input_cost_per_second": 0.0001, + "metadata": { + "notes": "Deepgram's hosted OpenAI Whisper models - pricing may differ from native Deepgram models" + }, + "mode": "audio_transcription", + "output_cost_per_second": 0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": ["/v1/audio/transcriptions"], + "provider": "deepgram" + }, + "deepgram/whisper-small": { + "input_cost_per_second": 0.0001, + "metadata": { + "notes": "Deepgram's hosted OpenAI Whisper models - pricing may differ from native Deepgram models" + }, + "mode": "audio_transcription", + "output_cost_per_second": 0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": ["/v1/audio/transcriptions"], + "provider": "deepgram" + }, + "deepgram/whisper-tiny": { + "input_cost_per_second": 0.0001, + "metadata": { + "notes": "Deepgram's hosted OpenAI Whisper models - pricing may differ from native Deepgram models" + }, + "mode": "audio_transcription", + "output_cost_per_second": 0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": ["/v1/audio/transcriptions"], + "provider": "deepgram" + }, + "deepinfra/Gryphe/MythoMax-L2-13b": { + "max_tokens": 4096, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "input_cost_per_token": 8e-8, + "output_cost_per_token": 9e-8, + "mode": "chat", + "supports_tool_choice": true, + "provider": "deepinfra" + }, + "deepinfra/NousResearch/Hermes-3-Llama-3.1-405B": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 0.000001, + "output_cost_per_token": 0.000001, + "mode": "chat", + "supports_tool_choice": true, + "provider": "deepinfra" + }, + "deepinfra/NousResearch/Hermes-3-Llama-3.1-70B": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 3e-7, + "output_cost_per_token": 3e-7, + "mode": "chat", + "supports_tool_choice": false, + "provider": "deepinfra" + }, + "deepinfra/Qwen/QwQ-32B": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 1.5e-7, + "output_cost_per_token": 4e-7, + "mode": "chat", + "supports_tool_choice": true, + "provider": "deepinfra" + }, + "deepinfra/Qwen/Qwen2.5-72B-Instruct": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 1.2e-7, + "output_cost_per_token": 3.9e-7, + "mode": "chat", + "supports_tool_choice": true, + "provider": "deepinfra" + }, + "deepinfra/Qwen/Qwen2.5-7B-Instruct": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 4e-8, + "output_cost_per_token": 1e-7, + "mode": "chat", + "supports_tool_choice": false, + "provider": "deepinfra" + }, + "deepinfra/Qwen/Qwen2.5-VL-32B-Instruct": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 2e-7, + "output_cost_per_token": 6e-7, + "mode": "chat", + "supports_tool_choice": true, + "supports_vision": true, + "provider": "deepinfra" + }, + "deepinfra/Qwen/Qwen3-14B": { + "max_tokens": 40960, + "max_input_tokens": 40960, + "max_output_tokens": 40960, + "input_cost_per_token": 6e-8, + "output_cost_per_token": 2.4e-7, + "mode": "chat", + "supports_tool_choice": true, + "provider": "deepinfra" + }, + "deepinfra/Qwen/Qwen3-235B-A22B": { + "max_tokens": 40960, + "max_input_tokens": 40960, + "max_output_tokens": 40960, + "input_cost_per_token": 1.8e-7, + "output_cost_per_token": 5.4e-7, + "mode": "chat", + "supports_tool_choice": true, + "provider": "deepinfra" + }, + "deepinfra/Qwen/Qwen3-235B-A22B-Instruct-2507": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "input_cost_per_token": 9e-8, + "output_cost_per_token": 6e-7, + "mode": "chat", + "supports_tool_choice": true, + "provider": "deepinfra" + }, + "deepinfra/Qwen/Qwen3-235B-A22B-Thinking-2507": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "input_cost_per_token": 3e-7, + "output_cost_per_token": 0.0000029, + "mode": "chat", + "supports_tool_choice": true, + "provider": "deepinfra" + }, + "deepinfra/Qwen/Qwen3-30B-A3B": { + "max_tokens": 40960, + "max_input_tokens": 40960, + "max_output_tokens": 40960, + "input_cost_per_token": 8e-8, + "output_cost_per_token": 2.9e-7, + "mode": "chat", + "supports_tool_choice": true, + "provider": "deepinfra" + }, + "deepinfra/Qwen/Qwen3-32B": { + "max_tokens": 40960, + "max_input_tokens": 40960, + "max_output_tokens": 40960, + "input_cost_per_token": 1e-7, + "output_cost_per_token": 2.8e-7, + "mode": "chat", + "supports_tool_choice": true, + "provider": "deepinfra" + }, + "deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "input_cost_per_token": 4e-7, + "output_cost_per_token": 0.0000016, + "mode": "chat", + "supports_tool_choice": true, + "provider": "deepinfra" + }, + "deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "input_cost_per_token": 2.9e-7, + "output_cost_per_token": 0.0000012, + "mode": "chat", + "supports_tool_choice": true, + "provider": "deepinfra" + }, + "deepinfra/Qwen/Qwen3-Next-80B-A3B-Instruct": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "input_cost_per_token": 1.4e-7, + "output_cost_per_token": 0.0000014, + "mode": "chat", + "supports_tool_choice": true, + "provider": "deepinfra" + }, + "deepinfra/Qwen/Qwen3-Next-80B-A3B-Thinking": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "input_cost_per_token": 1.4e-7, + "output_cost_per_token": 0.0000014, + "mode": "chat", + "supports_tool_choice": true, + "provider": "deepinfra" + }, + "deepinfra/Sao10K/L3-8B-Lunaris-v1-Turbo": { + "max_tokens": 8192, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "input_cost_per_token": 4e-8, + "output_cost_per_token": 5e-8, + "mode": "chat", + "supports_tool_choice": false, + "provider": "deepinfra" + }, + "deepinfra/Sao10K/L3.1-70B-Euryale-v2.2": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 6.5e-7, + "output_cost_per_token": 7.5e-7, + "mode": "chat", + "supports_tool_choice": false, + "provider": "deepinfra" + }, + "deepinfra/Sao10K/L3.3-70B-Euryale-v2.3": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 6.5e-7, + "output_cost_per_token": 7.5e-7, + "mode": "chat", + "supports_tool_choice": false, + "provider": "deepinfra" + }, + "deepinfra/allenai/olmOCR-7B-0725-FP8": { + "max_tokens": 16384, + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "input_cost_per_token": 2.7e-7, + "output_cost_per_token": 0.0000015, + "mode": "chat", + "supports_tool_choice": false, + "provider": "deepinfra" + }, + "deepinfra/anthropic/claude-3-7-sonnet-latest": { + "max_tokens": 200000, + "max_input_tokens": 200000, + "max_output_tokens": 200000, + "input_cost_per_token": 0.0000033, + "output_cost_per_token": 0.0000165, + "cache_read_input_token_cost": 3.3e-7, + "mode": "chat", + "supports_tool_choice": true, + "provider": "deepinfra" + }, + "deepinfra/anthropic/claude-4-opus": { + "max_tokens": 200000, + "max_input_tokens": 200000, + "max_output_tokens": 200000, + "input_cost_per_token": 0.0000165, + "output_cost_per_token": 0.0000825, + "mode": "chat", + "supports_tool_choice": true, + "provider": "deepinfra" + }, + "deepinfra/anthropic/claude-4-sonnet": { + "max_tokens": 200000, + "max_input_tokens": 200000, + "max_output_tokens": 200000, + "input_cost_per_token": 0.0000033, + "output_cost_per_token": 0.0000165, + "mode": "chat", + "supports_tool_choice": true, + "provider": "deepinfra" + }, + "deepinfra/deepseek-ai/DeepSeek-R1": { + "max_tokens": 163840, + "max_input_tokens": 163840, + "max_output_tokens": 163840, + "input_cost_per_token": 7e-7, + "output_cost_per_token": 0.0000024, + "mode": "chat", + "supports_tool_choice": true, + "provider": "deepinfra" + }, + "deepinfra/deepseek-ai/DeepSeek-R1-0528": { + "max_tokens": 163840, + "max_input_tokens": 163840, + "max_output_tokens": 163840, + "input_cost_per_token": 5e-7, + "output_cost_per_token": 0.00000215, + "cache_read_input_token_cost": 4e-7, + "mode": "chat", + "supports_tool_choice": true, + "provider": "deepinfra" + }, + "deepinfra/deepseek-ai/DeepSeek-R1-0528-Turbo": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 0.000001, + "output_cost_per_token": 0.000003, + "mode": "chat", + "supports_tool_choice": true, + "provider": "deepinfra" + }, + "deepinfra/deepseek-ai/DeepSeek-R1-Distill-Llama-70B": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 2e-7, + "output_cost_per_token": 6e-7, + "mode": "chat", + "supports_tool_choice": false, + "provider": "deepinfra" + }, + "deepinfra/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 2.7e-7, + "output_cost_per_token": 2.7e-7, + "mode": "chat", + "supports_tool_choice": true, + "provider": "deepinfra" + }, + "deepinfra/deepseek-ai/DeepSeek-R1-Turbo": { + "max_tokens": 40960, + "max_input_tokens": 40960, + "max_output_tokens": 40960, + "input_cost_per_token": 0.000001, + "output_cost_per_token": 0.000003, + "mode": "chat", + "supports_tool_choice": true, + "provider": "deepinfra" + }, + "deepinfra/deepseek-ai/DeepSeek-V3": { + "max_tokens": 163840, + "max_input_tokens": 163840, + "max_output_tokens": 163840, + "input_cost_per_token": 3.8e-7, + "output_cost_per_token": 8.9e-7, + "mode": "chat", + "supports_tool_choice": true, + "provider": "deepinfra" + }, + "deepinfra/deepseek-ai/DeepSeek-V3-0324": { + "max_tokens": 163840, + "max_input_tokens": 163840, + "max_output_tokens": 163840, + "input_cost_per_token": 2.5e-7, + "output_cost_per_token": 8.8e-7, + "mode": "chat", + "supports_tool_choice": true, + "provider": "deepinfra" + }, + "deepinfra/deepseek-ai/DeepSeek-V3.1": { + "max_tokens": 163840, + "max_input_tokens": 163840, + "max_output_tokens": 163840, + "input_cost_per_token": 2.7e-7, + "output_cost_per_token": 0.000001, + "cache_read_input_token_cost": 2.16e-7, + "mode": "chat", + "supports_tool_choice": true, + "supports_reasoning": true, + "provider": "deepinfra" + }, + "deepinfra/deepseek-ai/DeepSeek-V3.1-Terminus": { + "max_tokens": 163840, + "max_input_tokens": 163840, + "max_output_tokens": 163840, + "input_cost_per_token": 2.7e-7, + "output_cost_per_token": 0.000001, + "cache_read_input_token_cost": 2.16e-7, + "mode": "chat", + "supports_tool_choice": true, + "provider": "deepinfra" + }, + "deepinfra/google/gemini-2.0-flash-001": { + "max_tokens": 1000000, + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "input_cost_per_token": 1e-7, + "output_cost_per_token": 4e-7, + "mode": "chat", + "supports_tool_choice": true, + "provider": "deepinfra" + }, + "deepinfra/google/gemini-2.5-flash": { + "max_tokens": 1000000, + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "input_cost_per_token": 3e-7, + "output_cost_per_token": 0.0000025, + "mode": "chat", + "supports_tool_choice": true, + "provider": "deepinfra" + }, + "deepinfra/google/gemini-2.5-pro": { + "max_tokens": 1000000, + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "input_cost_per_token": 0.00000125, + "output_cost_per_token": 0.00001, + "mode": "chat", + "supports_tool_choice": true, + "provider": "deepinfra" + }, + "deepinfra/google/gemma-3-12b-it": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 5e-8, + "output_cost_per_token": 1e-7, + "mode": "chat", + "supports_tool_choice": true, + "provider": "deepinfra" + }, + "deepinfra/google/gemma-3-27b-it": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 9e-8, + "output_cost_per_token": 1.6e-7, + "mode": "chat", + "supports_tool_choice": true, + "provider": "deepinfra" + }, + "deepinfra/google/gemma-3-4b-it": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 4e-8, + "output_cost_per_token": 8e-8, + "mode": "chat", + "supports_tool_choice": true, + "provider": "deepinfra" + }, + "deepinfra/meta-llama/Llama-3.2-11B-Vision-Instruct": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 4.9e-8, + "output_cost_per_token": 4.9e-8, + "mode": "chat", + "supports_tool_choice": false, + "provider": "deepinfra" + }, + "deepinfra/meta-llama/Llama-3.2-3B-Instruct": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 2e-8, + "output_cost_per_token": 2e-8, + "mode": "chat", + "supports_tool_choice": true, + "provider": "deepinfra" + }, + "deepinfra/meta-llama/Llama-3.3-70B-Instruct": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 2.3e-7, + "output_cost_per_token": 4e-7, + "mode": "chat", + "supports_tool_choice": true, + "provider": "deepinfra" + }, + "deepinfra/meta-llama/Llama-3.3-70B-Instruct-Turbo": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 1.3e-7, + "output_cost_per_token": 3.9e-7, + "mode": "chat", + "supports_tool_choice": true, + "provider": "deepinfra" + }, + "deepinfra/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8": { + "max_tokens": 1048576, + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "input_cost_per_token": 1.5e-7, + "output_cost_per_token": 6e-7, + "mode": "chat", + "supports_tool_choice": true, + "provider": "deepinfra" + }, + "deepinfra/meta-llama/Llama-4-Scout-17B-16E-Instruct": { + "max_tokens": 327680, + "max_input_tokens": 327680, + "max_output_tokens": 327680, + "input_cost_per_token": 8e-8, + "output_cost_per_token": 3e-7, + "mode": "chat", + "supports_tool_choice": true, + "provider": "deepinfra" + }, + "deepinfra/meta-llama/Llama-Guard-3-8B": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 5.5e-8, + "output_cost_per_token": 5.5e-8, + "mode": "chat", + "supports_tool_choice": false, + "provider": "deepinfra" + }, + "deepinfra/meta-llama/Llama-Guard-4-12B": { + "max_tokens": 163840, + "max_input_tokens": 163840, + "max_output_tokens": 163840, + "input_cost_per_token": 1.8e-7, + "output_cost_per_token": 1.8e-7, + "mode": "chat", + "supports_tool_choice": false, + "provider": "deepinfra" + }, + "deepinfra/meta-llama/Meta-Llama-3-8B-Instruct": { + "max_tokens": 8192, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "input_cost_per_token": 3e-8, + "output_cost_per_token": 6e-8, + "mode": "chat", + "supports_tool_choice": true, + "provider": "deepinfra" + }, + "deepinfra/meta-llama/Meta-Llama-3.1-70B-Instruct": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 4e-7, + "output_cost_per_token": 4e-7, + "mode": "chat", + "supports_tool_choice": true, + "provider": "deepinfra" + }, + "deepinfra/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 1e-7, + "output_cost_per_token": 2.8e-7, + "mode": "chat", + "supports_tool_choice": true, + "provider": "deepinfra" + }, + "deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 3e-8, + "output_cost_per_token": 5e-8, + "mode": "chat", + "supports_tool_choice": true, + "provider": "deepinfra" + }, + "deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 2e-8, + "output_cost_per_token": 3e-8, + "mode": "chat", + "supports_tool_choice": true, + "provider": "deepinfra" + }, + "deepinfra/microsoft/WizardLM-2-8x22B": { + "max_tokens": 65536, + "max_input_tokens": 65536, + "max_output_tokens": 65536, + "input_cost_per_token": 4.8e-7, + "output_cost_per_token": 4.8e-7, + "mode": "chat", + "supports_tool_choice": false, + "provider": "deepinfra" + }, + "deepinfra/microsoft/phi-4": { + "max_tokens": 16384, + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "input_cost_per_token": 7e-8, + "output_cost_per_token": 1.4e-7, + "mode": "chat", + "supports_tool_choice": true, + "provider": "deepinfra" + }, + "deepinfra/mistralai/Mistral-Nemo-Instruct-2407": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 2e-8, + "output_cost_per_token": 4e-8, + "mode": "chat", + "supports_tool_choice": true, + "provider": "deepinfra" + }, + "deepinfra/mistralai/Mistral-Small-24B-Instruct-2501": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 5e-8, + "output_cost_per_token": 8e-8, + "mode": "chat", + "supports_tool_choice": true, + "provider": "deepinfra" + }, + "deepinfra/mistralai/Mistral-Small-3.2-24B-Instruct-2506": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 7.5e-8, + "output_cost_per_token": 2e-7, + "mode": "chat", + "supports_tool_choice": true, + "provider": "deepinfra" + }, + "deepinfra/mistralai/Mixtral-8x7B-Instruct-v0.1": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 4e-7, + "output_cost_per_token": 4e-7, + "mode": "chat", + "supports_tool_choice": true, + "provider": "deepinfra" + }, + "deepinfra/moonshotai/Kimi-K2-Instruct": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 5e-7, + "output_cost_per_token": 0.000002, + "mode": "chat", + "supports_tool_choice": true, + "provider": "deepinfra" + }, + "deepinfra/moonshotai/Kimi-K2-Instruct-0905": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "input_cost_per_token": 5e-7, + "output_cost_per_token": 0.000002, + "cache_read_input_token_cost": 4e-7, + "mode": "chat", + "supports_tool_choice": true, + "provider": "deepinfra" + }, + "deepinfra/nvidia/Llama-3.1-Nemotron-70B-Instruct": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 6e-7, + "output_cost_per_token": 6e-7, + "mode": "chat", + "supports_tool_choice": true, + "provider": "deepinfra" + }, + "deepinfra/nvidia/Llama-3.3-Nemotron-Super-49B-v1.5": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 1e-7, + "output_cost_per_token": 4e-7, + "mode": "chat", + "supports_tool_choice": true, + "provider": "deepinfra" + }, + "deepinfra/nvidia/NVIDIA-Nemotron-Nano-9B-v2": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 4e-8, + "output_cost_per_token": 1.6e-7, + "mode": "chat", + "supports_tool_choice": true, + "provider": "deepinfra" + }, + "deepinfra/openai/gpt-oss-120b": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 5e-8, + "output_cost_per_token": 4.5e-7, + "mode": "chat", + "supports_tool_choice": true, + "provider": "deepinfra" + }, + "deepinfra/openai/gpt-oss-20b": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 4e-8, + "output_cost_per_token": 1.5e-7, + "mode": "chat", + "supports_tool_choice": true, + "provider": "deepinfra" + }, + "deepinfra/zai-org/GLM-4.5": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 4e-7, + "output_cost_per_token": 0.0000016, + "mode": "chat", + "supports_tool_choice": true, + "provider": "deepinfra" + }, + "deepseek/deepseek-chat": { + "cache_creation_input_token_cost": 0, + "cache_read_input_token_cost": 7e-8, + "input_cost_per_token": 2.7e-7, + "input_cost_per_token_cache_hit": 7e-8, + "max_input_tokens": 65536, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.0000011, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_tool_choice": true, + "provider": "deepseek" + }, + "deepseek/deepseek-coder": { + "input_cost_per_token": 1.4e-7, + "input_cost_per_token_cache_hit": 1.4e-8, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2.8e-7, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_tool_choice": true, + "provider": "deepseek" + }, + "deepseek/deepseek-r1": { + "input_cost_per_token": 5.5e-7, + "input_cost_per_token_cache_hit": 1.4e-7, + "max_input_tokens": 65536, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.00000219, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "provider": "deepseek" + }, + "deepseek/deepseek-reasoner": { + "input_cost_per_token": 5.5e-7, + "input_cost_per_token_cache_hit": 1.4e-7, + "max_input_tokens": 65536, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.00000219, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "provider": "deepseek" + }, + "deepseek/deepseek-v3": { + "cache_creation_input_token_cost": 0, + "cache_read_input_token_cost": 7e-8, + "input_cost_per_token": 2.7e-7, + "input_cost_per_token_cache_hit": 7e-8, + "max_input_tokens": 65536, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.0000011, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_tool_choice": true, + "provider": "deepseek" + }, + "deepseek.v3-v1:0": { + "input_cost_per_token": 5.8e-7, + "max_input_tokens": 163840, + "max_output_tokens": 81920, + "max_tokens": 163840, + "mode": "chat", + "output_cost_per_token": 0.00000168, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "provider": "bedrock_converse" + }, + "dolphin": { + "input_cost_per_token": 5e-7, + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "completion", + "output_cost_per_token": 5e-7, + "provider": "nlp_cloud" + }, + "doubao-embedding": { + "input_cost_per_token": 0, + "max_input_tokens": 4096, + "max_tokens": 4096, + "metadata": { + "notes": "Volcengine Doubao embedding model - standard version with 2560 dimensions" + }, + "mode": "embedding", + "output_cost_per_token": 0, + "output_vector_size": 2560, + "provider": "volcengine" + }, + "doubao-embedding-large": { + "input_cost_per_token": 0, + "max_input_tokens": 4096, + "max_tokens": 4096, + "metadata": { + "notes": "Volcengine Doubao embedding model - large version with 2048 dimensions" + }, + "mode": "embedding", + "output_cost_per_token": 0, + "output_vector_size": 2048, + "provider": "volcengine" + }, + "doubao-embedding-large-text-240915": { + "input_cost_per_token": 0, + "max_input_tokens": 4096, + "max_tokens": 4096, + "metadata": { + "notes": "Volcengine Doubao embedding model - text-240915 version with 4096 dimensions" + }, + "mode": "embedding", + "output_cost_per_token": 0, + "output_vector_size": 4096, + "provider": "volcengine" + }, + "doubao-embedding-large-text-250515": { + "input_cost_per_token": 0, + "max_input_tokens": 4096, + "max_tokens": 4096, + "metadata": { + "notes": "Volcengine Doubao embedding model - text-250515 version with 2048 dimensions" + }, + "mode": "embedding", + "output_cost_per_token": 0, + "output_vector_size": 2048, + "provider": "volcengine" + }, + "doubao-embedding-text-240715": { + "input_cost_per_token": 0, + "max_input_tokens": 4096, + "max_tokens": 4096, + "metadata": { + "notes": "Volcengine Doubao embedding model - text-240715 version with 2560 dimensions" + }, + "mode": "embedding", + "output_cost_per_token": 0, + "output_vector_size": 2560, + "provider": "volcengine" + }, + "exa_ai/search": { + "mode": "search", + "tiered_pricing": [ + { "input_cost_per_query": 0.005, "max_results_range": [0, 25] }, + { "input_cost_per_query": 0.025, "max_results_range": [26, 100] } + ], + "provider": "exa_ai" + }, + "firecrawl/search": { + "mode": "search", + "tiered_pricing": [ + { "input_cost_per_query": 0.00166, "max_results_range": [1, 10] }, + { "input_cost_per_query": 0.00332, "max_results_range": [11, 20] }, + { "input_cost_per_query": 0.00498, "max_results_range": [21, 30] }, + { "input_cost_per_query": 0.00664, "max_results_range": [31, 40] }, + { "input_cost_per_query": 0.0083, "max_results_range": [41, 50] }, + { "input_cost_per_query": 0.00996, "max_results_range": [51, 60] }, + { "input_cost_per_query": 0.01162, "max_results_range": [61, 70] }, + { "input_cost_per_query": 0.01328, "max_results_range": [71, 80] }, + { "input_cost_per_query": 0.01494, "max_results_range": [81, 90] }, + { "input_cost_per_query": 0.0166, "max_results_range": [91, 100] } + ], + "metadata": { + "notes": "Firecrawl search pricing: $83 for 100,000 credits, 2 credits per 10 results. Cost = ceiling(limit/10) * 2 * $0.00083" + }, + "provider": "firecrawl" + }, + "perplexity/search": { + "input_cost_per_query": 0.005, + "mode": "search", + "provider": "perplexity" + }, + "searxng/search": { + "mode": "search", + "input_cost_per_query": 0, + "metadata": { + "notes": "SearXNG is an open-source metasearch engine. Free to use when self-hosted or using public instances." + }, + "provider": "searxng" + }, + "elevenlabs/scribe_v1": { + "input_cost_per_second": 0.0000611, + "metadata": { + "calculation": "$0.22/hour = $0.00366/minute = $0.0000611 per second (enterprise pricing)", + "notes": "ElevenLabs Scribe v1 - state-of-the-art speech recognition model with 99 language support", + "original_pricing_per_hour": 0.22 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0, + "source": "https://elevenlabs.io/pricing", + "supported_endpoints": ["/v1/audio/transcriptions"], + "provider": "elevenlabs" + }, + "elevenlabs/scribe_v1_experimental": { + "input_cost_per_second": 0.0000611, + "metadata": { + "calculation": "$0.22/hour = $0.00366/minute = $0.0000611 per second (enterprise pricing)", + "notes": "ElevenLabs Scribe v1 experimental - enhanced version of the main Scribe model", + "original_pricing_per_hour": 0.22 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0, + "source": "https://elevenlabs.io/pricing", + "supported_endpoints": ["/v1/audio/transcriptions"], + "provider": "elevenlabs" + }, + "embed-english-light-v2.0": { + "input_cost_per_token": 1e-7, + "max_input_tokens": 1024, + "max_tokens": 1024, + "mode": "embedding", + "output_cost_per_token": 0, + "provider": "cohere" + }, + "embed-english-light-v3.0": { + "input_cost_per_token": 1e-7, + "max_input_tokens": 1024, + "max_tokens": 1024, + "mode": "embedding", + "output_cost_per_token": 0, + "provider": "cohere" + }, + "embed-english-v2.0": { + "input_cost_per_token": 1e-7, + "max_input_tokens": 4096, + "max_tokens": 4096, + "mode": "embedding", + "output_cost_per_token": 0, + "provider": "cohere" + }, + "embed-english-v3.0": { + "input_cost_per_image": 0.0001, + "input_cost_per_token": 1e-7, + "max_input_tokens": 1024, + "max_tokens": 1024, + "metadata": { + "notes": "'supports_image_input' is a deprecated field. Use 'supports_embedding_image_input' instead." + }, + "mode": "embedding", + "output_cost_per_token": 0, + "supports_embedding_image_input": true, + "supports_image_input": true, + "provider": "cohere" + }, + "embed-multilingual-v2.0": { + "input_cost_per_token": 1e-7, + "max_input_tokens": 768, + "max_tokens": 768, + "mode": "embedding", + "output_cost_per_token": 0, + "provider": "cohere" + }, + "embed-multilingual-v3.0": { + "input_cost_per_token": 1e-7, + "max_input_tokens": 1024, + "max_tokens": 1024, + "mode": "embedding", + "output_cost_per_token": 0, + "supports_embedding_image_input": true, + "provider": "cohere" + }, + "eu.amazon.nova-lite-v1:0": { + "input_cost_per_token": 7.8e-8, + "max_input_tokens": 300000, + "max_output_tokens": 10000, + "max_tokens": 10000, + "mode": "chat", + "output_cost_per_token": 3.12e-7, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_vision": true, + "provider": "bedrock_converse" + }, + "eu.amazon.nova-micro-v1:0": { + "input_cost_per_token": 4.6e-8, + "max_input_tokens": 128000, + "max_output_tokens": 10000, + "max_tokens": 10000, + "mode": "chat", + "output_cost_per_token": 1.84e-7, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "provider": "bedrock_converse" + }, + "eu.amazon.nova-pro-v1:0": { + "input_cost_per_token": 0.00000105, + "max_input_tokens": 300000, + "max_output_tokens": 10000, + "max_tokens": 10000, + "mode": "chat", + "output_cost_per_token": 0.0000042, + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_vision": true, + "provider": "bedrock_converse" + }, + "eu.anthropic.claude-3-5-haiku-20241022-v1:0": { + "input_cost_per_token": 2.5e-7, + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.00000125, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "provider": "bedrock" + }, + "eu.anthropic.claude-haiku-4-5-20251001-v1:0": { + "cache_creation_input_token_cost": 0.000001375, + "cache_read_input_token_cost": 1.1e-7, + "input_cost_per_token": 0.0000011, + "deprecation_date": "2026-10-15", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 0.0000055, + "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock", + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 346, + "provider": "bedrock_converse" + }, + "eu.anthropic.claude-3-5-sonnet-20240620-v1:0": { + "input_cost_per_token": 0.000003, + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.000015, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "bedrock" + }, + "eu.anthropic.claude-3-5-sonnet-20241022-v2:0": { + "input_cost_per_token": 0.000003, + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.000015, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "bedrock" + }, + "eu.anthropic.claude-3-7-sonnet-20250219-v1:0": { + "input_cost_per_token": 0.000003, + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.000015, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "bedrock" + }, + "eu.anthropic.claude-3-haiku-20240307-v1:0": { + "input_cost_per_token": 2.5e-7, + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.00000125, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "bedrock" + }, + "eu.anthropic.claude-3-opus-20240229-v1:0": { + "input_cost_per_token": 0.000015, + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.000075, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "bedrock" + }, + "eu.anthropic.claude-3-sonnet-20240229-v1:0": { + "input_cost_per_token": 0.000003, + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.000015, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "bedrock" + }, + "eu.anthropic.claude-opus-4-1-20250805-v1:0": { + "cache_creation_input_token_cost": 0.00001875, + "cache_read_input_token_cost": 0.0000015, + "input_cost_per_token": 0.000015, + "max_input_tokens": 200000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 0.000075, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159, + "provider": "bedrock_converse" + }, + "eu.anthropic.claude-opus-4-20250514-v1:0": { + "cache_creation_input_token_cost": 0.00001875, + "cache_read_input_token_cost": 0.0000015, + "input_cost_per_token": 0.000015, + "max_input_tokens": 200000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 0.000075, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159, + "provider": "bedrock_converse" + }, + "eu.anthropic.claude-sonnet-4-20250514-v1:0": { + "cache_creation_input_token_cost": 0.00000375, + "cache_read_input_token_cost": 3e-7, + "input_cost_per_token": 0.000003, + "input_cost_per_token_above_200k_tokens": 0.000006, + "output_cost_per_token_above_200k_tokens": 0.0000225, + "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, + "cache_read_input_token_cost_above_200k_tokens": 6e-7, + "max_input_tokens": 1000000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 0.000015, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159, + "provider": "bedrock_converse" + }, + "eu.anthropic.claude-sonnet-4-5-20250929-v1:0": { + "cache_creation_input_token_cost": 0.000004125, + "cache_read_input_token_cost": 3.3e-7, + "input_cost_per_token": 0.0000033, + "input_cost_per_token_above_200k_tokens": 0.0000066, + "output_cost_per_token_above_200k_tokens": 0.00002475, + "cache_creation_input_token_cost_above_200k_tokens": 0.00000825, + "cache_read_input_token_cost_above_200k_tokens": 6.6e-7, + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 0.0000165, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 346, + "provider": "bedrock_converse" + }, + "eu.meta.llama3-2-1b-instruct-v1:0": { + "input_cost_per_token": 1.3e-7, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.3e-7, + "supports_function_calling": true, + "supports_tool_choice": false, + "provider": "bedrock" + }, + "eu.meta.llama3-2-3b-instruct-v1:0": { + "input_cost_per_token": 1.9e-7, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.9e-7, + "supports_function_calling": true, + "supports_tool_choice": false, + "provider": "bedrock" + }, + "eu.mistral.pixtral-large-2502-v1:0": { + "input_cost_per_token": 0.000002, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.000006, + "supports_function_calling": true, + "supports_tool_choice": false, + "provider": "bedrock_converse" + }, + "fal_ai/bria/text-to-image/3.2": { + "mode": "image_generation", + "output_cost_per_image": 0.0398, + "supported_endpoints": ["/v1/images/generations"], + "provider": "fal_ai" + }, + "fal_ai/fal-ai/flux-pro/v1.1": { + "mode": "image_generation", + "output_cost_per_image": 0.04, + "supported_endpoints": ["/v1/images/generations"], + "provider": "fal_ai" + }, + "fal_ai/fal-ai/flux-pro/v1.1-ultra": { + "mode": "image_generation", + "output_cost_per_image": 0.06, + "supported_endpoints": ["/v1/images/generations"], + "provider": "fal_ai" + }, + "fal_ai/fal-ai/flux/schnell": { + "mode": "image_generation", + "output_cost_per_image": 0.003, + "supported_endpoints": ["/v1/images/generations"], + "provider": "fal_ai" + }, + "fal_ai/fal-ai/bytedance/seedream/v3/text-to-image": { + "mode": "image_generation", + "output_cost_per_image": 0.03, + "supported_endpoints": ["/v1/images/generations"], + "provider": "fal_ai" + }, + "fal_ai/fal-ai/bytedance/dreamina/v3.1/text-to-image": { + "mode": "image_generation", + "output_cost_per_image": 0.03, + "supported_endpoints": ["/v1/images/generations"], + "provider": "fal_ai" + }, + "fal_ai/fal-ai/ideogram/v3": { + "mode": "image_generation", + "output_cost_per_image": 0.06, + "supported_endpoints": ["/v1/images/generations"], + "provider": "fal_ai" + }, + "fal_ai/fal-ai/imagen4/preview": { + "mode": "image_generation", + "output_cost_per_image": 0.0398, + "supported_endpoints": ["/v1/images/generations"], + "provider": "fal_ai" + }, + "fal_ai/fal-ai/imagen4/preview/fast": { + "mode": "image_generation", + "output_cost_per_image": 0.02, + "supported_endpoints": ["/v1/images/generations"], + "provider": "fal_ai" + }, + "fal_ai/fal-ai/imagen4/preview/ultra": { + "mode": "image_generation", + "output_cost_per_image": 0.06, + "supported_endpoints": ["/v1/images/generations"], + "provider": "fal_ai" + }, + "fal_ai/fal-ai/recraft/v3/text-to-image": { + "mode": "image_generation", + "output_cost_per_image": 0.0398, + "supported_endpoints": ["/v1/images/generations"], + "provider": "fal_ai" + }, + "fal_ai/fal-ai/stable-diffusion-v35-medium": { + "mode": "image_generation", + "output_cost_per_image": 0.0398, + "supported_endpoints": ["/v1/images/generations"], + "provider": "fal_ai" + }, + "featherless_ai/featherless-ai/Qwerky-72B": { + "max_input_tokens": 32768, + "max_output_tokens": 4096, + "max_tokens": 32768, + "mode": "chat", + "provider": "featherless_ai" + }, + "featherless_ai/featherless-ai/Qwerky-QwQ-32B": { + "max_input_tokens": 32768, + "max_output_tokens": 4096, + "max_tokens": 32768, + "mode": "chat", + "provider": "featherless_ai" + }, + "fireworks-ai-4.1b-to-16b": { + "input_cost_per_token": 2e-7, + "output_cost_per_token": 2e-7, + "provider": "fireworks_ai" + }, + "fireworks-ai-56b-to-176b": { + "input_cost_per_token": 0.0000012, + "output_cost_per_token": 0.0000012, + "provider": "fireworks_ai" + }, + "fireworks-ai-above-16b": { + "input_cost_per_token": 9e-7, + "output_cost_per_token": 9e-7, + "provider": "fireworks_ai" + }, + "fireworks-ai-default": { + "input_cost_per_token": 0, + "output_cost_per_token": 0, + "provider": "fireworks_ai" + }, + "fireworks-ai-embedding-150m-to-350m": { + "input_cost_per_token": 1.6e-8, + "output_cost_per_token": 0, + "provider": "fireworks_ai-embedding-models" + }, + "fireworks-ai-embedding-up-to-150m": { + "input_cost_per_token": 8e-9, + "output_cost_per_token": 0, + "provider": "fireworks_ai-embedding-models" + }, + "fireworks-ai-moe-up-to-56b": { + "input_cost_per_token": 5e-7, + "output_cost_per_token": 5e-7, + "provider": "fireworks_ai" + }, + "fireworks-ai-up-to-4b": { + "input_cost_per_token": 2e-7, + "output_cost_per_token": 2e-7, + "provider": "fireworks_ai" + }, + "fireworks_ai/WhereIsAI/UAE-Large-V1": { + "input_cost_per_token": 1.6e-8, + "max_input_tokens": 512, + "max_tokens": 512, + "mode": "embedding", + "output_cost_per_token": 0, + "source": "https://fireworks.ai/pricing", + "provider": "fireworks_ai-embedding-models" + }, + "fireworks_ai/accounts/fireworks/models/deepseek-coder-v2-instruct": { + "input_cost_per_token": 0.0000012, + "max_input_tokens": 65536, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 0.0000012, + "source": "https://fireworks.ai/pricing", + "supports_function_calling": false, + "supports_response_schema": true, + "supports_tool_choice": false, + "provider": "fireworks_ai" + }, + "fireworks_ai/accounts/fireworks/models/deepseek-r1": { + "input_cost_per_token": 0.000003, + "max_input_tokens": 128000, + "max_output_tokens": 20480, + "max_tokens": 20480, + "mode": "chat", + "output_cost_per_token": 0.000008, + "source": "https://fireworks.ai/pricing", + "supports_response_schema": true, + "supports_tool_choice": false, + "provider": "fireworks_ai" + }, + "fireworks_ai/accounts/fireworks/models/deepseek-r1-0528": { + "input_cost_per_token": 0.000003, + "max_input_tokens": 160000, + "max_output_tokens": 160000, + "max_tokens": 160000, + "mode": "chat", + "output_cost_per_token": 0.000008, + "source": "https://fireworks.ai/pricing", + "supports_response_schema": true, + "supports_tool_choice": false, + "provider": "fireworks_ai" + }, + "fireworks_ai/accounts/fireworks/models/deepseek-r1-basic": { + "input_cost_per_token": 5.5e-7, + "max_input_tokens": 128000, + "max_output_tokens": 20480, + "max_tokens": 20480, + "mode": "chat", + "output_cost_per_token": 0.00000219, + "source": "https://fireworks.ai/pricing", + "supports_response_schema": true, + "supports_tool_choice": false, + "provider": "fireworks_ai" + }, + "fireworks_ai/accounts/fireworks/models/deepseek-v3": { + "input_cost_per_token": 9e-7, + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 9e-7, + "source": "https://fireworks.ai/pricing", + "supports_response_schema": true, + "supports_tool_choice": false, + "provider": "fireworks_ai" + }, + "fireworks_ai/accounts/fireworks/models/deepseek-v3-0324": { + "input_cost_per_token": 9e-7, + "max_input_tokens": 163840, + "max_output_tokens": 163840, + "max_tokens": 163840, + "mode": "chat", + "output_cost_per_token": 9e-7, + "source": "https://fireworks.ai/models/fireworks/deepseek-v3-0324", + "supports_response_schema": true, + "supports_tool_choice": false, + "provider": "fireworks_ai" + }, + "fireworks_ai/accounts/fireworks/models/deepseek-v3p1": { + "input_cost_per_token": 5.6e-7, + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.00000168, + "source": "https://fireworks.ai/pricing", + "supports_response_schema": true, + "supports_tool_choice": true, + "provider": "fireworks_ai" + }, + "fireworks_ai/accounts/fireworks/models/deepseek-v3p1-terminus": { + "input_cost_per_token": 5.6e-7, + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.00000168, + "source": "https://fireworks.ai/pricing", + "supports_response_schema": true, + "supports_tool_choice": true, + "provider": "fireworks_ai" + }, + "fireworks_ai/accounts/fireworks/models/firefunction-v2": { + "input_cost_per_token": 9e-7, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 9e-7, + "source": "https://fireworks.ai/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "provider": "fireworks_ai" + }, + "fireworks_ai/accounts/fireworks/models/glm-4p5": { + "input_cost_per_token": 5.5e-7, + "max_input_tokens": 128000, + "max_output_tokens": 96000, + "max_tokens": 96000, + "mode": "chat", + "output_cost_per_token": 0.00000219, + "source": "https://fireworks.ai/models/fireworks/glm-4p5", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "provider": "fireworks_ai" + }, + "fireworks_ai/accounts/fireworks/models/glm-4p5-air": { + "input_cost_per_token": 2.2e-7, + "max_input_tokens": 128000, + "max_output_tokens": 96000, + "max_tokens": 96000, + "mode": "chat", + "output_cost_per_token": 8.8e-7, + "source": "https://artificialanalysis.ai/models/glm-4-5-air", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "provider": "fireworks_ai" + }, + "fireworks_ai/accounts/fireworks/models/gpt-oss-120b": { + "input_cost_per_token": 1.5e-7, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 6e-7, + "source": "https://fireworks.ai/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "provider": "fireworks_ai" + }, + "fireworks_ai/accounts/fireworks/models/gpt-oss-20b": { + "input_cost_per_token": 5e-8, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2e-7, + "source": "https://fireworks.ai/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "provider": "fireworks_ai" + }, + "fireworks_ai/accounts/fireworks/models/kimi-k2-instruct": { + "input_cost_per_token": 6e-7, + "max_input_tokens": 131072, + "max_output_tokens": 16384, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 0.0000025, + "source": "https://fireworks.ai/models/fireworks/kimi-k2-instruct", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "provider": "fireworks_ai" + }, + "fireworks_ai/accounts/fireworks/models/kimi-k2-thinking": { + "input_cost_per_token": 6e-7, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 0.0000025, + "source": "https://fireworks.ai/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_web_search": true, + "provider": "fireworks_ai" + }, + "fireworks_ai/accounts/fireworks/models/llama-v3p1-405b-instruct": { + "input_cost_per_token": 0.000003, + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 0.000003, + "source": "https://fireworks.ai/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "provider": "fireworks_ai" + }, + "fireworks_ai/accounts/fireworks/models/llama-v3p1-8b-instruct": { + "input_cost_per_token": 1e-7, + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1e-7, + "source": "https://fireworks.ai/pricing", + "supports_function_calling": false, + "supports_response_schema": true, + "supports_tool_choice": false, + "provider": "fireworks_ai" + }, + "fireworks_ai/accounts/fireworks/models/llama-v3p2-11b-vision-instruct": { + "input_cost_per_token": 2e-7, + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 2e-7, + "source": "https://fireworks.ai/pricing", + "supports_function_calling": false, + "supports_response_schema": true, + "supports_tool_choice": false, + "supports_vision": true, + "provider": "fireworks_ai" + }, + "fireworks_ai/accounts/fireworks/models/llama-v3p2-1b-instruct": { + "input_cost_per_token": 1e-7, + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1e-7, + "source": "https://fireworks.ai/pricing", + "supports_function_calling": false, + "supports_response_schema": true, + "supports_tool_choice": false, + "provider": "fireworks_ai" + }, + "fireworks_ai/accounts/fireworks/models/llama-v3p2-3b-instruct": { + "input_cost_per_token": 1e-7, + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1e-7, + "source": "https://fireworks.ai/pricing", + "supports_function_calling": false, + "supports_response_schema": true, + "supports_tool_choice": false, + "provider": "fireworks_ai" + }, + "fireworks_ai/accounts/fireworks/models/llama-v3p2-90b-vision-instruct": { + "input_cost_per_token": 9e-7, + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 9e-7, + "source": "https://fireworks.ai/pricing", + "supports_response_schema": true, + "supports_tool_choice": false, + "supports_vision": true, + "provider": "fireworks_ai" + }, + "fireworks_ai/accounts/fireworks/models/llama4-maverick-instruct-basic": { + "input_cost_per_token": 2.2e-7, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 8.8e-7, + "source": "https://fireworks.ai/pricing", + "supports_response_schema": true, + "supports_tool_choice": false, + "provider": "fireworks_ai" + }, + "fireworks_ai/accounts/fireworks/models/llama4-scout-instruct-basic": { + "input_cost_per_token": 1.5e-7, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 6e-7, + "source": "https://fireworks.ai/pricing", + "supports_response_schema": true, + "supports_tool_choice": false, + "provider": "fireworks_ai" + }, + "fireworks_ai/accounts/fireworks/models/mixtral-8x22b-instruct-hf": { + "input_cost_per_token": 0.0000012, + "max_input_tokens": 65536, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 0.0000012, + "source": "https://fireworks.ai/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "provider": "fireworks_ai" + }, + "fireworks_ai/accounts/fireworks/models/qwen2-72b-instruct": { + "input_cost_per_token": 9e-7, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 9e-7, + "source": "https://fireworks.ai/pricing", + "supports_function_calling": false, + "supports_response_schema": true, + "supports_tool_choice": false, + "provider": "fireworks_ai" + }, + "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b-instruct": { + "input_cost_per_token": 9e-7, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 9e-7, + "source": "https://fireworks.ai/pricing", + "supports_function_calling": false, + "supports_response_schema": true, + "supports_tool_choice": false, + "provider": "fireworks_ai" + }, + "fireworks_ai/accounts/fireworks/models/yi-large": { + "input_cost_per_token": 0.000003, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0.000003, + "source": "https://fireworks.ai/pricing", + "supports_function_calling": false, + "supports_response_schema": true, + "supports_tool_choice": false, + "provider": "fireworks_ai" + }, + "fireworks_ai/nomic-ai/nomic-embed-text-v1": { + "input_cost_per_token": 8e-9, + "max_input_tokens": 8192, + "max_tokens": 8192, + "mode": "embedding", + "output_cost_per_token": 0, + "source": "https://fireworks.ai/pricing", + "provider": "fireworks_ai-embedding-models" + }, + "fireworks_ai/nomic-ai/nomic-embed-text-v1.5": { + "input_cost_per_token": 8e-9, + "max_input_tokens": 8192, + "max_tokens": 8192, + "mode": "embedding", + "output_cost_per_token": 0, + "source": "https://fireworks.ai/pricing", + "provider": "fireworks_ai-embedding-models" + }, + "fireworks_ai/thenlper/gte-base": { + "input_cost_per_token": 8e-9, + "max_input_tokens": 512, + "max_tokens": 512, + "mode": "embedding", + "output_cost_per_token": 0, + "source": "https://fireworks.ai/pricing", + "provider": "fireworks_ai-embedding-models" + }, + "fireworks_ai/thenlper/gte-large": { + "input_cost_per_token": 1.6e-8, + "max_input_tokens": 512, + "max_tokens": 512, + "mode": "embedding", + "output_cost_per_token": 0, + "source": "https://fireworks.ai/pricing", + "provider": "fireworks_ai-embedding-models" + }, + "friendliai/meta-llama-3.1-70b-instruct": { + "input_cost_per_token": 6e-7, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 6e-7, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "friendliai" + }, + "friendliai/meta-llama-3.1-8b-instruct": { + "input_cost_per_token": 1e-7, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1e-7, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "friendliai" + }, + "ft:babbage-002": { + "input_cost_per_token": 4e-7, + "input_cost_per_token_batches": 2e-7, + "max_input_tokens": 16384, + "max_output_tokens": 4096, + "max_tokens": 16384, + "mode": "completion", + "output_cost_per_token": 4e-7, + "output_cost_per_token_batches": 2e-7, + "provider": "text-completion-openai" + }, + "ft:davinci-002": { + "input_cost_per_token": 0.000002, + "input_cost_per_token_batches": 0.000001, + "max_input_tokens": 16384, + "max_output_tokens": 4096, + "max_tokens": 16384, + "mode": "completion", + "output_cost_per_token": 0.000002, + "output_cost_per_token_batches": 0.000001, + "provider": "text-completion-openai" + }, + "ft:gpt-3.5-turbo": { + "input_cost_per_token": 0.000003, + "input_cost_per_token_batches": 0.0000015, + "max_input_tokens": 16385, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.000006, + "output_cost_per_token_batches": 0.000003, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "openai" + }, + "ft:gpt-3.5-turbo-0125": { + "input_cost_per_token": 0.000003, + "max_input_tokens": 16385, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.000006, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "openai" + }, + "ft:gpt-3.5-turbo-0613": { + "input_cost_per_token": 0.000003, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.000006, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "openai" + }, + "ft:gpt-3.5-turbo-1106": { + "input_cost_per_token": 0.000003, + "max_input_tokens": 16385, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.000006, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "openai" + }, + "ft:gpt-4-0613": { + "input_cost_per_token": 0.00003, + "max_input_tokens": 8192, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.00006, + "source": "OpenAI needs to add pricing for this ft model, will be updated when added by OpenAI. Defaulting to base model pricing", + "supports_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "openai" + }, + "ft:gpt-4o-2024-08-06": { + "input_cost_per_token": 0.00000375, + "input_cost_per_token_batches": 0.000001875, + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 0.000015, + "output_cost_per_token_batches": 0.0000075, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "openai" + }, + "ft:gpt-4o-2024-11-20": { + "cache_creation_input_token_cost": 0.000001875, + "input_cost_per_token": 0.00000375, + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 0.000015, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "openai" + }, + "ft:gpt-4o-mini-2024-07-18": { + "cache_read_input_token_cost": 1.5e-7, + "input_cost_per_token": 3e-7, + "input_cost_per_token_batches": 1.5e-7, + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 0.0000012, + "output_cost_per_token_batches": 6e-7, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "openai" + }, + "gemini-1.0-pro": { + "input_cost_per_character": 1.25e-7, + "input_cost_per_image": 0.0025, + "input_cost_per_token": 5e-7, + "input_cost_per_video_per_second": 0.002, + "max_input_tokens": 32760, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_character": 3.75e-7, + "output_cost_per_token": 0.0000015, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#google_models", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "provider": "vertex_ai-language-models" + }, + "gemini-1.0-pro-001": { + "deprecation_date": "2025-04-09", + "input_cost_per_character": 1.25e-7, + "input_cost_per_image": 0.0025, + "input_cost_per_token": 5e-7, + "input_cost_per_video_per_second": 0.002, + "max_input_tokens": 32760, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_character": 3.75e-7, + "output_cost_per_token": 0.0000015, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "provider": "vertex_ai-language-models" + }, + "gemini-1.0-pro-002": { + "deprecation_date": "2025-04-09", + "input_cost_per_character": 1.25e-7, + "input_cost_per_image": 0.0025, + "input_cost_per_token": 5e-7, + "input_cost_per_video_per_second": 0.002, + "max_input_tokens": 32760, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_character": 3.75e-7, + "output_cost_per_token": 0.0000015, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "provider": "vertex_ai-language-models" + }, + "gemini-1.0-pro-vision": { + "input_cost_per_image": 0.0025, + "input_cost_per_token": 5e-7, + "max_images_per_prompt": 16, + "max_input_tokens": 16384, + "max_output_tokens": 2048, + "max_tokens": 2048, + "max_video_length": 2, + "max_videos_per_prompt": 1, + "mode": "chat", + "output_cost_per_token": 0.0000015, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "vertex_ai-vision-models" + }, + "gemini-1.0-pro-vision-001": { + "deprecation_date": "2025-04-09", + "input_cost_per_image": 0.0025, + "input_cost_per_token": 5e-7, + "max_images_per_prompt": 16, + "max_input_tokens": 16384, + "max_output_tokens": 2048, + "max_tokens": 2048, + "max_video_length": 2, + "max_videos_per_prompt": 1, + "mode": "chat", + "output_cost_per_token": 0.0000015, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "vertex_ai-vision-models" + }, + "gemini-1.0-ultra": { + "input_cost_per_character": 1.25e-7, + "input_cost_per_image": 0.0025, + "input_cost_per_token": 5e-7, + "input_cost_per_video_per_second": 0.002, + "max_input_tokens": 8192, + "max_output_tokens": 2048, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_character": 3.75e-7, + "output_cost_per_token": 0.0000015, + "source": "As of Jun, 2024. There is no available doc on vertex ai pricing gemini-1.0-ultra-001. Using gemini-1.0-pro pricing. Got max_tokens info here: https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "provider": "vertex_ai-language-models" + }, + "gemini-1.0-ultra-001": { + "input_cost_per_character": 1.25e-7, + "input_cost_per_image": 0.0025, + "input_cost_per_token": 5e-7, + "input_cost_per_video_per_second": 0.002, + "max_input_tokens": 8192, + "max_output_tokens": 2048, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_character": 3.75e-7, + "output_cost_per_token": 0.0000015, + "source": "As of Jun, 2024. There is no available doc on vertex ai pricing gemini-1.0-ultra-001. Using gemini-1.0-pro pricing. Got max_tokens info here: https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "provider": "vertex_ai-language-models" + }, + "gemini-1.5-flash": { + "input_cost_per_audio_per_second": 0.000002, + "input_cost_per_audio_per_second_above_128k_tokens": 0.000004, + "input_cost_per_character": 1.875e-8, + "input_cost_per_character_above_128k_tokens": 2.5e-7, + "input_cost_per_image": 0.00002, + "input_cost_per_image_above_128k_tokens": 0.00004, + "input_cost_per_token": 7.5e-8, + "input_cost_per_token_above_128k_tokens": 0.000001, + "input_cost_per_video_per_second": 0.00002, + "input_cost_per_video_per_second_above_128k_tokens": 0.00004, + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1000000, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_character": 7.5e-8, + "output_cost_per_character_above_128k_tokens": 1.5e-7, + "output_cost_per_token": 3e-7, + "output_cost_per_token_above_128k_tokens": 6e-7, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "vertex_ai-language-models" + }, + "gemini-1.5-flash-001": { + "deprecation_date": "2025-05-24", + "input_cost_per_audio_per_second": 0.000002, + "input_cost_per_audio_per_second_above_128k_tokens": 0.000004, + "input_cost_per_character": 1.875e-8, + "input_cost_per_character_above_128k_tokens": 2.5e-7, + "input_cost_per_image": 0.00002, + "input_cost_per_image_above_128k_tokens": 0.00004, + "input_cost_per_token": 7.5e-8, + "input_cost_per_token_above_128k_tokens": 0.000001, + "input_cost_per_video_per_second": 0.00002, + "input_cost_per_video_per_second_above_128k_tokens": 0.00004, + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1000000, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_character": 7.5e-8, + "output_cost_per_character_above_128k_tokens": 1.5e-7, + "output_cost_per_token": 3e-7, + "output_cost_per_token_above_128k_tokens": 6e-7, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "vertex_ai-language-models" + }, + "gemini-1.5-flash-002": { + "deprecation_date": "2025-09-24", + "input_cost_per_audio_per_second": 0.000002, + "input_cost_per_audio_per_second_above_128k_tokens": 0.000004, + "input_cost_per_character": 1.875e-8, + "input_cost_per_character_above_128k_tokens": 2.5e-7, + "input_cost_per_image": 0.00002, + "input_cost_per_image_above_128k_tokens": 0.00004, + "input_cost_per_token": 7.5e-8, + "input_cost_per_token_above_128k_tokens": 0.000001, + "input_cost_per_video_per_second": 0.00002, + "input_cost_per_video_per_second_above_128k_tokens": 0.00004, + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_character": 7.5e-8, + "output_cost_per_character_above_128k_tokens": 1.5e-7, + "output_cost_per_token": 3e-7, + "output_cost_per_token_above_128k_tokens": 6e-7, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-1.5-flash", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "vertex_ai-language-models" + }, + "gemini-1.5-flash-exp-0827": { + "input_cost_per_audio_per_second": 0.000002, + "input_cost_per_audio_per_second_above_128k_tokens": 0.000004, + "input_cost_per_character": 1.875e-8, + "input_cost_per_character_above_128k_tokens": 2.5e-7, + "input_cost_per_image": 0.00002, + "input_cost_per_image_above_128k_tokens": 0.00004, + "input_cost_per_token": 4.688e-9, + "input_cost_per_token_above_128k_tokens": 0.000001, + "input_cost_per_video_per_second": 0.00002, + "input_cost_per_video_per_second_above_128k_tokens": 0.00004, + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1000000, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_character": 1.875e-8, + "output_cost_per_character_above_128k_tokens": 3.75e-8, + "output_cost_per_token": 4.6875e-9, + "output_cost_per_token_above_128k_tokens": 9.375e-9, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "vertex_ai-language-models" + }, + "gemini-1.5-flash-preview-0514": { + "input_cost_per_audio_per_second": 0.000002, + "input_cost_per_audio_per_second_above_128k_tokens": 0.000004, + "input_cost_per_character": 1.875e-8, + "input_cost_per_character_above_128k_tokens": 2.5e-7, + "input_cost_per_image": 0.00002, + "input_cost_per_image_above_128k_tokens": 0.00004, + "input_cost_per_token": 7.5e-8, + "input_cost_per_token_above_128k_tokens": 0.000001, + "input_cost_per_video_per_second": 0.00002, + "input_cost_per_video_per_second_above_128k_tokens": 0.00004, + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1000000, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_character": 1.875e-8, + "output_cost_per_character_above_128k_tokens": 3.75e-8, + "output_cost_per_token": 4.6875e-9, + "output_cost_per_token_above_128k_tokens": 9.375e-9, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "vertex_ai-language-models" + }, + "gemini-1.5-pro": { + "input_cost_per_audio_per_second": 0.00003125, + "input_cost_per_audio_per_second_above_128k_tokens": 0.0000625, + "input_cost_per_character": 3.125e-7, + "input_cost_per_character_above_128k_tokens": 6.25e-7, + "input_cost_per_image": 0.00032875, + "input_cost_per_image_above_128k_tokens": 0.0006575, + "input_cost_per_token": 0.00000125, + "input_cost_per_token_above_128k_tokens": 0.0000025, + "input_cost_per_video_per_second": 0.00032875, + "input_cost_per_video_per_second_above_128k_tokens": 0.0006575, + "max_input_tokens": 2097152, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_character": 0.00000125, + "output_cost_per_character_above_128k_tokens": 0.0000025, + "output_cost_per_token": 0.000005, + "output_cost_per_token_above_128k_tokens": 0.00001, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "vertex_ai-language-models" + }, + "gemini-1.5-pro-001": { + "deprecation_date": "2025-05-24", + "input_cost_per_audio_per_second": 0.00003125, + "input_cost_per_audio_per_second_above_128k_tokens": 0.0000625, + "input_cost_per_character": 3.125e-7, + "input_cost_per_character_above_128k_tokens": 6.25e-7, + "input_cost_per_image": 0.00032875, + "input_cost_per_image_above_128k_tokens": 0.0006575, + "input_cost_per_token": 0.00000125, + "input_cost_per_token_above_128k_tokens": 0.0000025, + "input_cost_per_video_per_second": 0.00032875, + "input_cost_per_video_per_second_above_128k_tokens": 0.0006575, + "max_input_tokens": 1000000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_character": 0.00000125, + "output_cost_per_character_above_128k_tokens": 0.0000025, + "output_cost_per_token": 0.000005, + "output_cost_per_token_above_128k_tokens": 0.00001, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "vertex_ai-language-models" + }, + "gemini-1.5-pro-002": { + "deprecation_date": "2025-09-24", + "input_cost_per_audio_per_second": 0.00003125, + "input_cost_per_audio_per_second_above_128k_tokens": 0.0000625, + "input_cost_per_character": 3.125e-7, + "input_cost_per_character_above_128k_tokens": 6.25e-7, + "input_cost_per_image": 0.00032875, + "input_cost_per_image_above_128k_tokens": 0.0006575, + "input_cost_per_token": 0.00000125, + "input_cost_per_token_above_128k_tokens": 0.0000025, + "input_cost_per_video_per_second": 0.00032875, + "input_cost_per_video_per_second_above_128k_tokens": 0.0006575, + "max_input_tokens": 2097152, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_character": 0.00000125, + "output_cost_per_character_above_128k_tokens": 0.0000025, + "output_cost_per_token": 0.000005, + "output_cost_per_token_above_128k_tokens": 0.00001, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-1.5-pro", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "vertex_ai-language-models" + }, + "gemini-1.5-pro-preview-0215": { + "input_cost_per_audio_per_second": 0.00003125, + "input_cost_per_audio_per_second_above_128k_tokens": 0.0000625, + "input_cost_per_character": 3.125e-7, + "input_cost_per_character_above_128k_tokens": 6.25e-7, + "input_cost_per_image": 0.00032875, + "input_cost_per_image_above_128k_tokens": 0.0006575, + "input_cost_per_token": 7.8125e-8, + "input_cost_per_token_above_128k_tokens": 1.5625e-7, + "input_cost_per_video_per_second": 0.00032875, + "input_cost_per_video_per_second_above_128k_tokens": 0.0006575, + "max_input_tokens": 1000000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_character": 0.00000125, + "output_cost_per_character_above_128k_tokens": 0.0000025, + "output_cost_per_token": 3.125e-7, + "output_cost_per_token_above_128k_tokens": 6.25e-7, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "vertex_ai-language-models" + }, + "gemini-1.5-pro-preview-0409": { + "input_cost_per_audio_per_second": 0.00003125, + "input_cost_per_audio_per_second_above_128k_tokens": 0.0000625, + "input_cost_per_character": 3.125e-7, + "input_cost_per_character_above_128k_tokens": 6.25e-7, + "input_cost_per_image": 0.00032875, + "input_cost_per_image_above_128k_tokens": 0.0006575, + "input_cost_per_token": 7.8125e-8, + "input_cost_per_token_above_128k_tokens": 1.5625e-7, + "input_cost_per_video_per_second": 0.00032875, + "input_cost_per_video_per_second_above_128k_tokens": 0.0006575, + "max_input_tokens": 1000000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_character": 0.00000125, + "output_cost_per_character_above_128k_tokens": 0.0000025, + "output_cost_per_token": 3.125e-7, + "output_cost_per_token_above_128k_tokens": 6.25e-7, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "provider": "vertex_ai-language-models" + }, + "gemini-1.5-pro-preview-0514": { + "input_cost_per_audio_per_second": 0.00003125, + "input_cost_per_audio_per_second_above_128k_tokens": 0.0000625, + "input_cost_per_character": 3.125e-7, + "input_cost_per_character_above_128k_tokens": 6.25e-7, + "input_cost_per_image": 0.00032875, + "input_cost_per_image_above_128k_tokens": 0.0006575, + "input_cost_per_token": 7.8125e-8, + "input_cost_per_token_above_128k_tokens": 1.5625e-7, + "input_cost_per_video_per_second": 0.00032875, + "input_cost_per_video_per_second_above_128k_tokens": 0.0006575, + "max_input_tokens": 1000000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_character": 0.00000125, + "output_cost_per_character_above_128k_tokens": 0.0000025, + "output_cost_per_token": 3.125e-7, + "output_cost_per_token_above_128k_tokens": 6.25e-7, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "vertex_ai-language-models" + }, + "gemini-2.0-flash": { + "cache_read_input_token_cost": 2.5e-8, + "input_cost_per_audio_token": 7e-7, + "input_cost_per_token": 1e-7, + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 4e-7, + "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_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true, + "provider": "vertex_ai-language-models" + }, + "gemini-2.0-flash-001": { + "cache_read_input_token_cost": 3.75e-8, + "deprecation_date": "2026-02-05", + "input_cost_per_audio_token": 0.000001, + "input_cost_per_token": 1.5e-7, + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 6e-7, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "supported_modalities": ["text", "image", "audio", "video"], + "supported_output_modalities": ["text", "image"], + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "provider": "vertex_ai-language-models" + }, + "gemini-2.0-flash-exp": { + "cache_read_input_token_cost": 3.75e-8, + "input_cost_per_audio_per_second": 0, + "input_cost_per_audio_per_second_above_128k_tokens": 0, + "input_cost_per_character": 0, + "input_cost_per_character_above_128k_tokens": 0, + "input_cost_per_image": 0, + "input_cost_per_image_above_128k_tokens": 0, + "input_cost_per_token": 1.5e-7, + "input_cost_per_token_above_128k_tokens": 0, + "input_cost_per_video_per_second": 0, + "input_cost_per_video_per_second_above_128k_tokens": 0, + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_character": 0, + "output_cost_per_character_above_128k_tokens": 0, + "output_cost_per_token": 6e-7, + "output_cost_per_token_above_128k_tokens": 0, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "supported_modalities": ["text", "image", "audio", "video"], + "supported_output_modalities": ["text", "image"], + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "provider": "vertex_ai-language-models" + }, + "gemini-2.0-flash-lite": { + "cache_read_input_token_cost": 1.875e-8, + "input_cost_per_audio_token": 7.5e-8, + "input_cost_per_token": 7.5e-8, + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 50, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 3e-7, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash", + "supported_modalities": ["text", "image", "audio", "video"], + "supported_output_modalities": ["text"], + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "provider": "vertex_ai-language-models" + }, + "gemini-2.0-flash-lite-001": { + "cache_read_input_token_cost": 1.875e-8, + "deprecation_date": "2026-02-25", + "input_cost_per_audio_token": 7.5e-8, + "input_cost_per_token": 7.5e-8, + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 50, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 3e-7, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash", + "supported_modalities": ["text", "image", "audio", "video"], + "supported_output_modalities": ["text"], + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "provider": "vertex_ai-language-models" + }, + "gemini-2.0-flash-live-preview-04-09": { + "cache_read_input_token_cost": 7.5e-8, + "input_cost_per_audio_token": 0.000003, + "input_cost_per_image": 0.000003, + "input_cost_per_token": 5e-7, + "input_cost_per_video_per_second": 0.000003, + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_audio_token": 0.000012, + "output_cost_per_token": 0.000002, + "rpm": 10, + "source": "https://cloud.google.com/vertex-ai/docs/generative-ai/model-reference/gemini#gemini-2-0-flash-live-preview-04-09", + "supported_endpoints": ["/v1/chat/completions", "/v1/completions"], + "supported_modalities": ["text", "image", "audio", "video"], + "supported_output_modalities": ["text", "audio"], + "supports_audio_output": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 250000, + "provider": "vertex_ai-language-models" + }, + "gemini-2.0-flash-preview-image-generation": { + "cache_read_input_token_cost": 2.5e-8, + "input_cost_per_audio_token": 7e-7, + "input_cost_per_token": 1e-7, + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 4e-7, + "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_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "provider": "vertex_ai-language-models" + }, + "gemini-2.0-flash-thinking-exp": { + "cache_read_input_token_cost": 0, + "input_cost_per_audio_per_second": 0, + "input_cost_per_audio_per_second_above_128k_tokens": 0, + "input_cost_per_character": 0, + "input_cost_per_character_above_128k_tokens": 0, + "input_cost_per_image": 0, + "input_cost_per_image_above_128k_tokens": 0, + "input_cost_per_token": 0, + "input_cost_per_token_above_128k_tokens": 0, + "input_cost_per_video_per_second": 0, + "input_cost_per_video_per_second_above_128k_tokens": 0, + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_character": 0, + "output_cost_per_character_above_128k_tokens": 0, + "output_cost_per_token": 0, + "output_cost_per_token_above_128k_tokens": 0, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash", + "supported_modalities": ["text", "image", "audio", "video"], + "supported_output_modalities": ["text", "image"], + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "provider": "vertex_ai-language-models" + }, + "gemini-2.0-flash-thinking-exp-01-21": { + "cache_read_input_token_cost": 0, + "input_cost_per_audio_per_second": 0, + "input_cost_per_audio_per_second_above_128k_tokens": 0, + "input_cost_per_character": 0, + "input_cost_per_character_above_128k_tokens": 0, + "input_cost_per_image": 0, + "input_cost_per_image_above_128k_tokens": 0, + "input_cost_per_token": 0, + "input_cost_per_token_above_128k_tokens": 0, + "input_cost_per_video_per_second": 0, + "input_cost_per_video_per_second_above_128k_tokens": 0, + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_pdf_size_mb": 30, + "max_tokens": 65536, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_character": 0, + "output_cost_per_character_above_128k_tokens": 0, + "output_cost_per_token": 0, + "output_cost_per_token_above_128k_tokens": 0, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash", + "supported_modalities": ["text", "image", "audio", "video"], + "supported_output_modalities": ["text", "image"], + "supports_audio_output": false, + "supports_function_calling": false, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "provider": "vertex_ai-language-models" + }, + "gemini-2.0-pro-exp-02-05": { + "cache_read_input_token_cost": 3.125e-7, + "input_cost_per_token": 0.00000125, + "input_cost_per_token_above_200k_tokens": 0.0000025, + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 2097152, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 0.00001, + "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_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "provider": "vertex_ai-language-models" + }, + "gemini-2.5-flash": { + "cache_read_input_token_cost": 3e-8, + "input_cost_per_audio_token": 0.000001, + "input_cost_per_token": 3e-7, + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_reasoning_token": 0.0000025, + "output_cost_per_token": 0.0000025, + "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": ["text", "image", "audio", "video"], + "supported_output_modalities": ["text"], + "supports_audio_output": false, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true, + "provider": "vertex_ai-language-models" + }, + "gemini-2.5-flash-image": { + "cache_read_input_token_cost": 3e-8, + "input_cost_per_audio_token": 0.000001, + "input_cost_per_token": 3e-7, + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "max_pdf_size_mb": 30, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "image_generation", + "output_cost_per_image": 0.039, + "output_cost_per_reasoning_token": 0.0000025, + "output_cost_per_token": 0.0000025, + "rpm": 100000, + "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-flash-image", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": ["text", "image", "audio", "video"], + "supported_output_modalities": ["text", "image"], + "supports_audio_output": false, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": false, + "tpm": 8000000, + "provider": "vertex_ai-language-models" + }, + "gemini-2.5-flash-image-preview": { + "cache_read_input_token_cost": 7.5e-8, + "input_cost_per_audio_token": 0.000001, + "input_cost_per_token": 3e-7, + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "image_generation", + "output_cost_per_image": 0.039, + "output_cost_per_reasoning_token": 0.00003, + "output_cost_per_token": 0.00003, + "rpm": 100000, + "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": ["text", "image", "audio", "video"], + "supported_output_modalities": ["text", "image"], + "supports_audio_output": false, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 8000000, + "provider": "vertex_ai-language-models" + }, + "gemini-3-pro-image-preview": { + "input_cost_per_image": 0.0011, + "input_cost_per_token": 0.000002, + "input_cost_per_token_batches": 0.000001, + "max_input_tokens": 65536, + "max_output_tokens": 32768, + "max_tokens": 65536, + "mode": "image_generation", + "output_cost_per_image": 0.134, + "output_cost_per_token": 0.000012, + "output_cost_per_token_batches": 0.000006, + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text", "image"], + "supports_function_calling": false, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_vision": true, + "supports_web_search": true, + "provider": "vertex_ai-language-models" + }, + "gemini-2.5-flash-lite": { + "cache_read_input_token_cost": 2.5e-8, + "input_cost_per_audio_token": 5e-7, + "input_cost_per_token": 1e-7, + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_reasoning_token": 4e-7, + "output_cost_per_token": 4e-7, + "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": ["text", "image", "audio", "video"], + "supported_output_modalities": ["text"], + "supports_audio_output": false, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true, + "provider": "vertex_ai-language-models" + }, + "gemini-2.5-flash-lite-preview-09-2025": { + "cache_read_input_token_cost": 2.5e-8, + "input_cost_per_audio_token": 3e-7, + "input_cost_per_token": 1e-7, + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_reasoning_token": 4e-7, + "output_cost_per_token": 4e-7, + "source": "https://developers.googleblog.com/en/continuing-to-bring-you-our-latest-models-with-an-improved-gemini-2-5-flash-and-flash-lite-release/", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": ["text", "image", "audio", "video"], + "supported_output_modalities": ["text"], + "supports_audio_output": false, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true, + "provider": "vertex_ai-language-models" + }, + "gemini-2.5-flash-preview-09-2025": { + "cache_read_input_token_cost": 7.5e-8, + "input_cost_per_audio_token": 0.000001, + "input_cost_per_token": 3e-7, + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_reasoning_token": 0.0000025, + "output_cost_per_token": 0.0000025, + "source": "https://developers.googleblog.com/en/continuing-to-bring-you-our-latest-models-with-an-improved-gemini-2-5-flash-and-flash-lite-release/", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": ["text", "image", "audio", "video"], + "supported_output_modalities": ["text"], + "supports_audio_output": false, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true, + "provider": "vertex_ai-language-models" + }, + "gemini-live-2.5-flash-preview-native-audio-09-2025": { + "cache_read_input_token_cost": 7.5e-8, + "input_cost_per_audio_token": 0.000003, + "input_cost_per_token": 3e-7, + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_audio_token": 0.000012, + "output_cost_per_token": 0.000002, + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "supported_endpoints": ["/v1/chat/completions", "/v1/completions"], + "supported_modalities": ["text", "image", "audio", "video"], + "supported_output_modalities": ["text", "audio"], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true, + "provider": "vertex_ai-language-models" + }, + "gemini/gemini-live-2.5-flash-preview-native-audio-09-2025": { + "cache_read_input_token_cost": 7.5e-8, + "input_cost_per_audio_token": 0.000003, + "input_cost_per_token": 3e-7, + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_audio_token": 0.000012, + "output_cost_per_token": 0.000002, + "rpm": 100000, + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "supported_endpoints": ["/v1/chat/completions", "/v1/completions"], + "supported_modalities": ["text", "image", "audio", "video"], + "supported_output_modalities": ["text", "audio"], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 8000000, + "provider": "gemini" + }, + "gemini-2.5-flash-lite-preview-06-17": { + "cache_read_input_token_cost": 2.5e-8, + "input_cost_per_audio_token": 5e-7, + "input_cost_per_token": 1e-7, + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_reasoning_token": 4e-7, + "output_cost_per_token": 4e-7, + "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": ["text", "image", "audio", "video"], + "supported_output_modalities": ["text"], + "supports_audio_output": false, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true, + "provider": "vertex_ai-language-models" + }, + "gemini-2.5-flash-preview-04-17": { + "cache_read_input_token_cost": 3.75e-8, + "input_cost_per_audio_token": 0.000001, + "input_cost_per_token": 1.5e-7, + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_reasoning_token": 0.0000035, + "output_cost_per_token": 6e-7, + "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": ["text", "image", "audio", "video"], + "supported_output_modalities": ["text"], + "supports_audio_output": false, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "provider": "vertex_ai-language-models" + }, + "gemini-2.5-flash-preview-05-20": { + "cache_read_input_token_cost": 7.5e-8, + "input_cost_per_audio_token": 0.000001, + "input_cost_per_token": 3e-7, + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_reasoning_token": 0.0000025, + "output_cost_per_token": 0.0000025, + "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": ["text", "image", "audio", "video"], + "supported_output_modalities": ["text"], + "supports_audio_output": false, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true, + "provider": "vertex_ai-language-models" + }, + "gemini-2.5-pro": { + "cache_read_input_token_cost": 1.25e-7, + "cache_creation_input_token_cost_above_200k_tokens": 2.5e-7, + "input_cost_per_token": 0.00000125, + "input_cost_per_token_above_200k_tokens": 0.0000025, + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 0.00001, + "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_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "provider": "vertex_ai-language-models" + }, + "gemini-3-pro-preview": { + "cache_read_input_token_cost": 2e-7, + "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": 0.000002, + "input_cost_per_token_above_200k_tokens": 0.000004, + "input_cost_per_token_batches": 0.000001, + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 0.000012, + "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_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "provider": "vertex_ai-language-models" + }, + "vertex_ai/gemini-3-pro-preview": { + "cache_read_input_token_cost": 2e-7, + "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": 0.000002, + "input_cost_per_token_above_200k_tokens": 0.000004, + "input_cost_per_token_batches": 0.000001, + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 0.000012, + "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_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "provider": "vertex_ai" + }, + "gemini-2.5-pro-exp-03-25": { + "cache_read_input_token_cost": 3.125e-7, + "input_cost_per_token": 0.00000125, + "input_cost_per_token_above_200k_tokens": 0.0000025, + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 0.00001, + "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_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "provider": "vertex_ai-language-models" + }, + "gemini-2.5-pro-preview-03-25": { + "cache_read_input_token_cost": 3.125e-7, + "input_cost_per_audio_token": 0.00000125, + "input_cost_per_token": 0.00000125, + "input_cost_per_token_above_200k_tokens": 0.0000025, + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 0.00001, + "output_cost_per_token_above_200k_tokens": 0.000015, + "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": ["text", "image", "audio", "video"], + "supported_output_modalities": ["text"], + "supports_audio_output": false, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "provider": "vertex_ai-language-models" + }, + "gemini-2.5-pro-preview-05-06": { + "cache_read_input_token_cost": 3.125e-7, + "input_cost_per_audio_token": 0.00000125, + "input_cost_per_token": 0.00000125, + "input_cost_per_token_above_200k_tokens": 0.0000025, + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 0.00001, + "output_cost_per_token_above_200k_tokens": 0.000015, + "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": ["text", "image", "audio", "video"], + "supported_output_modalities": ["text"], + "supported_regions": ["global"], + "supports_audio_output": false, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "provider": "vertex_ai-language-models" + }, + "gemini-2.5-pro-preview-06-05": { + "cache_read_input_token_cost": 3.125e-7, + "input_cost_per_audio_token": 0.00000125, + "input_cost_per_token": 0.00000125, + "input_cost_per_token_above_200k_tokens": 0.0000025, + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 0.00001, + "output_cost_per_token_above_200k_tokens": 0.000015, + "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": ["text", "image", "audio", "video"], + "supported_output_modalities": ["text"], + "supports_audio_output": false, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "provider": "vertex_ai-language-models" + }, + "gemini-2.5-pro-preview-tts": { + "cache_read_input_token_cost": 3.125e-7, + "input_cost_per_audio_token": 7e-7, + "input_cost_per_token": 0.00000125, + "input_cost_per_token_above_200k_tokens": 0.0000025, + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 0.00001, + "output_cost_per_token_above_200k_tokens": 0.000015, + "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro-preview", + "supported_modalities": ["text"], + "supported_output_modalities": ["audio"], + "supports_audio_output": false, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "provider": "vertex_ai-language-models" + }, + "gemini-embedding-001": { + "input_cost_per_token": 1.5e-7, + "max_input_tokens": 2048, + "max_tokens": 2048, + "mode": "embedding", + "output_cost_per_token": 0, + "output_vector_size": 3072, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models", + "provider": "vertex_ai-embedding-models" + }, + "gemini-flash-experimental": { + "input_cost_per_character": 0, + "input_cost_per_token": 0, + "max_input_tokens": 1000000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_character": 0, + "output_cost_per_token": 0, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/gemini-experimental", + "supports_function_calling": false, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "provider": "vertex_ai-language-models" + }, + "gemini-pro": { + "input_cost_per_character": 1.25e-7, + "input_cost_per_image": 0.0025, + "input_cost_per_token": 5e-7, + "input_cost_per_video_per_second": 0.002, + "max_input_tokens": 32760, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_character": 3.75e-7, + "output_cost_per_token": 0.0000015, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "provider": "vertex_ai-language-models" + }, + "gemini-pro-experimental": { + "input_cost_per_character": 0, + "input_cost_per_token": 0, + "max_input_tokens": 1000000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_character": 0, + "output_cost_per_token": 0, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/gemini-experimental", + "supports_function_calling": false, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "provider": "vertex_ai-language-models" + }, + "gemini-pro-vision": { + "input_cost_per_image": 0.0025, + "input_cost_per_token": 5e-7, + "max_images_per_prompt": 16, + "max_input_tokens": 16384, + "max_output_tokens": 2048, + "max_tokens": 2048, + "max_video_length": 2, + "max_videos_per_prompt": 1, + "mode": "chat", + "output_cost_per_token": 0.0000015, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "vertex_ai-vision-models" + }, + "gemini/gemini-embedding-001": { + "input_cost_per_token": 1.5e-7, + "max_input_tokens": 2048, + "max_tokens": 2048, + "mode": "embedding", + "output_cost_per_token": 0, + "output_vector_size": 3072, + "rpm": 10000, + "source": "https://ai.google.dev/gemini-api/docs/embeddings#model-versions", + "tpm": 10000000, + "provider": "gemini" + }, + "gemini/gemini-1.5-flash": { + "input_cost_per_token": 7.5e-8, + "input_cost_per_token_above_128k_tokens": 1.5e-7, + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 3e-7, + "output_cost_per_token_above_128k_tokens": 6e-7, + "rpm": 2000, + "source": "https://ai.google.dev/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "tpm": 4000000, + "provider": "gemini" + }, + "gemini/gemini-1.5-flash-001": { + "cache_creation_input_token_cost": 0.000001, + "cache_read_input_token_cost": 1.875e-8, + "deprecation_date": "2025-05-24", + "input_cost_per_token": 7.5e-8, + "input_cost_per_token_above_128k_tokens": 1.5e-7, + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 3e-7, + "output_cost_per_token_above_128k_tokens": 6e-7, + "rpm": 2000, + "source": "https://ai.google.dev/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "tpm": 4000000, + "provider": "gemini" + }, + "gemini/gemini-1.5-flash-002": { + "cache_creation_input_token_cost": 0.000001, + "cache_read_input_token_cost": 1.875e-8, + "deprecation_date": "2025-09-24", + "input_cost_per_token": 7.5e-8, + "input_cost_per_token_above_128k_tokens": 1.5e-7, + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 3e-7, + "output_cost_per_token_above_128k_tokens": 6e-7, + "rpm": 2000, + "source": "https://ai.google.dev/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "tpm": 4000000, + "provider": "gemini" + }, + "gemini/gemini-1.5-flash-8b": { + "input_cost_per_token": 0, + "input_cost_per_token_above_128k_tokens": 0, + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 0, + "output_cost_per_token_above_128k_tokens": 0, + "rpm": 4000, + "source": "https://ai.google.dev/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "tpm": 4000000, + "provider": "gemini" + }, + "gemini/gemini-1.5-flash-8b-exp-0827": { + "input_cost_per_token": 0, + "input_cost_per_token_above_128k_tokens": 0, + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1000000, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 0, + "output_cost_per_token_above_128k_tokens": 0, + "rpm": 4000, + "source": "https://ai.google.dev/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "tpm": 4000000, + "provider": "gemini" + }, + "gemini/gemini-1.5-flash-8b-exp-0924": { + "input_cost_per_token": 0, + "input_cost_per_token_above_128k_tokens": 0, + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 0, + "output_cost_per_token_above_128k_tokens": 0, + "rpm": 4000, + "source": "https://ai.google.dev/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "tpm": 4000000, + "provider": "gemini" + }, + "gemini/gemini-1.5-flash-exp-0827": { + "input_cost_per_token": 0, + "input_cost_per_token_above_128k_tokens": 0, + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 0, + "output_cost_per_token_above_128k_tokens": 0, + "rpm": 2000, + "source": "https://ai.google.dev/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "tpm": 4000000, + "provider": "gemini" + }, + "gemini/gemini-1.5-flash-latest": { + "input_cost_per_token": 7.5e-8, + "input_cost_per_token_above_128k_tokens": 1.5e-7, + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 3e-7, + "output_cost_per_token_above_128k_tokens": 6e-7, + "rpm": 2000, + "source": "https://ai.google.dev/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "tpm": 4000000, + "provider": "gemini" + }, + "gemini/gemini-1.5-pro": { + "input_cost_per_token": 0.0000035, + "input_cost_per_token_above_128k_tokens": 0.000007, + "max_input_tokens": 2097152, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.0000105, + "output_cost_per_token_above_128k_tokens": 0.000021, + "rpm": 1000, + "source": "https://ai.google.dev/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "tpm": 4000000, + "provider": "gemini" + }, + "gemini/gemini-1.5-pro-001": { + "deprecation_date": "2025-05-24", + "input_cost_per_token": 0.0000035, + "input_cost_per_token_above_128k_tokens": 0.000007, + "max_input_tokens": 2097152, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.0000105, + "output_cost_per_token_above_128k_tokens": 0.000021, + "rpm": 1000, + "source": "https://ai.google.dev/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "tpm": 4000000, + "provider": "gemini" + }, + "gemini/gemini-1.5-pro-002": { + "deprecation_date": "2025-09-24", + "input_cost_per_token": 0.0000035, + "input_cost_per_token_above_128k_tokens": 0.000007, + "max_input_tokens": 2097152, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.0000105, + "output_cost_per_token_above_128k_tokens": 0.000021, + "rpm": 1000, + "source": "https://ai.google.dev/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "tpm": 4000000, + "provider": "gemini" + }, + "gemini/gemini-1.5-pro-exp-0801": { + "input_cost_per_token": 0.0000035, + "input_cost_per_token_above_128k_tokens": 0.000007, + "max_input_tokens": 2097152, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.0000105, + "output_cost_per_token_above_128k_tokens": 0.000021, + "rpm": 1000, + "source": "https://ai.google.dev/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "tpm": 4000000, + "provider": "gemini" + }, + "gemini/gemini-1.5-pro-exp-0827": { + "input_cost_per_token": 0, + "input_cost_per_token_above_128k_tokens": 0, + "max_input_tokens": 2097152, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0, + "output_cost_per_token_above_128k_tokens": 0, + "rpm": 1000, + "source": "https://ai.google.dev/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "tpm": 4000000, + "provider": "gemini" + }, + "gemini/gemini-1.5-pro-latest": { + "input_cost_per_token": 0.0000035, + "input_cost_per_token_above_128k_tokens": 0.000007, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.00000105, + "output_cost_per_token_above_128k_tokens": 0.000021, + "rpm": 1000, + "source": "https://ai.google.dev/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "tpm": 4000000, + "provider": "gemini" + }, + "gemini/gemini-2.0-flash": { + "cache_read_input_token_cost": 2.5e-8, + "input_cost_per_audio_token": 7e-7, + "input_cost_per_token": 1e-7, + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 4e-7, + "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_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 10000000, + "provider": "gemini" + }, + "gemini/gemini-2.0-flash-001": { + "cache_read_input_token_cost": 2.5e-8, + "input_cost_per_audio_token": 7e-7, + "input_cost_per_token": 1e-7, + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 4e-7, + "rpm": 10000, + "source": "https://ai.google.dev/pricing#2_0flash", + "supported_modalities": ["text", "image", "audio", "video"], + "supported_output_modalities": ["text", "image"], + "supports_audio_output": false, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 10000000, + "provider": "gemini" + }, + "gemini/gemini-2.0-flash-exp": { + "cache_read_input_token_cost": 0, + "input_cost_per_audio_per_second": 0, + "input_cost_per_audio_per_second_above_128k_tokens": 0, + "input_cost_per_character": 0, + "input_cost_per_character_above_128k_tokens": 0, + "input_cost_per_image": 0, + "input_cost_per_image_above_128k_tokens": 0, + "input_cost_per_token": 0, + "input_cost_per_token_above_128k_tokens": 0, + "input_cost_per_video_per_second": 0, + "input_cost_per_video_per_second_above_128k_tokens": 0, + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_character": 0, + "output_cost_per_character_above_128k_tokens": 0, + "output_cost_per_token": 0, + "output_cost_per_token_above_128k_tokens": 0, + "rpm": 10, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash", + "supported_modalities": ["text", "image", "audio", "video"], + "supported_output_modalities": ["text", "image"], + "supports_audio_output": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 4000000, + "provider": "gemini" + }, + "gemini/gemini-2.0-flash-lite": { + "cache_read_input_token_cost": 1.875e-8, + "input_cost_per_audio_token": 7.5e-8, + "input_cost_per_token": 7.5e-8, + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 50, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 3e-7, + "rpm": 4000, + "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.0-flash-lite", + "supported_modalities": ["text", "image", "audio", "video"], + "supported_output_modalities": ["text"], + "supports_audio_output": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 4000000, + "provider": "gemini" + }, + "gemini/gemini-2.0-flash-lite-preview-02-05": { + "cache_read_input_token_cost": 1.875e-8, + "input_cost_per_audio_token": 7.5e-8, + "input_cost_per_token": 7.5e-8, + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 3e-7, + "rpm": 60000, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash-lite", + "supported_modalities": ["text", "image", "audio", "video"], + "supported_output_modalities": ["text"], + "supports_audio_output": false, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 10000000, + "provider": "gemini" + }, + "gemini/gemini-2.0-flash-live-001": { + "cache_read_input_token_cost": 7.5e-8, + "input_cost_per_audio_token": 0.0000021, + "input_cost_per_image": 0.0000021, + "input_cost_per_token": 3.5e-7, + "input_cost_per_video_per_second": 0.0000021, + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_audio_token": 0.0000085, + "output_cost_per_token": 0.0000015, + "rpm": 10, + "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2-0-flash-live-001", + "supported_endpoints": ["/v1/chat/completions", "/v1/completions"], + "supported_modalities": ["text", "image", "audio", "video"], + "supported_output_modalities": ["text", "audio"], + "supports_audio_output": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 250000, + "provider": "gemini" + }, + "gemini/gemini-2.0-flash-preview-image-generation": { + "cache_read_input_token_cost": 2.5e-8, + "input_cost_per_audio_token": 7e-7, + "input_cost_per_token": 1e-7, + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 4e-7, + "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_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 10000000, + "provider": "gemini" + }, + "gemini/gemini-2.0-flash-thinking-exp": { + "cache_read_input_token_cost": 0, + "input_cost_per_audio_per_second": 0, + "input_cost_per_audio_per_second_above_128k_tokens": 0, + "input_cost_per_character": 0, + "input_cost_per_character_above_128k_tokens": 0, + "input_cost_per_image": 0, + "input_cost_per_image_above_128k_tokens": 0, + "input_cost_per_token": 0, + "input_cost_per_token_above_128k_tokens": 0, + "input_cost_per_video_per_second": 0, + "input_cost_per_video_per_second_above_128k_tokens": 0, + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_character": 0, + "output_cost_per_character_above_128k_tokens": 0, + "output_cost_per_token": 0, + "output_cost_per_token_above_128k_tokens": 0, + "rpm": 10, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash", + "supported_modalities": ["text", "image", "audio", "video"], + "supported_output_modalities": ["text", "image"], + "supports_audio_output": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 4000000, + "provider": "gemini" + }, + "gemini/gemini-2.0-flash-thinking-exp-01-21": { + "cache_read_input_token_cost": 0, + "input_cost_per_audio_per_second": 0, + "input_cost_per_audio_per_second_above_128k_tokens": 0, + "input_cost_per_character": 0, + "input_cost_per_character_above_128k_tokens": 0, + "input_cost_per_image": 0, + "input_cost_per_image_above_128k_tokens": 0, + "input_cost_per_token": 0, + "input_cost_per_token_above_128k_tokens": 0, + "input_cost_per_video_per_second": 0, + "input_cost_per_video_per_second_above_128k_tokens": 0, + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_character": 0, + "output_cost_per_character_above_128k_tokens": 0, + "output_cost_per_token": 0, + "output_cost_per_token_above_128k_tokens": 0, + "rpm": 10, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash", + "supported_modalities": ["text", "image", "audio", "video"], + "supported_output_modalities": ["text", "image"], + "supports_audio_output": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 4000000, + "provider": "gemini" + }, + "gemini/gemini-2.0-pro-exp-02-05": { + "cache_read_input_token_cost": 0, + "input_cost_per_audio_per_second": 0, + "input_cost_per_audio_per_second_above_128k_tokens": 0, + "input_cost_per_character": 0, + "input_cost_per_character_above_128k_tokens": 0, + "input_cost_per_image": 0, + "input_cost_per_image_above_128k_tokens": 0, + "input_cost_per_token": 0, + "input_cost_per_token_above_128k_tokens": 0, + "input_cost_per_video_per_second": 0, + "input_cost_per_video_per_second_above_128k_tokens": 0, + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 2097152, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_character": 0, + "output_cost_per_character_above_128k_tokens": 0, + "output_cost_per_token": 0, + "output_cost_per_token_above_128k_tokens": 0, + "rpm": 2, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "supports_audio_input": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 1000000, + "provider": "gemini" + }, + "gemini/gemini-2.5-flash": { + "cache_read_input_token_cost": 3e-8, + "input_cost_per_audio_token": 0.000001, + "input_cost_per_token": 3e-7, + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_reasoning_token": 0.0000025, + "output_cost_per_token": 0.0000025, + "rpm": 100000, + "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": ["text", "image", "audio", "video"], + "supported_output_modalities": ["text"], + "supports_audio_output": false, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 8000000, + "provider": "gemini" + }, + "gemini/gemini-2.5-flash-image": { + "cache_read_input_token_cost": 3e-8, + "input_cost_per_audio_token": 0.000001, + "input_cost_per_token": 3e-7, + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "supports_reasoning": false, + "max_images_per_prompt": 3000, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "max_pdf_size_mb": 30, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "image_generation", + "output_cost_per_image": 0.039, + "output_cost_per_reasoning_token": 0.0000025, + "output_cost_per_token": 0.0000025, + "rpm": 100000, + "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-flash-image", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": ["text", "image", "audio", "video"], + "supported_output_modalities": ["text", "image"], + "supports_audio_output": false, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 8000000, + "provider": "vertex_ai-language-models" + }, + "gemini/gemini-2.5-flash-image-preview": { + "cache_read_input_token_cost": 7.5e-8, + "input_cost_per_audio_token": 0.000001, + "input_cost_per_token": 3e-7, + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "image_generation", + "output_cost_per_image": 0.039, + "output_cost_per_reasoning_token": 0.00003, + "output_cost_per_token": 0.00003, + "rpm": 100000, + "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": ["text", "image", "audio", "video"], + "supported_output_modalities": ["text", "image"], + "supports_audio_output": false, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 8000000, + "provider": "gemini" + }, + "gemini/gemini-3-pro-image-preview": { + "input_cost_per_image": 0.0011, + "input_cost_per_token": 0.000002, + "input_cost_per_token_batches": 0.000001, + "max_input_tokens": 65536, + "max_output_tokens": 32768, + "max_tokens": 65536, + "mode": "image_generation", + "output_cost_per_image": 0.134, + "output_cost_per_token": 0.000012, + "rpm": 1000, + "tpm": 4000000, + "output_cost_per_token_batches": 0.000006, + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text", "image"], + "supports_function_calling": false, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_vision": true, + "supports_web_search": true, + "provider": "gemini" + }, + "gemini/gemini-2.5-flash-lite": { + "cache_read_input_token_cost": 2.5e-8, + "input_cost_per_audio_token": 5e-7, + "input_cost_per_token": 1e-7, + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_reasoning_token": 4e-7, + "output_cost_per_token": 4e-7, + "rpm": 15, + "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-lite", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": ["text", "image", "audio", "video"], + "supported_output_modalities": ["text"], + "supports_audio_output": false, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 250000, + "provider": "gemini" + }, + "gemini/gemini-2.5-flash-lite-preview-09-2025": { + "cache_read_input_token_cost": 2.5e-8, + "input_cost_per_audio_token": 3e-7, + "input_cost_per_token": 1e-7, + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_reasoning_token": 4e-7, + "output_cost_per_token": 4e-7, + "rpm": 15, + "source": "https://developers.googleblog.com/en/continuing-to-bring-you-our-latest-models-with-an-improved-gemini-2-5-flash-and-flash-lite-release/", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": ["text", "image", "audio", "video"], + "supported_output_modalities": ["text"], + "supports_audio_output": false, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 250000, + "provider": "gemini" + }, + "gemini/gemini-2.5-flash-preview-09-2025": { + "cache_read_input_token_cost": 7.5e-8, + "input_cost_per_audio_token": 0.000001, + "input_cost_per_token": 3e-7, + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_reasoning_token": 0.0000025, + "output_cost_per_token": 0.0000025, + "rpm": 15, + "source": "https://developers.googleblog.com/en/continuing-to-bring-you-our-latest-models-with-an-improved-gemini-2-5-flash-and-flash-lite-release/", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": ["text", "image", "audio", "video"], + "supported_output_modalities": ["text"], + "supports_audio_output": false, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 250000, + "provider": "gemini" + }, + "gemini/gemini-flash-latest": { + "cache_read_input_token_cost": 7.5e-8, + "input_cost_per_audio_token": 0.000001, + "input_cost_per_token": 3e-7, + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_reasoning_token": 0.0000025, + "output_cost_per_token": 0.0000025, + "rpm": 15, + "source": "https://developers.googleblog.com/en/continuing-to-bring-you-our-latest-models-with-an-improved-gemini-2-5-flash-and-flash-lite-release/", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": ["text", "image", "audio", "video"], + "supported_output_modalities": ["text"], + "supports_audio_output": false, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 250000, + "provider": "gemini" + }, + "gemini/gemini-flash-lite-latest": { + "cache_read_input_token_cost": 2.5e-8, + "input_cost_per_audio_token": 3e-7, + "input_cost_per_token": 1e-7, + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_reasoning_token": 4e-7, + "output_cost_per_token": 4e-7, + "rpm": 15, + "source": "https://developers.googleblog.com/en/continuing-to-bring-you-our-latest-models-with-an-improved-gemini-2-5-flash-and-flash-lite-release/", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": ["text", "image", "audio", "video"], + "supported_output_modalities": ["text"], + "supports_audio_output": false, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 250000, + "provider": "gemini" + }, + "gemini/gemini-2.5-flash-lite-preview-06-17": { + "cache_read_input_token_cost": 2.5e-8, + "input_cost_per_audio_token": 5e-7, + "input_cost_per_token": 1e-7, + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_reasoning_token": 4e-7, + "output_cost_per_token": 4e-7, + "rpm": 15, + "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-lite", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": ["text", "image", "audio", "video"], + "supported_output_modalities": ["text"], + "supports_audio_output": false, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 250000, + "provider": "gemini" + }, + "gemini/gemini-2.5-flash-preview-04-17": { + "cache_read_input_token_cost": 3.75e-8, + "input_cost_per_audio_token": 0.000001, + "input_cost_per_token": 1.5e-7, + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_reasoning_token": 0.0000035, + "output_cost_per_token": 6e-7, + "rpm": 10, + "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", + "supported_endpoints": ["/v1/chat/completions", "/v1/completions"], + "supported_modalities": ["text", "image", "audio", "video"], + "supported_output_modalities": ["text"], + "supports_audio_output": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 250000, + "provider": "gemini" + }, + "gemini/gemini-2.5-flash-preview-05-20": { + "cache_read_input_token_cost": 7.5e-8, + "input_cost_per_audio_token": 0.000001, + "input_cost_per_token": 3e-7, + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_reasoning_token": 0.0000025, + "output_cost_per_token": 0.0000025, + "rpm": 10, + "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", + "supported_endpoints": ["/v1/chat/completions", "/v1/completions"], + "supported_modalities": ["text", "image", "audio", "video"], + "supported_output_modalities": ["text"], + "supports_audio_output": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 250000, + "provider": "gemini" + }, + "gemini/gemini-2.5-flash-preview-tts": { + "cache_read_input_token_cost": 3.75e-8, + "input_cost_per_audio_token": 0.000001, + "input_cost_per_token": 1.5e-7, + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_reasoning_token": 0.0000035, + "output_cost_per_token": 6e-7, + "rpm": 10, + "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", + "supported_endpoints": ["/v1/chat/completions", "/v1/completions"], + "supported_modalities": ["text"], + "supported_output_modalities": ["audio"], + "supports_audio_output": false, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 250000, + "provider": "gemini" + }, + "gemini/gemini-2.5-pro": { + "cache_read_input_token_cost": 3.125e-7, + "input_cost_per_token": 0.00000125, + "input_cost_per_token_above_200k_tokens": 0.0000025, + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 0.00001, + "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_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 800000, + "provider": "gemini" + }, + "gemini/gemini-3-pro-preview": { + "cache_read_input_token_cost": 2e-7, + "cache_read_input_token_cost_above_200k_tokens": 4e-7, + "input_cost_per_token": 0.000002, + "input_cost_per_token_above_200k_tokens": 0.000004, + "input_cost_per_token_batches": 0.000001, + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 0.000012, + "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_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 800000, + "provider": "gemini" + }, + "gemini/gemini-2.5-pro-exp-03-25": { + "cache_read_input_token_cost": 0, + "input_cost_per_token": 0, + "input_cost_per_token_above_200k_tokens": 0, + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 0, + "output_cost_per_token_above_200k_tokens": 0, + "rpm": 5, + "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_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 250000, + "provider": "gemini" + }, + "gemini/gemini-2.5-pro-preview-03-25": { + "cache_read_input_token_cost": 3.125e-7, + "input_cost_per_audio_token": 7e-7, + "input_cost_per_token": 0.00000125, + "input_cost_per_token_above_200k_tokens": 0.0000025, + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 0.00001, + "output_cost_per_token_above_200k_tokens": 0.000015, + "rpm": 10000, + "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro-preview", + "supported_modalities": ["text", "image", "audio", "video"], + "supported_output_modalities": ["text"], + "supports_audio_output": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 10000000, + "provider": "gemini" + }, + "gemini/gemini-2.5-pro-preview-05-06": { + "cache_read_input_token_cost": 3.125e-7, + "input_cost_per_audio_token": 7e-7, + "input_cost_per_token": 0.00000125, + "input_cost_per_token_above_200k_tokens": 0.0000025, + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 0.00001, + "output_cost_per_token_above_200k_tokens": 0.000015, + "rpm": 10000, + "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro-preview", + "supported_modalities": ["text", "image", "audio", "video"], + "supported_output_modalities": ["text"], + "supports_audio_output": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 10000000, + "provider": "gemini" + }, + "gemini/gemini-2.5-pro-preview-06-05": { + "cache_read_input_token_cost": 3.125e-7, + "input_cost_per_audio_token": 7e-7, + "input_cost_per_token": 0.00000125, + "input_cost_per_token_above_200k_tokens": 0.0000025, + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 0.00001, + "output_cost_per_token_above_200k_tokens": 0.000015, + "rpm": 10000, + "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro-preview", + "supported_modalities": ["text", "image", "audio", "video"], + "supported_output_modalities": ["text"], + "supports_audio_output": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 10000000, + "provider": "gemini" + }, + "gemini/gemini-2.5-pro-preview-tts": { + "cache_read_input_token_cost": 3.125e-7, + "input_cost_per_audio_token": 7e-7, + "input_cost_per_token": 0.00000125, + "input_cost_per_token_above_200k_tokens": 0.0000025, + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 0.00001, + "output_cost_per_token_above_200k_tokens": 0.000015, + "rpm": 10000, + "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro-preview", + "supported_modalities": ["text"], + "supported_output_modalities": ["audio"], + "supports_audio_output": false, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 10000000, + "provider": "gemini" + }, + "gemini/gemini-exp-1114": { + "input_cost_per_token": 0, + "input_cost_per_token_above_128k_tokens": 0, + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "metadata": { + "notes": "Rate limits not documented for gemini-exp-1114. Assuming same as gemini-1.5-pro.", + "supports_tool_choice": true + }, + "mode": "chat", + "output_cost_per_token": 0, + "output_cost_per_token_above_128k_tokens": 0, + "rpm": 1000, + "source": "https://ai.google.dev/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "tpm": 4000000, + "provider": "gemini" + }, + "gemini/gemini-exp-1206": { + "input_cost_per_token": 0, + "input_cost_per_token_above_128k_tokens": 0, + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 2097152, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "metadata": { + "notes": "Rate limits not documented for gemini-exp-1206. Assuming same as gemini-1.5-pro.", + "supports_tool_choice": true + }, + "mode": "chat", + "output_cost_per_token": 0, + "output_cost_per_token_above_128k_tokens": 0, + "rpm": 1000, + "source": "https://ai.google.dev/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "tpm": 4000000, + "provider": "gemini" + }, + "gemini/gemini-gemma-2-27b-it": { + "input_cost_per_token": 3.5e-7, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.00000105, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "gemini" + }, + "gemini/gemini-gemma-2-9b-it": { + "input_cost_per_token": 3.5e-7, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.00000105, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "gemini" + }, + "gemini/gemini-pro": { + "input_cost_per_token": 3.5e-7, + "input_cost_per_token_above_128k_tokens": 7e-7, + "max_input_tokens": 32760, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.00000105, + "output_cost_per_token_above_128k_tokens": 0.0000021, + "rpd": 30000, + "rpm": 360, + "source": "https://ai.google.dev/gemini-api/docs/models/gemini", + "supports_function_calling": true, + "supports_tool_choice": true, + "tpm": 120000, + "provider": "gemini" + }, + "gemini/gemini-pro-vision": { + "input_cost_per_token": 3.5e-7, + "input_cost_per_token_above_128k_tokens": 7e-7, + "max_input_tokens": 30720, + "max_output_tokens": 2048, + "max_tokens": 2048, + "mode": "chat", + "output_cost_per_token": 0.00000105, + "output_cost_per_token_above_128k_tokens": 0.0000021, + "rpd": 30000, + "rpm": 360, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true, + "tpm": 120000, + "provider": "gemini" + }, + "gemini/gemma-3-27b-it": { + "input_cost_per_audio_per_second": 0, + "input_cost_per_audio_per_second_above_128k_tokens": 0, + "input_cost_per_character": 0, + "input_cost_per_character_above_128k_tokens": 0, + "input_cost_per_image": 0, + "input_cost_per_image_above_128k_tokens": 0, + "input_cost_per_token": 0, + "input_cost_per_token_above_128k_tokens": 0, + "input_cost_per_video_per_second": 0, + "input_cost_per_video_per_second_above_128k_tokens": 0, + "max_input_tokens": 131072, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_character": 0, + "output_cost_per_character_above_128k_tokens": 0, + "output_cost_per_token": 0, + "output_cost_per_token_above_128k_tokens": 0, + "source": "https://aistudio.google.com", + "supports_audio_output": false, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": false, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "gemini" + }, + "gemini/imagen-3.0-fast-generate-001": { + "mode": "image_generation", + "output_cost_per_image": 0.02, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "provider": "gemini" + }, + "gemini/imagen-3.0-generate-001": { + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "provider": "gemini" + }, + "gemini/imagen-3.0-generate-002": { + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "provider": "gemini" + }, + "gemini/imagen-4.0-fast-generate-001": { + "mode": "image_generation", + "output_cost_per_image": 0.02, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "provider": "gemini" + }, + "gemini/imagen-4.0-generate-001": { + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "provider": "gemini" + }, + "gemini/imagen-4.0-ultra-generate-001": { + "mode": "image_generation", + "output_cost_per_image": 0.06, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "provider": "gemini" + }, + "gemini/learnlm-1.5-pro-experimental": { + "input_cost_per_audio_per_second": 0, + "input_cost_per_audio_per_second_above_128k_tokens": 0, + "input_cost_per_character": 0, + "input_cost_per_character_above_128k_tokens": 0, + "input_cost_per_image": 0, + "input_cost_per_image_above_128k_tokens": 0, + "input_cost_per_token": 0, + "input_cost_per_token_above_128k_tokens": 0, + "input_cost_per_video_per_second": 0, + "input_cost_per_video_per_second_above_128k_tokens": 0, + "max_input_tokens": 32767, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_character": 0, + "output_cost_per_character_above_128k_tokens": 0, + "output_cost_per_token": 0, + "output_cost_per_token_above_128k_tokens": 0, + "source": "https://aistudio.google.com", + "supports_audio_output": false, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "gemini" + }, + "gemini/veo-2.0-generate-001": { + "max_input_tokens": 1024, + "max_tokens": 1024, + "mode": "video_generation", + "output_cost_per_second": 0.35, + "source": "https://ai.google.dev/gemini-api/docs/video", + "supported_modalities": ["text"], + "supported_output_modalities": ["video"], + "provider": "gemini" + }, + "gemini/veo-3.0-fast-generate-preview": { + "max_input_tokens": 1024, + "max_tokens": 1024, + "mode": "video_generation", + "output_cost_per_second": 0.4, + "source": "https://ai.google.dev/gemini-api/docs/video", + "supported_modalities": ["text"], + "supported_output_modalities": ["video"], + "provider": "gemini" + }, + "gemini/veo-3.0-generate-preview": { + "max_input_tokens": 1024, + "max_tokens": 1024, + "mode": "video_generation", + "output_cost_per_second": 0.75, + "source": "https://ai.google.dev/gemini-api/docs/video", + "supported_modalities": ["text"], + "supported_output_modalities": ["video"], + "provider": "gemini" + }, + "gemini/veo-3.1-fast-generate-preview": { + "max_input_tokens": 1024, + "max_tokens": 1024, + "mode": "video_generation", + "output_cost_per_second": 0.15, + "source": "https://ai.google.dev/gemini-api/docs/video", + "supported_modalities": ["text"], + "supported_output_modalities": ["video"], + "provider": "gemini" + }, + "gemini/veo-3.1-generate-preview": { + "max_input_tokens": 1024, + "max_tokens": 1024, + "mode": "video_generation", + "output_cost_per_second": 0.4, + "source": "https://ai.google.dev/gemini-api/docs/video", + "supported_modalities": ["text"], + "supported_output_modalities": ["video"], + "provider": "gemini" + }, + "google_pse/search": { + "input_cost_per_query": 0.005, + "mode": "search", + "provider": "google_pse" + }, + "global.anthropic.claude-sonnet-4-5-20250929-v1:0": { + "cache_creation_input_token_cost": 0.00000375, + "cache_read_input_token_cost": 3e-7, + "input_cost_per_token": 0.000003, + "input_cost_per_token_above_200k_tokens": 0.000006, + "output_cost_per_token_above_200k_tokens": 0.0000225, + "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, + "cache_read_input_token_cost_above_200k_tokens": 6e-7, + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 0.000015, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 346, + "provider": "bedrock_converse" + }, + "global.anthropic.claude-sonnet-4-20250514-v1:0": { + "cache_creation_input_token_cost": 0.00000375, + "cache_read_input_token_cost": 3e-7, + "input_cost_per_token": 0.000003, + "input_cost_per_token_above_200k_tokens": 0.000006, + "output_cost_per_token_above_200k_tokens": 0.0000225, + "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, + "cache_read_input_token_cost_above_200k_tokens": 6e-7, + "max_input_tokens": 1000000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 0.000015, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159, + "provider": "bedrock_converse" + }, + "global.anthropic.claude-haiku-4-5-20251001-v1:0": { + "cache_creation_input_token_cost": 0.000001375, + "cache_read_input_token_cost": 1.1e-7, + "input_cost_per_token": 0.0000011, + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 0.0000055, + "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock", + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 346, + "provider": "bedrock_converse" + }, + "gpt-3.5-turbo": { + "input_cost_per_token": 5e-7, + "max_input_tokens": 16385, + "max_output_tokens": 4096, + "max_tokens": 4097, + "mode": "chat", + "output_cost_per_token": 0.0000015, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "openai" + }, + "gpt-3.5-turbo-0125": { + "input_cost_per_token": 5e-7, + "max_input_tokens": 16385, + "max_output_tokens": 4096, + "max_tokens": 16385, + "mode": "chat", + "output_cost_per_token": 0.0000015, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "openai" + }, + "gpt-3.5-turbo-0301": { + "input_cost_per_token": 0.0000015, + "max_input_tokens": 4097, + "max_output_tokens": 4096, + "max_tokens": 4097, + "mode": "chat", + "output_cost_per_token": 0.000002, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "openai" + }, + "gpt-3.5-turbo-0613": { + "input_cost_per_token": 0.0000015, + "max_input_tokens": 4097, + "max_output_tokens": 4096, + "max_tokens": 4097, + "mode": "chat", + "output_cost_per_token": 0.000002, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "openai" + }, + "gpt-3.5-turbo-1106": { + "deprecation_date": "2026-09-28", + "input_cost_per_token": 0.000001, + "max_input_tokens": 16385, + "max_output_tokens": 4096, + "max_tokens": 16385, + "mode": "chat", + "output_cost_per_token": 0.000002, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "openai" + }, + "gpt-3.5-turbo-16k": { + "input_cost_per_token": 0.000003, + "max_input_tokens": 16385, + "max_output_tokens": 4096, + "max_tokens": 16385, + "mode": "chat", + "output_cost_per_token": 0.000004, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "openai" + }, + "gpt-3.5-turbo-16k-0613": { + "input_cost_per_token": 0.000003, + "max_input_tokens": 16385, + "max_output_tokens": 4096, + "max_tokens": 16385, + "mode": "chat", + "output_cost_per_token": 0.000004, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "openai" + }, + "gpt-3.5-turbo-instruct": { + "input_cost_per_token": 0.0000015, + "max_input_tokens": 8192, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "completion", + "output_cost_per_token": 0.000002, + "provider": "text-completion-openai" + }, + "gpt-3.5-turbo-instruct-0914": { + "input_cost_per_token": 0.0000015, + "max_input_tokens": 8192, + "max_output_tokens": 4097, + "max_tokens": 4097, + "mode": "completion", + "output_cost_per_token": 0.000002, + "provider": "text-completion-openai" + }, + "gpt-4": { + "input_cost_per_token": 0.00003, + "max_input_tokens": 8192, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.00006, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "openai" + }, + "gpt-4-0125-preview": { + "deprecation_date": "2026-03-26", + "input_cost_per_token": 0.00001, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.00003, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "openai" + }, + "gpt-4-0314": { + "input_cost_per_token": 0.00003, + "max_input_tokens": 8192, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.00006, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "openai" + }, + "gpt-4-0613": { + "deprecation_date": "2025-06-06", + "input_cost_per_token": 0.00003, + "max_input_tokens": 8192, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.00006, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "openai" + }, + "gpt-4-1106-preview": { + "deprecation_date": "2026-03-26", + "input_cost_per_token": 0.00001, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.00003, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "openai" + }, + "gpt-4-1106-vision-preview": { + "deprecation_date": "2024-12-06", + "input_cost_per_token": 0.00001, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.00003, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "openai" + }, + "gpt-4-32k": { + "input_cost_per_token": 0.00006, + "max_input_tokens": 32768, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.00012, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "openai" + }, + "gpt-4-32k-0314": { + "input_cost_per_token": 0.00006, + "max_input_tokens": 32768, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.00012, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "openai" + }, + "gpt-4-32k-0613": { + "input_cost_per_token": 0.00006, + "max_input_tokens": 32768, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.00012, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "openai" + }, + "gpt-4-turbo": { + "input_cost_per_token": 0.00001, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.00003, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "openai" + }, + "gpt-4-turbo-2024-04-09": { + "input_cost_per_token": 0.00001, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.00003, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "openai" + }, + "gpt-4-turbo-preview": { + "input_cost_per_token": 0.00001, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.00003, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "openai" + }, + "gpt-4-vision-preview": { + "deprecation_date": "2024-12-06", + "input_cost_per_token": 0.00001, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.00003, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "openai" + }, + "gpt-4.1": { + "cache_read_input_token_cost": 5e-7, + "cache_read_input_token_cost_priority": 8.75e-7, + "input_cost_per_token": 0.000002, + "input_cost_per_token_batches": 0.000001, + "input_cost_per_token_priority": 0.0000035, + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0.000008, + "output_cost_per_token_batches": 0.000004, + "output_cost_per_token_priority": 0.000014, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_service_tier": true, + "supports_vision": true, + "provider": "openai" + }, + "gpt-4.1-2025-04-14": { + "cache_read_input_token_cost": 5e-7, + "input_cost_per_token": 0.000002, + "input_cost_per_token_batches": 0.000001, + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0.000008, + "output_cost_per_token_batches": 0.000004, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_service_tier": true, + "supports_vision": true, + "provider": "openai" + }, + "gpt-4.1-mini": { + "cache_read_input_token_cost": 1e-7, + "cache_read_input_token_cost_priority": 1.75e-7, + "input_cost_per_token": 4e-7, + "input_cost_per_token_batches": 2e-7, + "input_cost_per_token_priority": 7e-7, + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0.0000016, + "output_cost_per_token_batches": 8e-7, + "output_cost_per_token_priority": 0.0000028, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_service_tier": true, + "supports_vision": true, + "provider": "openai" + }, + "gpt-4.1-mini-2025-04-14": { + "cache_read_input_token_cost": 1e-7, + "input_cost_per_token": 4e-7, + "input_cost_per_token_batches": 2e-7, + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0.0000016, + "output_cost_per_token_batches": 8e-7, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_service_tier": true, + "supports_vision": true, + "provider": "openai" + }, + "gpt-4.1-nano": { + "cache_read_input_token_cost": 2.5e-8, + "cache_read_input_token_cost_priority": 5e-8, + "input_cost_per_token": 1e-7, + "input_cost_per_token_batches": 5e-8, + "input_cost_per_token_priority": 2e-7, + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 4e-7, + "output_cost_per_token_batches": 2e-7, + "output_cost_per_token_priority": 8e-7, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_service_tier": true, + "supports_vision": true, + "provider": "openai" + }, + "gpt-4.1-nano-2025-04-14": { + "cache_read_input_token_cost": 2.5e-8, + "input_cost_per_token": 1e-7, + "input_cost_per_token_batches": 5e-8, + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 4e-7, + "output_cost_per_token_batches": 2e-7, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_service_tier": true, + "supports_vision": true, + "provider": "openai" + }, + "gpt-4.5-preview": { + "cache_read_input_token_cost": 0.0000375, + "input_cost_per_token": 0.000075, + "input_cost_per_token_batches": 0.0000375, + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 0.00015, + "output_cost_per_token_batches": 0.000075, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "openai" + }, + "gpt-4.5-preview-2025-02-27": { + "cache_read_input_token_cost": 0.0000375, + "deprecation_date": "2025-07-14", + "input_cost_per_token": 0.000075, + "input_cost_per_token_batches": 0.0000375, + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 0.00015, + "output_cost_per_token_batches": 0.000075, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "openai" + }, + "gpt-4o": { + "cache_read_input_token_cost": 0.00000125, + "cache_read_input_token_cost_priority": 0.000002125, + "input_cost_per_token": 0.0000025, + "input_cost_per_token_batches": 0.00000125, + "input_cost_per_token_priority": 0.00000425, + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 0.00001, + "output_cost_per_token_batches": 0.000005, + "output_cost_per_token_priority": 0.000017, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_service_tier": true, + "supports_vision": true, + "provider": "openai" + }, + "gpt-4o-2024-05-13": { + "input_cost_per_token": 0.000005, + "input_cost_per_token_batches": 0.0000025, + "input_cost_per_token_priority": 0.00000875, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.000015, + "output_cost_per_token_batches": 0.0000075, + "output_cost_per_token_priority": 0.00002625, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "openai" + }, + "gpt-4o-2024-08-06": { + "cache_read_input_token_cost": 0.00000125, + "input_cost_per_token": 0.0000025, + "input_cost_per_token_batches": 0.00000125, + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 0.00001, + "output_cost_per_token_batches": 0.000005, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_service_tier": true, + "supports_vision": true, + "provider": "openai" + }, + "gpt-4o-2024-11-20": { + "cache_read_input_token_cost": 0.00000125, + "input_cost_per_token": 0.0000025, + "input_cost_per_token_batches": 0.00000125, + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 0.00001, + "output_cost_per_token_batches": 0.000005, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_service_tier": true, + "supports_vision": true, + "provider": "openai" + }, + "gpt-4o-audio-preview": { + "input_cost_per_audio_token": 0.0001, + "input_cost_per_token": 0.0000025, + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_audio_token": 0.0002, + "output_cost_per_token": 0.00001, + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "openai" + }, + "gpt-4o-audio-preview-2024-10-01": { + "input_cost_per_audio_token": 0.0001, + "input_cost_per_token": 0.0000025, + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_audio_token": 0.0002, + "output_cost_per_token": 0.00001, + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "openai" + }, + "gpt-4o-audio-preview-2024-12-17": { + "input_cost_per_audio_token": 0.00004, + "input_cost_per_token": 0.0000025, + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_audio_token": 0.00008, + "output_cost_per_token": 0.00001, + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "openai" + }, + "gpt-4o-audio-preview-2025-06-03": { + "input_cost_per_audio_token": 0.00004, + "input_cost_per_token": 0.0000025, + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_audio_token": 0.00008, + "output_cost_per_token": 0.00001, + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "openai" + }, + "gpt-4o-mini": { + "cache_read_input_token_cost": 7.5e-8, + "cache_read_input_token_cost_priority": 1.25e-7, + "input_cost_per_token": 1.5e-7, + "input_cost_per_token_batches": 7.5e-8, + "input_cost_per_token_priority": 2.5e-7, + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 6e-7, + "output_cost_per_token_batches": 3e-7, + "output_cost_per_token_priority": 0.000001, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_service_tier": true, + "supports_vision": true, + "provider": "openai" + }, + "gpt-4o-mini-2024-07-18": { + "cache_read_input_token_cost": 7.5e-8, + "input_cost_per_token": 1.5e-7, + "input_cost_per_token_batches": 7.5e-8, + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 6e-7, + "output_cost_per_token_batches": 3e-7, + "search_context_cost_per_query": { + "search_context_size_high": 0.03, + "search_context_size_low": 0.025, + "search_context_size_medium": 0.0275 + }, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_service_tier": true, + "supports_vision": true, + "provider": "openai" + }, + "gpt-4o-mini-audio-preview": { + "input_cost_per_audio_token": 0.00001, + "input_cost_per_token": 1.5e-7, + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_audio_token": 0.00002, + "output_cost_per_token": 6e-7, + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "openai" + }, + "gpt-4o-mini-audio-preview-2024-12-17": { + "input_cost_per_audio_token": 0.00001, + "input_cost_per_token": 1.5e-7, + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_audio_token": 0.00002, + "output_cost_per_token": 6e-7, + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "openai" + }, + "gpt-4o-mini-realtime-preview": { + "cache_creation_input_audio_token_cost": 3e-7, + "cache_read_input_token_cost": 3e-7, + "input_cost_per_audio_token": 0.00001, + "input_cost_per_token": 6e-7, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_audio_token": 0.00002, + "output_cost_per_token": 0.0000024, + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "openai" + }, + "gpt-4o-mini-realtime-preview-2024-12-17": { + "cache_creation_input_audio_token_cost": 3e-7, + "cache_read_input_token_cost": 3e-7, + "input_cost_per_audio_token": 0.00001, + "input_cost_per_token": 6e-7, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_audio_token": 0.00002, + "output_cost_per_token": 0.0000024, + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "openai" + }, + "gpt-4o-mini-search-preview": { + "cache_read_input_token_cost": 7.5e-8, + "input_cost_per_token": 1.5e-7, + "input_cost_per_token_batches": 7.5e-8, + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 6e-7, + "output_cost_per_token_batches": 3e-7, + "search_context_cost_per_query": { + "search_context_size_high": 0.03, + "search_context_size_low": 0.025, + "search_context_size_medium": 0.0275 + }, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "provider": "openai" + }, + "gpt-4o-mini-search-preview-2025-03-11": { + "cache_read_input_token_cost": 7.5e-8, + "input_cost_per_token": 1.5e-7, + "input_cost_per_token_batches": 7.5e-8, + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 6e-7, + "output_cost_per_token_batches": 3e-7, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "openai" + }, + "gpt-4o-mini-transcribe": { + "input_cost_per_audio_token": 0.000003, + "input_cost_per_token": 0.00000125, + "max_input_tokens": 16000, + "max_output_tokens": 2000, + "mode": "audio_transcription", + "output_cost_per_token": 0.000005, + "supported_endpoints": ["/v1/audio/transcriptions"], + "provider": "openai" + }, + "gpt-4o-mini-tts": { + "input_cost_per_token": 0.0000025, + "mode": "audio_speech", + "output_cost_per_audio_token": 0.000012, + "output_cost_per_second": 0.00025, + "output_cost_per_token": 0.00001, + "supported_endpoints": ["/v1/audio/speech"], + "supported_modalities": ["text", "audio"], + "supported_output_modalities": ["audio"], + "provider": "openai" + }, + "gpt-4o-realtime-preview": { + "cache_read_input_token_cost": 0.0000025, + "input_cost_per_audio_token": 0.00004, + "input_cost_per_token": 0.000005, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_audio_token": 0.00008, + "output_cost_per_token": 0.00002, + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "openai" + }, + "gpt-4o-realtime-preview-2024-10-01": { + "cache_creation_input_audio_token_cost": 0.00002, + "cache_read_input_token_cost": 0.0000025, + "input_cost_per_audio_token": 0.0001, + "input_cost_per_token": 0.000005, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_audio_token": 0.0002, + "output_cost_per_token": 0.00002, + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "openai" + }, + "gpt-4o-realtime-preview-2024-12-17": { + "cache_read_input_token_cost": 0.0000025, + "input_cost_per_audio_token": 0.00004, + "input_cost_per_token": 0.000005, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_audio_token": 0.00008, + "output_cost_per_token": 0.00002, + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "openai" + }, + "gpt-4o-realtime-preview-2025-06-03": { + "cache_read_input_token_cost": 0.0000025, + "input_cost_per_audio_token": 0.00004, + "input_cost_per_token": 0.000005, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_audio_token": 0.00008, + "output_cost_per_token": 0.00002, + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "openai" + }, + "gpt-4o-search-preview": { + "cache_read_input_token_cost": 0.00000125, + "input_cost_per_token": 0.0000025, + "input_cost_per_token_batches": 0.00000125, + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 0.00001, + "output_cost_per_token_batches": 0.000005, + "search_context_cost_per_query": { + "search_context_size_high": 0.05, + "search_context_size_low": 0.03, + "search_context_size_medium": 0.035 + }, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "provider": "openai" + }, + "gpt-4o-search-preview-2025-03-11": { + "cache_read_input_token_cost": 0.00000125, + "input_cost_per_token": 0.0000025, + "input_cost_per_token_batches": 0.00000125, + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 0.00001, + "output_cost_per_token_batches": 0.000005, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "openai" + }, + "gpt-4o-transcribe": { + "input_cost_per_audio_token": 0.000006, + "input_cost_per_token": 0.0000025, + "max_input_tokens": 16000, + "max_output_tokens": 2000, + "mode": "audio_transcription", + "output_cost_per_token": 0.00001, + "supported_endpoints": ["/v1/audio/transcriptions"], + "provider": "openai" + }, + "gpt-5": { + "cache_read_input_token_cost": 1.25e-7, + "cache_read_input_token_cost_flex": 6.25e-8, + "cache_read_input_token_cost_priority": 2.5e-7, + "input_cost_per_token": 0.00000125, + "input_cost_per_token_flex": 6.25e-7, + "input_cost_per_token_priority": 0.0000025, + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.00001, + "output_cost_per_token_flex": 0.000005, + "output_cost_per_token_priority": 0.00002, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_service_tier": true, + "supports_vision": true, + "provider": "openai" + }, + "gpt-5.1": { + "cache_read_input_token_cost": 1.25e-7, + "cache_read_input_token_cost_priority": 2.5e-7, + "input_cost_per_token": 0.00000125, + "input_cost_per_token_priority": 0.0000025, + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.00001, + "output_cost_per_token_priority": 0.00002, + "supported_endpoints": ["/v1/chat/completions", "/v1/responses"], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text", "image"], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_service_tier": true, + "supports_vision": true, + "provider": "openai" + }, + "gpt-5.1-2025-11-13": { + "cache_read_input_token_cost": 1.25e-7, + "cache_read_input_token_cost_priority": 2.5e-7, + "input_cost_per_token": 0.00000125, + "input_cost_per_token_priority": 0.0000025, + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.00001, + "output_cost_per_token_priority": 0.00002, + "supported_endpoints": ["/v1/chat/completions", "/v1/responses"], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text", "image"], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_service_tier": true, + "supports_vision": true, + "provider": "openai" + }, + "gpt-5.1-chat-latest": { + "cache_read_input_token_cost": 1.25e-7, + "cache_read_input_token_cost_priority": 2.5e-7, + "input_cost_per_token": 0.00000125, + "input_cost_per_token_priority": 0.0000025, + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 0.00001, + "output_cost_per_token_priority": 0.00002, + "supported_endpoints": ["/v1/chat/completions", "/v1/responses"], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text", "image"], + "supports_function_calling": false, + "supports_native_streaming": true, + "supports_parallel_function_calling": false, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": false, + "supports_vision": true, + "provider": "openai" + }, + "gpt-5-pro": { + "input_cost_per_token": 0.000015, + "input_cost_per_token_batches": 0.0000075, + "max_input_tokens": 400000, + "max_output_tokens": 272000, + "max_tokens": 272000, + "mode": "responses", + "output_cost_per_token": 0.00012, + "output_cost_per_token_batches": 0.00006, + "supported_endpoints": ["/v1/batch", "/v1/responses"], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], + "supports_function_calling": true, + "supports_native_streaming": false, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "provider": "openai" + }, + "gpt-5-pro-2025-10-06": { + "input_cost_per_token": 0.000015, + "input_cost_per_token_batches": 0.0000075, + "max_input_tokens": 400000, + "max_output_tokens": 272000, + "max_tokens": 272000, + "mode": "responses", + "output_cost_per_token": 0.00012, + "output_cost_per_token_batches": 0.00006, + "supported_endpoints": ["/v1/batch", "/v1/responses"], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], + "supports_function_calling": true, + "supports_native_streaming": false, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "provider": "openai" + }, + "gpt-5-2025-08-07": { + "cache_read_input_token_cost": 1.25e-7, + "cache_read_input_token_cost_flex": 6.25e-8, + "cache_read_input_token_cost_priority": 2.5e-7, + "input_cost_per_token": 0.00000125, + "input_cost_per_token_flex": 6.25e-7, + "input_cost_per_token_priority": 0.0000025, + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.00001, + "output_cost_per_token_flex": 0.000005, + "output_cost_per_token_priority": 0.00002, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_service_tier": true, + "supports_vision": true, + "provider": "openai" + }, + "gpt-5-chat": { + "cache_read_input_token_cost": 1.25e-7, + "input_cost_per_token": 0.00000125, + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.00001, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], + "supports_function_calling": false, + "supports_native_streaming": true, + "supports_parallel_function_calling": false, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": false, + "supports_vision": true, + "provider": "openai" + }, + "gpt-5-chat-latest": { + "cache_read_input_token_cost": 1.25e-7, + "input_cost_per_token": 0.00000125, + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 0.00001, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], + "supports_function_calling": false, + "supports_native_streaming": true, + "supports_parallel_function_calling": false, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": false, + "supports_vision": true, + "provider": "openai" + }, + "gpt-5-codex": { + "cache_read_input_token_cost": 1.25e-7, + "input_cost_per_token": 0.00000125, + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "responses", + "output_cost_per_token": 0.00001, + "supported_endpoints": ["/v1/responses"], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": false, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "openai" + }, + "gpt-5.1-codex": { + "cache_read_input_token_cost": 1.25e-7, + "cache_read_input_token_cost_priority": 2.5e-7, + "input_cost_per_token": 0.00000125, + "input_cost_per_token_priority": 0.0000025, + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "responses", + "output_cost_per_token": 0.00001, + "output_cost_per_token_priority": 0.00002, + "supported_endpoints": ["/v1/responses"], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": false, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "openai" + }, + "gpt-5.1-codex-mini": { + "cache_read_input_token_cost": 2.5e-8, + "cache_read_input_token_cost_priority": 4.5e-8, + "input_cost_per_token": 2.5e-7, + "input_cost_per_token_priority": 4.5e-7, + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "responses", + "output_cost_per_token": 0.000002, + "output_cost_per_token_priority": 0.0000036, + "supported_endpoints": ["/v1/responses"], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": false, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "openai" + }, + "gpt-5-mini": { + "cache_read_input_token_cost": 2.5e-8, + "cache_read_input_token_cost_flex": 1.25e-8, + "cache_read_input_token_cost_priority": 4.5e-8, + "input_cost_per_token": 2.5e-7, + "input_cost_per_token_flex": 1.25e-7, + "input_cost_per_token_priority": 4.5e-7, + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.000002, + "output_cost_per_token_flex": 0.000001, + "output_cost_per_token_priority": 0.0000036, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_service_tier": true, + "supports_vision": true, + "provider": "openai" + }, + "gpt-5-mini-2025-08-07": { + "cache_read_input_token_cost": 2.5e-8, + "cache_read_input_token_cost_flex": 1.25e-8, + "cache_read_input_token_cost_priority": 4.5e-8, + "input_cost_per_token": 2.5e-7, + "input_cost_per_token_flex": 1.25e-7, + "input_cost_per_token_priority": 4.5e-7, + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.000002, + "output_cost_per_token_flex": 0.000001, + "output_cost_per_token_priority": 0.0000036, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_service_tier": true, + "supports_vision": true, + "provider": "openai" + }, + "gpt-5-nano": { + "cache_read_input_token_cost": 5e-9, + "cache_read_input_token_cost_flex": 2.5e-9, + "input_cost_per_token": 5e-8, + "input_cost_per_token_flex": 2.5e-8, + "input_cost_per_token_priority": 0.0000025, + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4e-7, + "output_cost_per_token_flex": 2e-7, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "openai" + }, + "gpt-5-nano-2025-08-07": { + "cache_read_input_token_cost": 5e-9, + "cache_read_input_token_cost_flex": 2.5e-9, + "input_cost_per_token": 5e-8, + "input_cost_per_token_flex": 2.5e-8, + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4e-7, + "output_cost_per_token_flex": 2e-7, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "openai" + }, + "gpt-image-1": { + "input_cost_per_pixel": 4.0054321e-8, + "mode": "image_generation", + "output_cost_per_pixel": 0, + "supported_endpoints": ["/v1/images/generations"], + "provider": "openai" + }, + "gpt-image-1-mini": { + "cache_read_input_image_token_cost": 2.5e-7, + "cache_read_input_token_cost": 2e-7, + "input_cost_per_image_token": 0.0000025, + "input_cost_per_token": 0.000002, + "mode": "chat", + "output_cost_per_image_token": 0.000008, + "supported_endpoints": ["/v1/images/generations", "/v1/images/edits"], + "provider": "openai" + }, + "gpt-realtime": { + "cache_creation_input_audio_token_cost": 4e-7, + "cache_read_input_token_cost": 4e-7, + "input_cost_per_audio_token": 0.000032, + "input_cost_per_image": 0.000005, + "input_cost_per_token": 0.000004, + "max_input_tokens": 32000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_audio_token": 0.000064, + "output_cost_per_token": 0.000016, + "supported_endpoints": ["/v1/realtime"], + "supported_modalities": ["text", "image", "audio"], + "supported_output_modalities": ["text", "audio"], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "openai" + }, + "gpt-realtime-mini": { + "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_token": 6e-7, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_audio_token": 0.00002, + "output_cost_per_token": 0.0000024, + "supported_endpoints": ["/v1/realtime"], + "supported_modalities": ["text", "image", "audio"], + "supported_output_modalities": ["text", "audio"], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "openai" + }, + "gpt-realtime-2025-08-28": { + "cache_creation_input_audio_token_cost": 4e-7, + "cache_read_input_token_cost": 4e-7, + "input_cost_per_audio_token": 0.000032, + "input_cost_per_image": 0.000005, + "input_cost_per_token": 0.000004, + "max_input_tokens": 32000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_audio_token": 0.000064, + "output_cost_per_token": 0.000016, + "supported_endpoints": ["/v1/realtime"], + "supported_modalities": ["text", "image", "audio"], + "supported_output_modalities": ["text", "audio"], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "openai" + }, + "gradient_ai/alibaba-qwen3-32b": { + "max_tokens": 2048, + "mode": "chat", + "supported_endpoints": ["/v1/chat/completions"], + "supported_modalities": ["text"], + "supports_tool_choice": false, + "provider": "gradient_ai" + }, + "gradient_ai/anthropic-claude-3-opus": { + "input_cost_per_token": 0.000015, + "max_tokens": 1024, + "mode": "chat", + "output_cost_per_token": 0.000075, + "supported_endpoints": ["/v1/chat/completions"], + "supported_modalities": ["text"], + "supports_tool_choice": false, + "provider": "gradient_ai" + }, + "gradient_ai/anthropic-claude-3.5-haiku": { + "input_cost_per_token": 8e-7, + "max_tokens": 1024, + "mode": "chat", + "output_cost_per_token": 0.000004, + "supported_endpoints": ["/v1/chat/completions"], + "supported_modalities": ["text"], + "supports_tool_choice": false, + "provider": "gradient_ai" + }, + "gradient_ai/anthropic-claude-3.5-sonnet": { + "input_cost_per_token": 0.000003, + "max_tokens": 1024, + "mode": "chat", + "output_cost_per_token": 0.000015, + "supported_endpoints": ["/v1/chat/completions"], + "supported_modalities": ["text"], + "supports_tool_choice": false, + "provider": "gradient_ai" + }, + "gradient_ai/anthropic-claude-3.7-sonnet": { + "input_cost_per_token": 0.000003, + "max_tokens": 1024, + "mode": "chat", + "output_cost_per_token": 0.000015, + "supported_endpoints": ["/v1/chat/completions"], + "supported_modalities": ["text"], + "supports_tool_choice": false, + "provider": "gradient_ai" + }, + "gradient_ai/deepseek-r1-distill-llama-70b": { + "input_cost_per_token": 9.9e-7, + "max_tokens": 8000, + "mode": "chat", + "output_cost_per_token": 9.9e-7, + "supported_endpoints": ["/v1/chat/completions"], + "supported_modalities": ["text"], + "supports_tool_choice": false, + "provider": "gradient_ai" + }, + "gradient_ai/llama3-8b-instruct": { + "input_cost_per_token": 2e-7, + "max_tokens": 512, + "mode": "chat", + "output_cost_per_token": 2e-7, + "supported_endpoints": ["/v1/chat/completions"], + "supported_modalities": ["text"], + "supports_tool_choice": false, + "provider": "gradient_ai" + }, + "gradient_ai/llama3.3-70b-instruct": { + "input_cost_per_token": 6.5e-7, + "max_tokens": 2048, + "mode": "chat", + "output_cost_per_token": 6.5e-7, + "supported_endpoints": ["/v1/chat/completions"], + "supported_modalities": ["text"], + "supports_tool_choice": false, + "provider": "gradient_ai" + }, + "gradient_ai/mistral-nemo-instruct-2407": { + "input_cost_per_token": 3e-7, + "max_tokens": 512, + "mode": "chat", + "output_cost_per_token": 3e-7, + "supported_endpoints": ["/v1/chat/completions"], + "supported_modalities": ["text"], + "supports_tool_choice": false, + "provider": "gradient_ai" + }, + "gradient_ai/openai-gpt-4o": { + "max_tokens": 16384, + "mode": "chat", + "supported_endpoints": ["/v1/chat/completions"], + "supported_modalities": ["text"], + "supports_tool_choice": false, + "provider": "gradient_ai" + }, + "gradient_ai/openai-gpt-4o-mini": { + "max_tokens": 16384, + "mode": "chat", + "supported_endpoints": ["/v1/chat/completions"], + "supported_modalities": ["text"], + "supports_tool_choice": false, + "provider": "gradient_ai" + }, + "gradient_ai/openai-o3": { + "input_cost_per_token": 0.000002, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 0.000008, + "supported_endpoints": ["/v1/chat/completions"], + "supported_modalities": ["text"], + "supports_tool_choice": false, + "provider": "gradient_ai" + }, + "gradient_ai/openai-o3-mini": { + "input_cost_per_token": 0.0000011, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 0.0000044, + "supported_endpoints": ["/v1/chat/completions"], + "supported_modalities": ["text"], + "supports_tool_choice": false, + "provider": "gradient_ai" + }, + "lemonade/Qwen3-Coder-30B-A3B-Instruct-GGUF": { + "input_cost_per_token": 0, + "max_tokens": 262144, + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "provider": "lemonade" + }, + "lemonade/gpt-oss-20b-mxfp4-GGUF": { + "input_cost_per_token": 0, + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "provider": "lemonade" + }, + "lemonade/gpt-oss-120b-mxfp-GGUF": { + "input_cost_per_token": 0, + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "provider": "lemonade" + }, + "lemonade/Gemma-3-4b-it-GGUF": { + "input_cost_per_token": 0, + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "provider": "lemonade" + }, + "lemonade/Qwen3-4B-Instruct-2507-GGUF": { + "input_cost_per_token": 0, + "max_tokens": 262144, + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "provider": "lemonade" + }, + "groq/deepseek-r1-distill-llama-70b": { + "input_cost_per_token": 7.5e-7, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 9.9e-7, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "provider": "groq" + }, + "groq/distil-whisper-large-v3-en": { + "input_cost_per_second": 0.00000556, + "mode": "audio_transcription", + "output_cost_per_second": 0, + "provider": "groq" + }, + "groq/gemma-7b-it": { + "deprecation_date": "2024-12-18", + "input_cost_per_token": 7e-8, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 7e-8, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "provider": "groq" + }, + "groq/gemma2-9b-it": { + "input_cost_per_token": 2e-7, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2e-7, + "supports_function_calling": false, + "supports_response_schema": true, + "supports_tool_choice": false, + "provider": "groq" + }, + "groq/llama-3.1-405b-reasoning": { + "input_cost_per_token": 5.9e-7, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 7.9e-7, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "provider": "groq" + }, + "groq/llama-3.1-70b-versatile": { + "deprecation_date": "2025-01-24", + "input_cost_per_token": 5.9e-7, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 7.9e-7, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "provider": "groq" + }, + "groq/llama-3.1-8b-instant": { + "input_cost_per_token": 5e-8, + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 8e-8, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "provider": "groq" + }, + "groq/llama-3.2-11b-text-preview": { + "deprecation_date": "2024-10-28", + "input_cost_per_token": 1.8e-7, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.8e-7, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "provider": "groq" + }, + "groq/llama-3.2-11b-vision-preview": { + "deprecation_date": "2025-04-14", + "input_cost_per_token": 1.8e-7, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.8e-7, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "groq" + }, + "groq/llama-3.2-1b-preview": { + "deprecation_date": "2025-04-14", + "input_cost_per_token": 4e-8, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 4e-8, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "provider": "groq" + }, + "groq/llama-3.2-3b-preview": { + "deprecation_date": "2025-04-14", + "input_cost_per_token": 6e-8, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 6e-8, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "provider": "groq" + }, + "groq/llama-3.2-90b-text-preview": { + "deprecation_date": "2024-11-25", + "input_cost_per_token": 9e-7, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 9e-7, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "provider": "groq" + }, + "groq/llama-3.2-90b-vision-preview": { + "deprecation_date": "2025-04-14", + "input_cost_per_token": 9e-7, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 9e-7, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "groq" + }, + "groq/llama-3.3-70b-specdec": { + "deprecation_date": "2025-04-14", + "input_cost_per_token": 5.9e-7, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 9.9e-7, + "supports_tool_choice": true, + "provider": "groq" + }, + "groq/llama-3.3-70b-versatile": { + "input_cost_per_token": 5.9e-7, + "max_input_tokens": 128000, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 7.9e-7, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "provider": "groq" + }, + "groq/llama-guard-3-8b": { + "input_cost_per_token": 2e-7, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2e-7, + "provider": "groq" + }, + "groq/llama2-70b-4096": { + "input_cost_per_token": 7e-7, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 8e-7, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "provider": "groq" + }, + "groq/llama3-groq-70b-8192-tool-use-preview": { + "deprecation_date": "2025-01-06", + "input_cost_per_token": 8.9e-7, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 8.9e-7, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "provider": "groq" + }, + "groq/llama3-groq-8b-8192-tool-use-preview": { + "deprecation_date": "2025-01-06", + "input_cost_per_token": 1.9e-7, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.9e-7, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "provider": "groq" + }, + "groq/meta-llama/llama-4-maverick-17b-128e-instruct": { + "input_cost_per_token": 2e-7, + "max_input_tokens": 131072, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 6e-7, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "provider": "groq" + }, + "groq/meta-llama/llama-4-scout-17b-16e-instruct": { + "input_cost_per_token": 1.1e-7, + "max_input_tokens": 131072, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 3.4e-7, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "provider": "groq" + }, + "groq/mistral-saba-24b": { + "input_cost_per_token": 7.9e-7, + "max_input_tokens": 32000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 7.9e-7, + "provider": "groq" + }, + "groq/mixtral-8x7b-32768": { + "deprecation_date": "2025-03-20", + "input_cost_per_token": 2.4e-7, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 2.4e-7, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "provider": "groq" + }, + "groq/moonshotai/kimi-k2-instruct": { + "input_cost_per_token": 0.000001, + "max_input_tokens": 131072, + "max_output_tokens": 16384, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 0.000003, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "provider": "groq" + }, + "groq/moonshotai/kimi-k2-instruct-0905": { + "input_cost_per_token": 0.000001, + "output_cost_per_token": 0.000003, + "cache_read_input_token_cost": 5e-7, + "max_input_tokens": 262144, + "max_output_tokens": 16384, + "max_tokens": 278528, + "mode": "chat", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "provider": "groq" + }, + "groq/openai/gpt-oss-120b": { + "input_cost_per_token": 1.5e-7, + "max_input_tokens": 131072, + "max_output_tokens": 32766, + "max_tokens": 32766, + "mode": "chat", + "output_cost_per_token": 7.5e-7, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_web_search": true, + "provider": "groq" + }, + "groq/openai/gpt-oss-20b": { + "input_cost_per_token": 1e-7, + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 5e-7, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_web_search": true, + "provider": "groq" + }, + "groq/playai-tts": { + "input_cost_per_character": 0.00005, + "max_input_tokens": 10000, + "max_output_tokens": 10000, + "max_tokens": 10000, + "mode": "audio_speech", + "provider": "groq" + }, + "groq/qwen/qwen3-32b": { + "input_cost_per_token": 2.9e-7, + "max_input_tokens": 131000, + "max_output_tokens": 131000, + "max_tokens": 131000, + "mode": "chat", + "output_cost_per_token": 5.9e-7, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "provider": "groq" + }, + "groq/whisper-large-v3": { + "input_cost_per_second": 0.00003083, + "mode": "audio_transcription", + "output_cost_per_second": 0, + "provider": "groq" + }, + "groq/whisper-large-v3-turbo": { + "input_cost_per_second": 0.00001111, + "mode": "audio_transcription", + "output_cost_per_second": 0, + "provider": "groq" + }, + "hd/1024-x-1024/dall-e-3": { + "input_cost_per_pixel": 7.629e-8, + "mode": "image_generation", + "output_cost_per_pixel": 0, + "provider": "openai" + }, + "hd/1024-x-1792/dall-e-3": { + "input_cost_per_pixel": 6.539e-8, + "mode": "image_generation", + "output_cost_per_pixel": 0, + "provider": "openai" + }, + "hd/1792-x-1024/dall-e-3": { + "input_cost_per_pixel": 6.539e-8, + "mode": "image_generation", + "output_cost_per_pixel": 0, + "provider": "openai" + }, + "heroku/claude-3-5-haiku": { + "max_tokens": 4096, + "mode": "chat", + "supports_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "heroku" + }, + "heroku/claude-3-5-sonnet-latest": { + "max_tokens": 8192, + "mode": "chat", + "supports_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "heroku" + }, + "heroku/claude-3-7-sonnet": { + "max_tokens": 8192, + "mode": "chat", + "supports_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "heroku" + }, + "heroku/claude-4-sonnet": { + "max_tokens": 8192, + "mode": "chat", + "supports_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "heroku" + }, + "high/1024-x-1024/gpt-image-1": { + "input_cost_per_pixel": 1.59263611e-7, + "mode": "image_generation", + "output_cost_per_pixel": 0, + "supported_endpoints": ["/v1/images/generations"], + "provider": "openai" + }, + "high/1024-x-1536/gpt-image-1": { + "input_cost_per_pixel": 1.58945719e-7, + "mode": "image_generation", + "output_cost_per_pixel": 0, + "supported_endpoints": ["/v1/images/generations"], + "provider": "openai" + }, + "high/1536-x-1024/gpt-image-1": { + "input_cost_per_pixel": 1.58945719e-7, + "mode": "image_generation", + "output_cost_per_pixel": 0, + "supported_endpoints": ["/v1/images/generations"], + "provider": "openai" + }, + "hyperbolic/NousResearch/Hermes-3-Llama-3.1-70B": { + "input_cost_per_token": 1.2e-7, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 3e-7, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "hyperbolic" + }, + "hyperbolic/Qwen/QwQ-32B": { + "input_cost_per_token": 2e-7, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2e-7, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "hyperbolic" + }, + "hyperbolic/Qwen/Qwen2.5-72B-Instruct": { + "input_cost_per_token": 1.2e-7, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 3e-7, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "hyperbolic" + }, + "hyperbolic/Qwen/Qwen2.5-Coder-32B-Instruct": { + "input_cost_per_token": 1.2e-7, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 3e-7, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "hyperbolic" + }, + "hyperbolic/Qwen/Qwen3-235B-A22B": { + "input_cost_per_token": 0.000002, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 0.000002, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "hyperbolic" + }, + "hyperbolic/deepseek-ai/DeepSeek-R1": { + "input_cost_per_token": 4e-7, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 4e-7, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "hyperbolic" + }, + "hyperbolic/deepseek-ai/DeepSeek-R1-0528": { + "input_cost_per_token": 2.5e-7, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.5e-7, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "hyperbolic" + }, + "hyperbolic/deepseek-ai/DeepSeek-V3": { + "input_cost_per_token": 2e-7, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 2e-7, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "hyperbolic" + }, + "hyperbolic/deepseek-ai/DeepSeek-V3-0324": { + "input_cost_per_token": 4e-7, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 4e-7, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "hyperbolic" + }, + "hyperbolic/meta-llama/Llama-3.2-3B-Instruct": { + "input_cost_per_token": 1.2e-7, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 3e-7, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "hyperbolic" + }, + "hyperbolic/meta-llama/Llama-3.3-70B-Instruct": { + "input_cost_per_token": 1.2e-7, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 3e-7, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "hyperbolic" + }, + "hyperbolic/meta-llama/Meta-Llama-3-70B-Instruct": { + "input_cost_per_token": 1.2e-7, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 3e-7, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "hyperbolic" + }, + "hyperbolic/meta-llama/Meta-Llama-3.1-405B-Instruct": { + "input_cost_per_token": 1.2e-7, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 3e-7, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "hyperbolic" + }, + "hyperbolic/meta-llama/Meta-Llama-3.1-70B-Instruct": { + "input_cost_per_token": 1.2e-7, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 3e-7, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "hyperbolic" + }, + "hyperbolic/meta-llama/Meta-Llama-3.1-8B-Instruct": { + "input_cost_per_token": 1.2e-7, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 3e-7, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "hyperbolic" + }, + "hyperbolic/moonshotai/Kimi-K2-Instruct": { + "input_cost_per_token": 0.000002, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 0.000002, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "hyperbolic" + }, + "j2-light": { + "input_cost_per_token": 0.000003, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "completion", + "output_cost_per_token": 0.000003, + "provider": "ai21" + }, + "j2-mid": { + "input_cost_per_token": 0.00001, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "completion", + "output_cost_per_token": 0.00001, + "provider": "ai21" + }, + "j2-ultra": { + "input_cost_per_token": 0.000015, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "completion", + "output_cost_per_token": 0.000015, + "provider": "ai21" + }, + "jamba-1.5": { + "input_cost_per_token": 2e-7, + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 4e-7, + "supports_tool_choice": true, + "provider": "ai21" + }, + "jamba-1.5-large": { + "input_cost_per_token": 0.000002, + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 0.000008, + "supports_tool_choice": true, + "provider": "ai21" + }, + "jamba-1.5-large@001": { + "input_cost_per_token": 0.000002, + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 0.000008, + "supports_tool_choice": true, + "provider": "ai21" + }, + "jamba-1.5-mini": { + "input_cost_per_token": 2e-7, + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 4e-7, + "supports_tool_choice": true, + "provider": "ai21" + }, + "jamba-1.5-mini@001": { + "input_cost_per_token": 2e-7, + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 4e-7, + "supports_tool_choice": true, + "provider": "ai21" + }, + "jamba-large-1.6": { + "input_cost_per_token": 0.000002, + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 0.000008, + "supports_tool_choice": true, + "provider": "ai21" + }, + "jamba-large-1.7": { + "input_cost_per_token": 0.000002, + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 0.000008, + "supports_tool_choice": true, + "provider": "ai21" + }, + "jamba-mini-1.6": { + "input_cost_per_token": 2e-7, + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 4e-7, + "supports_tool_choice": true, + "provider": "ai21" + }, + "jamba-mini-1.7": { + "input_cost_per_token": 2e-7, + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 4e-7, + "supports_tool_choice": true, + "provider": "ai21" + }, + "jina-reranker-v2-base-multilingual": { + "input_cost_per_token": 1.8e-8, + "max_document_chunks_per_query": 2048, + "max_input_tokens": 1024, + "max_output_tokens": 1024, + "max_tokens": 1024, + "mode": "rerank", + "output_cost_per_token": 1.8e-8, + "provider": "jina_ai" + }, + "jp.anthropic.claude-sonnet-4-5-20250929-v1:0": { + "cache_creation_input_token_cost": 0.000004125, + "cache_read_input_token_cost": 3.3e-7, + "input_cost_per_token": 0.0000033, + "input_cost_per_token_above_200k_tokens": 0.0000066, + "output_cost_per_token_above_200k_tokens": 0.00002475, + "cache_creation_input_token_cost_above_200k_tokens": 0.00000825, + "cache_read_input_token_cost_above_200k_tokens": 6.6e-7, + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 0.0000165, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 346, + "provider": "bedrock_converse" + }, + "jp.anthropic.claude-haiku-4-5-20251001-v1:0": { + "cache_creation_input_token_cost": 0.000001375, + "cache_read_input_token_cost": 1.1e-7, + "input_cost_per_token": 0.0000011, + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 0.0000055, + "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock", + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 346, + "provider": "bedrock_converse" + }, + "lambda_ai/deepseek-llama3.3-70b": { + "input_cost_per_token": 2e-7, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 6e-7, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "lambda_ai" + }, + "lambda_ai/deepseek-r1-0528": { + "input_cost_per_token": 2e-7, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 6e-7, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "lambda_ai" + }, + "lambda_ai/deepseek-r1-671b": { + "input_cost_per_token": 8e-7, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 8e-7, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "lambda_ai" + }, + "lambda_ai/deepseek-v3-0324": { + "input_cost_per_token": 2e-7, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 6e-7, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "lambda_ai" + }, + "lambda_ai/hermes3-405b": { + "input_cost_per_token": 8e-7, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 8e-7, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "lambda_ai" + }, + "lambda_ai/hermes3-70b": { + "input_cost_per_token": 1.2e-7, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 3e-7, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "lambda_ai" + }, + "lambda_ai/hermes3-8b": { + "input_cost_per_token": 2.5e-8, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4e-8, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "lambda_ai" + }, + "lambda_ai/lfm-40b": { + "input_cost_per_token": 1e-7, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2e-7, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "lambda_ai" + }, + "lambda_ai/lfm-7b": { + "input_cost_per_token": 2.5e-8, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4e-8, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "lambda_ai" + }, + "lambda_ai/llama-4-maverick-17b-128e-instruct-fp8": { + "input_cost_per_token": 5e-8, + "max_input_tokens": 131072, + "max_output_tokens": 8192, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1e-7, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "lambda_ai" + }, + "lambda_ai/llama-4-scout-17b-16e-instruct": { + "input_cost_per_token": 5e-8, + "max_input_tokens": 16384, + "max_output_tokens": 8192, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1e-7, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "lambda_ai" + }, + "lambda_ai/llama3.1-405b-instruct-fp8": { + "input_cost_per_token": 8e-7, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 8e-7, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "lambda_ai" + }, + "lambda_ai/llama3.1-70b-instruct-fp8": { + "input_cost_per_token": 1.2e-7, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 3e-7, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "lambda_ai" + }, + "lambda_ai/llama3.1-8b-instruct": { + "input_cost_per_token": 2.5e-8, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4e-8, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "lambda_ai" + }, + "lambda_ai/llama3.1-nemotron-70b-instruct-fp8": { + "input_cost_per_token": 1.2e-7, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 3e-7, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "lambda_ai" + }, + "lambda_ai/llama3.2-11b-vision-instruct": { + "input_cost_per_token": 1.5e-8, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.5e-8, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "lambda_ai" + }, + "lambda_ai/llama3.2-3b-instruct": { + "input_cost_per_token": 1.5e-8, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.5e-8, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "lambda_ai" + }, + "lambda_ai/llama3.3-70b-instruct-fp8": { + "input_cost_per_token": 1.2e-7, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 3e-7, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "lambda_ai" + }, + "lambda_ai/qwen25-coder-32b-instruct": { + "input_cost_per_token": 5e-8, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1e-7, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "lambda_ai" + }, + "lambda_ai/qwen3-32b-fp8": { + "input_cost_per_token": 5e-8, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1e-7, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "provider": "lambda_ai" + }, + "low/1024-x-1024/gpt-image-1": { + "input_cost_per_pixel": 1.0490417e-8, + "mode": "image_generation", + "output_cost_per_pixel": 0, + "supported_endpoints": ["/v1/images/generations"], + "provider": "openai" + }, + "low/1024-x-1536/gpt-image-1": { + "input_cost_per_pixel": 1.0172526e-8, + "mode": "image_generation", + "output_cost_per_pixel": 0, + "supported_endpoints": ["/v1/images/generations"], + "provider": "openai" + }, + "low/1536-x-1024/gpt-image-1": { + "input_cost_per_pixel": 1.0172526e-8, + "mode": "image_generation", + "output_cost_per_pixel": 0, + "supported_endpoints": ["/v1/images/generations"], + "provider": "openai" + }, + "luminous-base": { + "input_cost_per_token": 0.00003, + "max_tokens": 2048, + "mode": "completion", + "output_cost_per_token": 0.000033, + "provider": "aleph_alpha" + }, + "luminous-base-control": { + "input_cost_per_token": 0.0000375, + "max_tokens": 2048, + "mode": "chat", + "output_cost_per_token": 0.00004125, + "provider": "aleph_alpha" + }, + "luminous-extended": { + "input_cost_per_token": 0.000045, + "max_tokens": 2048, + "mode": "completion", + "output_cost_per_token": 0.0000495, + "provider": "aleph_alpha" + }, + "luminous-extended-control": { + "input_cost_per_token": 0.00005625, + "max_tokens": 2048, + "mode": "chat", + "output_cost_per_token": 0.000061875, + "provider": "aleph_alpha" + }, + "luminous-supreme": { + "input_cost_per_token": 0.000175, + "max_tokens": 2048, + "mode": "completion", + "output_cost_per_token": 0.0001925, + "provider": "aleph_alpha" + }, + "luminous-supreme-control": { + "input_cost_per_token": 0.00021875, + "max_tokens": 2048, + "mode": "chat", + "output_cost_per_token": 0.000240625, + "provider": "aleph_alpha" + }, + "max-x-max/50-steps/stability.stable-diffusion-xl-v0": { + "max_input_tokens": 77, + "max_tokens": 77, + "mode": "image_generation", + "output_cost_per_image": 0.036, + "provider": "bedrock" + }, + "max-x-max/max-steps/stability.stable-diffusion-xl-v0": { + "max_input_tokens": 77, + "max_tokens": 77, + "mode": "image_generation", + "output_cost_per_image": 0.072, + "provider": "bedrock" + }, + "medium/1024-x-1024/gpt-image-1": { + "input_cost_per_pixel": 4.0054321e-8, + "mode": "image_generation", + "output_cost_per_pixel": 0, + "supported_endpoints": ["/v1/images/generations"], + "provider": "openai" + }, + "medium/1024-x-1536/gpt-image-1": { + "input_cost_per_pixel": 4.0054321e-8, + "mode": "image_generation", + "output_cost_per_pixel": 0, + "supported_endpoints": ["/v1/images/generations"], + "provider": "openai" + }, + "medium/1536-x-1024/gpt-image-1": { + "input_cost_per_pixel": 4.0054321e-8, + "mode": "image_generation", + "output_cost_per_pixel": 0, + "supported_endpoints": ["/v1/images/generations"], + "provider": "openai" + }, + "low/1024-x-1024/gpt-image-1-mini": { + "input_cost_per_image": 0.005, + "mode": "image_generation", + "supported_endpoints": ["/v1/images/generations"], + "provider": "openai" + }, + "low/1024-x-1536/gpt-image-1-mini": { + "input_cost_per_image": 0.006, + "mode": "image_generation", + "supported_endpoints": ["/v1/images/generations"], + "provider": "openai" + }, + "low/1536-x-1024/gpt-image-1-mini": { + "input_cost_per_image": 0.006, + "mode": "image_generation", + "supported_endpoints": ["/v1/images/generations"], + "provider": "openai" + }, + "medium/1024-x-1024/gpt-image-1-mini": { + "input_cost_per_image": 0.011, + "mode": "image_generation", + "supported_endpoints": ["/v1/images/generations"], + "provider": "openai" + }, + "medium/1024-x-1536/gpt-image-1-mini": { + "input_cost_per_image": 0.015, + "mode": "image_generation", + "supported_endpoints": ["/v1/images/generations"], + "provider": "openai" + }, + "medium/1536-x-1024/gpt-image-1-mini": { + "input_cost_per_image": 0.015, + "mode": "image_generation", + "supported_endpoints": ["/v1/images/generations"], + "provider": "openai" + }, + "medlm-large": { + "input_cost_per_character": 0.000005, + "max_input_tokens": 8192, + "max_output_tokens": 1024, + "max_tokens": 1024, + "mode": "chat", + "output_cost_per_character": 0.000015, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "supports_tool_choice": true, + "provider": "vertex_ai-language-models" + }, + "medlm-medium": { + "input_cost_per_character": 5e-7, + "max_input_tokens": 32768, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_character": 0.000001, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "supports_tool_choice": true, + "provider": "vertex_ai-language-models" + }, + "meta.llama2-13b-chat-v1": { + "input_cost_per_token": 7.5e-7, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.000001, + "provider": "bedrock" + }, + "meta.llama2-70b-chat-v1": { + "input_cost_per_token": 0.00000195, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.00000256, + "provider": "bedrock" + }, + "meta.llama3-1-405b-instruct-v1:0": { + "input_cost_per_token": 0.00000532, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.000016, + "supports_function_calling": true, + "supports_tool_choice": false, + "provider": "bedrock" + }, + "meta.llama3-1-70b-instruct-v1:0": { + "input_cost_per_token": 9.9e-7, + "max_input_tokens": 128000, + "max_output_tokens": 2048, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 9.9e-7, + "supports_function_calling": true, + "supports_tool_choice": false, + "provider": "bedrock" + }, + "meta.llama3-1-8b-instruct-v1:0": { + "input_cost_per_token": 2.2e-7, + "max_input_tokens": 128000, + "max_output_tokens": 2048, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.2e-7, + "supports_function_calling": true, + "supports_tool_choice": false, + "provider": "bedrock" + }, + "meta.llama3-2-11b-instruct-v1:0": { + "input_cost_per_token": 3.5e-7, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3.5e-7, + "supports_function_calling": true, + "supports_tool_choice": false, + "supports_vision": true, + "provider": "bedrock" + }, + "meta.llama3-2-1b-instruct-v1:0": { + "input_cost_per_token": 1e-7, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-7, + "supports_function_calling": true, + "supports_tool_choice": false, + "provider": "bedrock" + }, + "meta.llama3-2-3b-instruct-v1:0": { + "input_cost_per_token": 1.5e-7, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.5e-7, + "supports_function_calling": true, + "supports_tool_choice": false, + "provider": "bedrock" + }, + "meta.llama3-2-90b-instruct-v1:0": { + "input_cost_per_token": 0.000002, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.000002, + "supports_function_calling": true, + "supports_tool_choice": false, + "supports_vision": true, + "provider": "bedrock" + }, + "meta.llama3-3-70b-instruct-v1:0": { + "input_cost_per_token": 7.2e-7, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 7.2e-7, + "supports_function_calling": true, + "supports_tool_choice": false, + "provider": "bedrock_converse" + }, + "meta.llama3-70b-instruct-v1:0": { + "input_cost_per_token": 0.00000265, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.0000035, + "provider": "bedrock" + }, + "meta.llama3-8b-instruct-v1:0": { + "input_cost_per_token": 3e-7, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 6e-7, + "provider": "bedrock" + }, + "meta.llama4-maverick-17b-instruct-v1:0": { + "input_cost_per_token": 2.4e-7, + "input_cost_per_token_batches": 1.2e-7, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 9.7e-7, + "output_cost_per_token_batches": 4.85e-7, + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text", "code"], + "supports_function_calling": true, + "supports_tool_choice": false, + "provider": "bedrock_converse" + }, + "meta.llama4-scout-17b-instruct-v1:0": { + "input_cost_per_token": 1.7e-7, + "input_cost_per_token_batches": 8.5e-8, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 6.6e-7, + "output_cost_per_token_batches": 3.3e-7, + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text", "code"], + "supports_function_calling": true, + "supports_tool_choice": false, + "provider": "bedrock_converse" + }, + "meta_llama/Llama-3.3-70B-Instruct": { + "max_input_tokens": 128000, + "max_output_tokens": 4028, + "max_tokens": 128000, + "mode": "chat", + "source": "https://llama.developer.meta.com/docs/models", + "supported_modalities": ["text"], + "supported_output_modalities": ["text"], + "supports_function_calling": true, + "supports_tool_choice": true, + "provider": "meta_llama" + }, + "meta_llama/Llama-3.3-8B-Instruct": { + "max_input_tokens": 128000, + "max_output_tokens": 4028, + "max_tokens": 128000, + "mode": "chat", + "source": "https://llama.developer.meta.com/docs/models", + "supported_modalities": ["text"], + "supported_output_modalities": ["text"], + "supports_function_calling": true, + "supports_tool_choice": true, + "provider": "meta_llama" + }, + "meta_llama/Llama-4-Maverick-17B-128E-Instruct-FP8": { + "max_input_tokens": 1000000, + "max_output_tokens": 4028, + "max_tokens": 128000, + "mode": "chat", + "source": "https://llama.developer.meta.com/docs/models", + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], + "supports_function_calling": true, + "supports_tool_choice": true, + "provider": "meta_llama" + }, + "meta_llama/Llama-4-Scout-17B-16E-Instruct-FP8": { + "max_input_tokens": 10000000, + "max_output_tokens": 4028, + "max_tokens": 128000, + "mode": "chat", + "source": "https://llama.developer.meta.com/docs/models", + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], + "supports_function_calling": true, + "supports_tool_choice": true, + "provider": "meta_llama" + }, + "mistral.mistral-7b-instruct-v0:2": { + "input_cost_per_token": 1.5e-7, + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 2e-7, + "supports_tool_choice": true, + "provider": "bedrock" + }, + "mistral.mistral-large-2402-v1:0": { + "input_cost_per_token": 0.000008, + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 0.000024, + "supports_function_calling": true, + "provider": "bedrock" + }, + "mistral.mistral-large-2407-v1:0": { + "input_cost_per_token": 0.000003, + "max_input_tokens": 128000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 0.000009, + "supports_function_calling": true, + "supports_tool_choice": true, + "provider": "bedrock" + }, + "mistral.mistral-small-2402-v1:0": { + "input_cost_per_token": 0.000001, + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 0.000003, + "supports_function_calling": true, + "provider": "bedrock" + }, + "mistral.mixtral-8x7b-instruct-v0:1": { + "input_cost_per_token": 4.5e-7, + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 7e-7, + "supports_tool_choice": true, + "provider": "bedrock" + }, + "mistral/codestral-2405": { + "input_cost_per_token": 0.000001, + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 0.000003, + "supports_assistant_prefill": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "provider": "mistral" + }, + "mistral/codestral-latest": { + "input_cost_per_token": 0.000001, + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 0.000003, + "supports_assistant_prefill": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "provider": "mistral" + }, + "mistral/codestral-mamba-latest": { + "input_cost_per_token": 2.5e-7, + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 2.5e-7, + "source": "https://mistral.ai/technology/", + "supports_assistant_prefill": true, + "supports_tool_choice": true, + "provider": "mistral" + }, + "mistral/devstral-medium-2507": { + "input_cost_per_token": 4e-7, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.000002, + "source": "https://mistral.ai/news/devstral", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "provider": "mistral" + }, + "mistral/devstral-small-2505": { + "input_cost_per_token": 1e-7, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3e-7, + "source": "https://mistral.ai/news/devstral", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "provider": "mistral" + }, + "mistral/devstral-small-2507": { + "input_cost_per_token": 1e-7, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3e-7, + "source": "https://mistral.ai/news/devstral", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "provider": "mistral" + }, + "mistral/magistral-medium-2506": { + "input_cost_per_token": 0.000002, + "max_input_tokens": 40000, + "max_output_tokens": 40000, + "max_tokens": 40000, + "mode": "chat", + "output_cost_per_token": 0.000005, + "source": "https://mistral.ai/news/magistral", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "provider": "mistral" + }, + "mistral/magistral-medium-2509": { + "input_cost_per_token": 0.000002, + "max_input_tokens": 40000, + "max_output_tokens": 40000, + "max_tokens": 40000, + "mode": "chat", + "output_cost_per_token": 0.000005, + "source": "https://mistral.ai/news/magistral", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "provider": "mistral" + }, + "mistral/mistral-ocr-latest": { + "ocr_cost_per_page": 0.001, + "annotation_cost_per_page": 0.003, + "mode": "ocr", + "supported_endpoints": ["/v1/ocr"], + "source": "https://mistral.ai/pricing#api-pricing", + "provider": "mistral" + }, + "mistral/mistral-ocr-2505-completion": { + "ocr_cost_per_page": 0.001, + "annotation_cost_per_page": 0.003, + "mode": "ocr", + "supported_endpoints": ["/v1/ocr"], + "source": "https://mistral.ai/pricing#api-pricing", + "provider": "mistral" + }, + "mistral/magistral-medium-latest": { + "input_cost_per_token": 0.000002, + "max_input_tokens": 40000, + "max_output_tokens": 40000, + "max_tokens": 40000, + "mode": "chat", + "output_cost_per_token": 0.000005, + "source": "https://mistral.ai/news/magistral", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "provider": "mistral" + }, + "mistral/magistral-small-2506": { + "input_cost_per_token": 5e-7, + "max_input_tokens": 40000, + "max_output_tokens": 40000, + "max_tokens": 40000, + "mode": "chat", + "output_cost_per_token": 0.0000015, + "source": "https://mistral.ai/pricing#api-pricing", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "provider": "mistral" + }, + "mistral/magistral-small-latest": { + "input_cost_per_token": 5e-7, + "max_input_tokens": 40000, + "max_output_tokens": 40000, + "max_tokens": 40000, + "mode": "chat", + "output_cost_per_token": 0.0000015, + "source": "https://mistral.ai/pricing#api-pricing", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "provider": "mistral" + }, + "mistral/mistral-embed": { + "input_cost_per_token": 1e-7, + "max_input_tokens": 8192, + "max_tokens": 8192, + "mode": "embedding", + "provider": "mistral" + }, + "mistral/codestral-embed": { + "input_cost_per_token": 1.5e-7, + "max_input_tokens": 8192, + "max_tokens": 8192, + "mode": "embedding", + "provider": "mistral" + }, + "mistral/codestral-embed-2505": { + "input_cost_per_token": 1.5e-7, + "max_input_tokens": 8192, + "max_tokens": 8192, + "mode": "embedding", + "provider": "mistral" + }, + "mistral/mistral-large-2402": { + "input_cost_per_token": 0.000004, + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 0.000012, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "provider": "mistral" + }, + "mistral/mistral-large-2407": { + "input_cost_per_token": 0.000003, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.000009, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "provider": "mistral" + }, + "mistral/mistral-large-2411": { + "input_cost_per_token": 0.000002, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.000006, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "provider": "mistral" + }, + "mistral/mistral-large-latest": { + "input_cost_per_token": 0.000002, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.000006, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "provider": "mistral" + }, + "mistral/mistral-medium": { + "input_cost_per_token": 0.0000027, + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 0.0000081, + "supports_assistant_prefill": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "provider": "mistral" + }, + "mistral/mistral-medium-2312": { + "input_cost_per_token": 0.0000027, + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 0.0000081, + "supports_assistant_prefill": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "provider": "mistral" + }, + "mistral/mistral-medium-2505": { + "input_cost_per_token": 4e-7, + "max_input_tokens": 131072, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 0.000002, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "provider": "mistral" + }, + "mistral/mistral-medium-latest": { + "input_cost_per_token": 4e-7, + "max_input_tokens": 131072, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 0.000002, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "provider": "mistral" + }, + "mistral/mistral-small": { + "input_cost_per_token": 1e-7, + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 3e-7, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "provider": "mistral" + }, + "mistral/mistral-small-latest": { + "input_cost_per_token": 1e-7, + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 3e-7, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "provider": "mistral" + }, + "mistral/mistral-tiny": { + "input_cost_per_token": 2.5e-7, + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 2.5e-7, + "supports_assistant_prefill": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "provider": "mistral" + }, + "mistral/open-codestral-mamba": { + "input_cost_per_token": 2.5e-7, + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 2.5e-7, + "source": "https://mistral.ai/technology/", + "supports_assistant_prefill": true, + "supports_tool_choice": true, + "provider": "mistral" + }, + "mistral/open-mistral-7b": { + "input_cost_per_token": 2.5e-7, + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 2.5e-7, + "supports_assistant_prefill": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "provider": "mistral" + }, + "mistral/open-mistral-nemo": { + "input_cost_per_token": 3e-7, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3e-7, + "source": "https://mistral.ai/technology/", + "supports_assistant_prefill": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "provider": "mistral" + }, + "mistral/open-mistral-nemo-2407": { + "input_cost_per_token": 3e-7, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3e-7, + "source": "https://mistral.ai/technology/", + "supports_assistant_prefill": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "provider": "mistral" + }, + "mistral/open-mixtral-8x22b": { + "input_cost_per_token": 0.000002, + "max_input_tokens": 65336, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 0.000006, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "provider": "mistral" + }, + "mistral/open-mixtral-8x7b": { + "input_cost_per_token": 7e-7, + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 7e-7, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "provider": "mistral" + }, + "mistral/pixtral-12b-2409": { + "input_cost_per_token": 1.5e-7, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.5e-7, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "mistral" + }, + "mistral/pixtral-large-2411": { + "input_cost_per_token": 0.000002, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.000006, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "mistral" + }, + "mistral/pixtral-large-latest": { + "input_cost_per_token": 0.000002, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.000006, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "mistral" + }, + "moonshot/kimi-k2-0711-preview": { + "cache_read_input_token_cost": 1.5e-7, + "input_cost_per_token": 6e-7, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 0.0000025, + "source": "https://platform.moonshot.ai/docs/pricing/chat#generation-model-kimi-k2", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_web_search": true, + "provider": "moonshot" + }, + "moonshot/kimi-latest": { + "cache_read_input_token_cost": 1.5e-7, + "input_cost_per_token": 0.000002, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 0.000005, + "source": "https://platform.moonshot.ai/docs/pricing", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "moonshot" + }, + "moonshot/kimi-latest-128k": { + "cache_read_input_token_cost": 1.5e-7, + "input_cost_per_token": 0.000002, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 0.000005, + "source": "https://platform.moonshot.ai/docs/pricing", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "moonshot" + }, + "moonshot/kimi-latest-32k": { + "cache_read_input_token_cost": 1.5e-7, + "input_cost_per_token": 0.000001, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0.000003, + "source": "https://platform.moonshot.ai/docs/pricing", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "moonshot" + }, + "moonshot/kimi-latest-8k": { + "cache_read_input_token_cost": 1.5e-7, + "input_cost_per_token": 2e-7, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.000002, + "source": "https://platform.moonshot.ai/docs/pricing", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "moonshot" + }, + "moonshot/kimi-thinking-preview": { + "input_cost_per_token": 0.00003, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 0.00003, + "source": "https://platform.moonshot.ai/docs/pricing", + "supports_vision": true, + "provider": "moonshot" + }, + "moonshot/kimi-k2-thinking": { + "cache_read_input_token_cost": 1.5e-7, + "input_cost_per_token": 6e-7, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 0.0000025, + "source": "https://platform.moonshot.ai/docs/pricing/chat#generation-model-kimi-k2", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_web_search": true, + "provider": "moonshot" + }, + "moonshot/moonshot-v1-128k": { + "input_cost_per_token": 0.000002, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 0.000005, + "source": "https://platform.moonshot.ai/docs/pricing", + "supports_function_calling": true, + "supports_tool_choice": true, + "provider": "moonshot" + }, + "moonshot/moonshot-v1-128k-0430": { + "input_cost_per_token": 0.000002, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 0.000005, + "source": "https://platform.moonshot.ai/docs/pricing", + "supports_function_calling": true, + "supports_tool_choice": true, + "provider": "moonshot" + }, + "moonshot/moonshot-v1-128k-vision-preview": { + "input_cost_per_token": 0.000002, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 0.000005, + "source": "https://platform.moonshot.ai/docs/pricing", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "moonshot" + }, + "moonshot/moonshot-v1-32k": { + "input_cost_per_token": 0.000001, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0.000003, + "source": "https://platform.moonshot.ai/docs/pricing", + "supports_function_calling": true, + "supports_tool_choice": true, + "provider": "moonshot" + }, + "moonshot/moonshot-v1-32k-0430": { + "input_cost_per_token": 0.000001, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0.000003, + "source": "https://platform.moonshot.ai/docs/pricing", + "supports_function_calling": true, + "supports_tool_choice": true, + "provider": "moonshot" + }, + "moonshot/moonshot-v1-32k-vision-preview": { + "input_cost_per_token": 0.000001, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0.000003, + "source": "https://platform.moonshot.ai/docs/pricing", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "moonshot" + }, + "moonshot/moonshot-v1-8k": { + "input_cost_per_token": 2e-7, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.000002, + "source": "https://platform.moonshot.ai/docs/pricing", + "supports_function_calling": true, + "supports_tool_choice": true, + "provider": "moonshot" + }, + "moonshot/moonshot-v1-8k-0430": { + "input_cost_per_token": 2e-7, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.000002, + "source": "https://platform.moonshot.ai/docs/pricing", + "supports_function_calling": true, + "supports_tool_choice": true, + "provider": "moonshot" + }, + "moonshot/moonshot-v1-8k-vision-preview": { + "input_cost_per_token": 2e-7, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.000002, + "source": "https://platform.moonshot.ai/docs/pricing", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "moonshot" + }, + "moonshot/moonshot-v1-auto": { + "input_cost_per_token": 0.000002, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 0.000005, + "source": "https://platform.moonshot.ai/docs/pricing", + "supports_function_calling": true, + "supports_tool_choice": true, + "provider": "moonshot" + }, + "morph/morph-v3-fast": { + "input_cost_per_token": 8e-7, + "max_input_tokens": 16000, + "max_output_tokens": 16000, + "max_tokens": 16000, + "mode": "chat", + "output_cost_per_token": 0.0000012, + "supports_function_calling": false, + "supports_parallel_function_calling": false, + "supports_system_messages": true, + "supports_tool_choice": false, + "supports_vision": false, + "provider": "morph" + }, + "morph/morph-v3-large": { + "input_cost_per_token": 9e-7, + "max_input_tokens": 16000, + "max_output_tokens": 16000, + "max_tokens": 16000, + "mode": "chat", + "output_cost_per_token": 0.0000019, + "supports_function_calling": false, + "supports_parallel_function_calling": false, + "supports_system_messages": true, + "supports_tool_choice": false, + "supports_vision": false, + "provider": "morph" + }, + "multimodalembedding": { + "input_cost_per_character": 2e-7, + "input_cost_per_image": 0.0001, + "input_cost_per_token": 8e-7, + "input_cost_per_video_per_second": 0.0005, + "input_cost_per_video_per_second_above_15s_interval": 0.002, + "input_cost_per_video_per_second_above_8s_interval": 0.001, + "max_input_tokens": 2048, + "max_tokens": 2048, + "mode": "embedding", + "output_cost_per_token": 0, + "output_vector_size": 768, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models", + "supported_endpoints": ["/v1/embeddings"], + "supported_modalities": ["text", "image", "video"], + "provider": "vertex_ai-embedding-models" + }, + "multimodalembedding@001": { + "input_cost_per_character": 2e-7, + "input_cost_per_image": 0.0001, + "input_cost_per_token": 8e-7, + "input_cost_per_video_per_second": 0.0005, + "input_cost_per_video_per_second_above_15s_interval": 0.002, + "input_cost_per_video_per_second_above_8s_interval": 0.001, + "max_input_tokens": 2048, + "max_tokens": 2048, + "mode": "embedding", + "output_cost_per_token": 0, + "output_vector_size": 768, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models", + "supported_endpoints": ["/v1/embeddings"], + "supported_modalities": ["text", "image", "video"], + "provider": "vertex_ai-embedding-models" + }, + "nscale/Qwen/QwQ-32B": { + "input_cost_per_token": 1.8e-7, + "mode": "chat", + "output_cost_per_token": 2e-7, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models", + "provider": "nscale" + }, + "nscale/Qwen/Qwen2.5-Coder-32B-Instruct": { + "input_cost_per_token": 6e-8, + "mode": "chat", + "output_cost_per_token": 2e-7, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models", + "provider": "nscale" + }, + "nscale/Qwen/Qwen2.5-Coder-3B-Instruct": { + "input_cost_per_token": 1e-8, + "mode": "chat", + "output_cost_per_token": 3e-8, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models", + "provider": "nscale" + }, + "nscale/Qwen/Qwen2.5-Coder-7B-Instruct": { + "input_cost_per_token": 1e-8, + "mode": "chat", + "output_cost_per_token": 3e-8, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models", + "provider": "nscale" + }, + "nscale/black-forest-labs/FLUX.1-schnell": { + "input_cost_per_pixel": 1.3e-9, + "mode": "image_generation", + "output_cost_per_pixel": 0, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#image-models", + "supported_endpoints": ["/v1/images/generations"], + "provider": "nscale" + }, + "nscale/deepseek-ai/DeepSeek-R1-Distill-Llama-70B": { + "input_cost_per_token": 3.75e-7, + "metadata": { + "notes": "Pricing listed as $0.75/1M tokens total. Assumed 50/50 split for input/output." + }, + "mode": "chat", + "output_cost_per_token": 3.75e-7, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models", + "provider": "nscale" + }, + "nscale/deepseek-ai/DeepSeek-R1-Distill-Llama-8B": { + "input_cost_per_token": 2.5e-8, + "metadata": { + "notes": "Pricing listed as $0.05/1M tokens total. Assumed 50/50 split for input/output." + }, + "mode": "chat", + "output_cost_per_token": 2.5e-8, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models", + "provider": "nscale" + }, + "nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B": { + "input_cost_per_token": 9e-8, + "metadata": { + "notes": "Pricing listed as $0.18/1M tokens total. Assumed 50/50 split for input/output." + }, + "mode": "chat", + "output_cost_per_token": 9e-8, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models", + "provider": "nscale" + }, + "nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B": { + "input_cost_per_token": 7e-8, + "metadata": { + "notes": "Pricing listed as $0.14/1M tokens total. Assumed 50/50 split for input/output." + }, + "mode": "chat", + "output_cost_per_token": 7e-8, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models", + "provider": "nscale" + }, + "nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B": { + "input_cost_per_token": 1.5e-7, + "metadata": { + "notes": "Pricing listed as $0.30/1M tokens total. Assumed 50/50 split for input/output." + }, + "mode": "chat", + "output_cost_per_token": 1.5e-7, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models", + "provider": "nscale" + }, + "nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B": { + "input_cost_per_token": 2e-7, + "metadata": { + "notes": "Pricing listed as $0.40/1M tokens total. Assumed 50/50 split for input/output." + }, + "mode": "chat", + "output_cost_per_token": 2e-7, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models", + "provider": "nscale" + }, + "nscale/meta-llama/Llama-3.1-8B-Instruct": { + "input_cost_per_token": 3e-8, + "metadata": { + "notes": "Pricing listed as $0.06/1M tokens total. Assumed 50/50 split for input/output." + }, + "mode": "chat", + "output_cost_per_token": 3e-8, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models", + "provider": "nscale" + }, + "nscale/meta-llama/Llama-3.3-70B-Instruct": { + "input_cost_per_token": 2e-7, + "metadata": { + "notes": "Pricing listed as $0.40/1M tokens total. Assumed 50/50 split for input/output." + }, + "mode": "chat", + "output_cost_per_token": 2e-7, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models", + "provider": "nscale" + }, + "nscale/meta-llama/Llama-4-Scout-17B-16E-Instruct": { + "input_cost_per_token": 9e-8, + "mode": "chat", + "output_cost_per_token": 2.9e-7, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models", + "provider": "nscale" + }, + "nscale/mistralai/mixtral-8x22b-instruct-v0.1": { + "input_cost_per_token": 6e-7, + "metadata": { + "notes": "Pricing listed as $1.20/1M tokens total. Assumed 50/50 split for input/output." + }, + "mode": "chat", + "output_cost_per_token": 6e-7, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models", + "provider": "nscale" + }, + "nscale/stabilityai/stable-diffusion-xl-base-1.0": { + "input_cost_per_pixel": 3e-9, + "mode": "image_generation", + "output_cost_per_pixel": 0, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#image-models", + "supported_endpoints": ["/v1/images/generations"], + "provider": "nscale" + }, + "o1": { + "cache_read_input_token_cost": 0.0000075, + "input_cost_per_token": 0.000015, + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 0.00006, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "openai" + }, + "o1-2024-12-17": { + "cache_read_input_token_cost": 0.0000075, + "input_cost_per_token": 0.000015, + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 0.00006, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "openai" + }, + "o1-mini": { + "cache_read_input_token_cost": 5.5e-7, + "input_cost_per_token": 0.0000011, + "max_input_tokens": 128000, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 0.0000044, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_vision": true, + "provider": "openai" + }, + "o1-mini-2024-09-12": { + "deprecation_date": "2025-10-27", + "cache_read_input_token_cost": 0.0000015, + "input_cost_per_token": 0.000003, + "max_input_tokens": 128000, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 0.000012, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_vision": true, + "provider": "openai" + }, + "o1-preview": { + "cache_read_input_token_cost": 0.0000075, + "input_cost_per_token": 0.000015, + "max_input_tokens": 128000, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0.00006, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_vision": true, + "provider": "openai" + }, + "o1-preview-2024-09-12": { + "cache_read_input_token_cost": 0.0000075, + "input_cost_per_token": 0.000015, + "max_input_tokens": 128000, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0.00006, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_vision": true, + "provider": "openai" + }, + "o1-pro": { + "input_cost_per_token": 0.00015, + "input_cost_per_token_batches": 0.000075, + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "responses", + "output_cost_per_token": 0.0006, + "output_cost_per_token_batches": 0.0003, + "supported_endpoints": ["/v1/responses", "/v1/batch"], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], + "supports_function_calling": true, + "supports_native_streaming": false, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "openai" + }, + "o1-pro-2025-03-19": { + "input_cost_per_token": 0.00015, + "input_cost_per_token_batches": 0.000075, + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "responses", + "output_cost_per_token": 0.0006, + "output_cost_per_token_batches": 0.0003, + "supported_endpoints": ["/v1/responses", "/v1/batch"], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], + "supports_function_calling": true, + "supports_native_streaming": false, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "openai" + }, + "o3": { + "cache_read_input_token_cost": 5e-7, + "cache_read_input_token_cost_flex": 2.5e-7, + "cache_read_input_token_cost_priority": 8.75e-7, + "input_cost_per_token": 0.000002, + "input_cost_per_token_flex": 0.000001, + "input_cost_per_token_priority": 0.0000035, + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 0.000008, + "output_cost_per_token_flex": 0.000004, + "output_cost_per_token_priority": 0.000014, + "supported_endpoints": [ + "/v1/responses", + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], + "supports_function_calling": true, + "supports_parallel_function_calling": false, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_service_tier": true, + "supports_vision": true, + "provider": "openai" + }, + "o3-2025-04-16": { + "cache_read_input_token_cost": 5e-7, + "input_cost_per_token": 0.000002, + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 0.000008, + "supported_endpoints": [ + "/v1/responses", + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], + "supports_function_calling": true, + "supports_parallel_function_calling": false, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_service_tier": true, + "supports_vision": true, + "provider": "openai" + }, + "o3-deep-research": { + "cache_read_input_token_cost": 0.0000025, + "input_cost_per_token": 0.00001, + "input_cost_per_token_batches": 0.000005, + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "responses", + "output_cost_per_token": 0.00004, + "output_cost_per_token_batches": 0.00002, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "openai" + }, + "o3-deep-research-2025-06-26": { + "cache_read_input_token_cost": 0.0000025, + "input_cost_per_token": 0.00001, + "input_cost_per_token_batches": 0.000005, + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "responses", + "output_cost_per_token": 0.00004, + "output_cost_per_token_batches": 0.00002, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "openai" + }, + "o3-mini": { + "cache_read_input_token_cost": 5.5e-7, + "input_cost_per_token": 0.0000011, + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 0.0000044, + "supports_function_calling": true, + "supports_parallel_function_calling": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "provider": "openai" + }, + "o3-mini-2025-01-31": { + "cache_read_input_token_cost": 5.5e-7, + "input_cost_per_token": 0.0000011, + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 0.0000044, + "supports_function_calling": true, + "supports_parallel_function_calling": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "provider": "openai" + }, + "o3-pro": { + "input_cost_per_token": 0.00002, + "input_cost_per_token_batches": 0.00001, + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "responses", + "output_cost_per_token": 0.00008, + "output_cost_per_token_batches": 0.00004, + "supported_endpoints": ["/v1/responses", "/v1/batch"], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], + "supports_function_calling": true, + "supports_parallel_function_calling": false, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "openai" + }, + "o3-pro-2025-06-10": { + "input_cost_per_token": 0.00002, + "input_cost_per_token_batches": 0.00001, + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "responses", + "output_cost_per_token": 0.00008, + "output_cost_per_token_batches": 0.00004, + "supported_endpoints": ["/v1/responses", "/v1/batch"], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], + "supports_function_calling": true, + "supports_parallel_function_calling": false, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "openai" + }, + "o4-mini": { + "cache_read_input_token_cost": 2.75e-7, + "cache_read_input_token_cost_flex": 1.375e-7, + "cache_read_input_token_cost_priority": 5e-7, + "input_cost_per_token": 0.0000011, + "input_cost_per_token_flex": 5.5e-7, + "input_cost_per_token_priority": 0.000002, + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 0.0000044, + "output_cost_per_token_flex": 0.0000022, + "output_cost_per_token_priority": 0.000008, + "supports_function_calling": true, + "supports_parallel_function_calling": false, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_service_tier": true, + "supports_vision": true, + "provider": "openai" + }, + "o4-mini-2025-04-16": { + "cache_read_input_token_cost": 2.75e-7, + "input_cost_per_token": 0.0000011, + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 0.0000044, + "supports_function_calling": true, + "supports_parallel_function_calling": false, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_service_tier": true, + "supports_vision": true, + "provider": "openai" + }, + "o4-mini-deep-research": { + "cache_read_input_token_cost": 5e-7, + "input_cost_per_token": 0.000002, + "input_cost_per_token_batches": 0.000001, + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "responses", + "output_cost_per_token": 0.000008, + "output_cost_per_token_batches": 0.000004, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "openai" + }, + "o4-mini-deep-research-2025-06-26": { + "cache_read_input_token_cost": 5e-7, + "input_cost_per_token": 0.000002, + "input_cost_per_token_batches": 0.000001, + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "responses", + "output_cost_per_token": 0.000008, + "output_cost_per_token_batches": 0.000004, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "openai" + }, + "oci/meta.llama-3.1-405b-instruct": { + "input_cost_per_token": 0.00001068, + "max_input_tokens": 128000, + "max_output_tokens": 4000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.00001068, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", + "supports_function_calling": true, + "supports_response_schema": false, + "provider": "oci" + }, + "oci/meta.llama-3.2-90b-vision-instruct": { + "input_cost_per_token": 0.000002, + "max_input_tokens": 128000, + "max_output_tokens": 4000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.000002, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", + "supports_function_calling": true, + "supports_response_schema": false, + "provider": "oci" + }, + "oci/meta.llama-3.3-70b-instruct": { + "input_cost_per_token": 7.2e-7, + "max_input_tokens": 128000, + "max_output_tokens": 4000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 7.2e-7, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", + "supports_function_calling": true, + "supports_response_schema": false, + "provider": "oci" + }, + "oci/meta.llama-4-maverick-17b-128e-instruct-fp8": { + "input_cost_per_token": 7.2e-7, + "max_input_tokens": 512000, + "max_output_tokens": 4000, + "max_tokens": 512000, + "mode": "chat", + "output_cost_per_token": 7.2e-7, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", + "supports_function_calling": true, + "supports_response_schema": false, + "provider": "oci" + }, + "oci/meta.llama-4-scout-17b-16e-instruct": { + "input_cost_per_token": 7.2e-7, + "max_input_tokens": 192000, + "max_output_tokens": 4000, + "max_tokens": 192000, + "mode": "chat", + "output_cost_per_token": 7.2e-7, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", + "supports_function_calling": true, + "supports_response_schema": false, + "provider": "oci" + }, + "oci/xai.grok-3": { + "input_cost_per_token": 0.000003, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.5e-7, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", + "supports_function_calling": true, + "supports_response_schema": false, + "provider": "oci" + }, + "oci/xai.grok-3-fast": { + "input_cost_per_token": 0.000005, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 0.000025, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", + "supports_function_calling": true, + "supports_response_schema": false, + "provider": "oci" + }, + "oci/xai.grok-3-mini": { + "input_cost_per_token": 3e-7, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 5e-7, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", + "supports_function_calling": true, + "supports_response_schema": false, + "provider": "oci" + }, + "oci/xai.grok-3-mini-fast": { + "input_cost_per_token": 6e-7, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 0.000004, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", + "supports_function_calling": true, + "supports_response_schema": false, + "provider": "oci" + }, + "oci/xai.grok-4": { + "input_cost_per_token": 0.000003, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.5e-7, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", + "supports_function_calling": true, + "supports_response_schema": false, + "provider": "oci" + }, + "oci/cohere.command-latest": { + "input_cost_per_token": 0.00000156, + "max_input_tokens": 128000, + "max_output_tokens": 4000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.00000156, + "source": "https://www.oracle.com/cloud/ai/generative-ai/pricing/", + "supports_function_calling": true, + "supports_response_schema": false, + "provider": "oci" + }, + "oci/cohere.command-a-03-2025": { + "input_cost_per_token": 0.00000156, + "max_input_tokens": 256000, + "max_output_tokens": 4000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 0.00000156, + "source": "https://www.oracle.com/cloud/ai/generative-ai/pricing/", + "supports_function_calling": true, + "supports_response_schema": false, + "provider": "oci" + }, + "oci/cohere.command-plus-latest": { + "input_cost_per_token": 0.00000156, + "max_input_tokens": 128000, + "max_output_tokens": 4000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.00000156, + "source": "https://www.oracle.com/cloud/ai/generative-ai/pricing/", + "supports_function_calling": true, + "supports_response_schema": false, + "provider": "oci" + }, + "ollama/codegeex4": { + "input_cost_per_token": 0, + "max_input_tokens": 32768, + "max_output_tokens": 8192, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0, + "supports_function_calling": false, + "provider": "ollama" + }, + "ollama/codegemma": { + "input_cost_per_token": 0, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "completion", + "output_cost_per_token": 0, + "provider": "ollama" + }, + "ollama/codellama": { + "input_cost_per_token": 0, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "completion", + "output_cost_per_token": 0, + "provider": "ollama" + }, + "ollama/deepseek-coder-v2-base": { + "input_cost_per_token": 0, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "completion", + "output_cost_per_token": 0, + "supports_function_calling": true, + "provider": "ollama" + }, + "ollama/deepseek-coder-v2-instruct": { + "input_cost_per_token": 0, + "max_input_tokens": 32768, + "max_output_tokens": 8192, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0, + "supports_function_calling": true, + "provider": "ollama" + }, + "ollama/deepseek-coder-v2-lite-base": { + "input_cost_per_token": 0, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "completion", + "output_cost_per_token": 0, + "supports_function_calling": true, + "provider": "ollama" + }, + "ollama/deepseek-coder-v2-lite-instruct": { + "input_cost_per_token": 0, + "max_input_tokens": 32768, + "max_output_tokens": 8192, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0, + "supports_function_calling": true, + "provider": "ollama" + }, + "ollama/deepseek-v3.1:671b-cloud": { + "input_cost_per_token": 0, + "max_input_tokens": 163840, + "max_output_tokens": 163840, + "max_tokens": 163840, + "mode": "chat", + "output_cost_per_token": 0, + "supports_function_calling": true, + "provider": "ollama" + }, + "ollama/gpt-oss:120b-cloud": { + "input_cost_per_token": 0, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 0, + "supports_function_calling": true, + "provider": "ollama" + }, + "ollama/gpt-oss:20b-cloud": { + "input_cost_per_token": 0, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 0, + "supports_function_calling": true, + "provider": "ollama" + }, + "ollama/internlm2_5-20b-chat": { + "input_cost_per_token": 0, + "max_input_tokens": 32768, + "max_output_tokens": 8192, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0, + "supports_function_calling": true, + "provider": "ollama" + }, + "ollama/llama2": { + "input_cost_per_token": 0, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0, + "provider": "ollama" + }, + "ollama/llama2-uncensored": { + "input_cost_per_token": 0, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "completion", + "output_cost_per_token": 0, + "provider": "ollama" + }, + "ollama/llama2:13b": { + "input_cost_per_token": 0, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0, + "provider": "ollama" + }, + "ollama/llama2:70b": { + "input_cost_per_token": 0, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0, + "provider": "ollama" + }, + "ollama/llama2:7b": { + "input_cost_per_token": 0, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0, + "provider": "ollama" + }, + "ollama/llama3": { + "input_cost_per_token": 0, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0, + "provider": "ollama" + }, + "ollama/llama3.1": { + "input_cost_per_token": 0, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0, + "supports_function_calling": true, + "provider": "ollama" + }, + "ollama/llama3:70b": { + "input_cost_per_token": 0, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0, + "provider": "ollama" + }, + "ollama/llama3:8b": { + "input_cost_per_token": 0, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0, + "provider": "ollama" + }, + "ollama/mistral": { + "input_cost_per_token": 0, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "completion", + "output_cost_per_token": 0, + "supports_function_calling": true, + "provider": "ollama" + }, + "ollama/mistral-7B-Instruct-v0.1": { + "input_cost_per_token": 0, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0, + "supports_function_calling": true, + "provider": "ollama" + }, + "ollama/mistral-7B-Instruct-v0.2": { + "input_cost_per_token": 0, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0, + "supports_function_calling": true, + "provider": "ollama" + }, + "ollama/mistral-large-instruct-2407": { + "input_cost_per_token": 0, + "max_input_tokens": 65536, + "max_output_tokens": 8192, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 0, + "supports_function_calling": true, + "provider": "ollama" + }, + "ollama/mixtral-8x22B-Instruct-v0.1": { + "input_cost_per_token": 0, + "max_input_tokens": 65536, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 0, + "supports_function_calling": true, + "provider": "ollama" + }, + "ollama/mixtral-8x7B-Instruct-v0.1": { + "input_cost_per_token": 0, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0, + "supports_function_calling": true, + "provider": "ollama" + }, + "ollama/orca-mini": { + "input_cost_per_token": 0, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "completion", + "output_cost_per_token": 0, + "provider": "ollama" + }, + "ollama/qwen3-coder:480b-cloud": { + "input_cost_per_token": 0, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 0, + "supports_function_calling": true, + "provider": "ollama" + }, + "ollama/vicuna": { + "input_cost_per_token": 0, + "max_input_tokens": 2048, + "max_output_tokens": 2048, + "max_tokens": 2048, + "mode": "completion", + "output_cost_per_token": 0, + "provider": "ollama" + }, + "omni-moderation-2024-09-26": { + "input_cost_per_token": 0, + "max_input_tokens": 32768, + "max_output_tokens": 0, + "max_tokens": 32768, + "mode": "moderation", + "output_cost_per_token": 0, + "provider": "openai" + }, + "omni-moderation-latest": { + "input_cost_per_token": 0, + "max_input_tokens": 32768, + "max_output_tokens": 0, + "max_tokens": 32768, + "mode": "moderation", + "output_cost_per_token": 0, + "provider": "openai" + }, + "omni-moderation-latest-intents": { + "input_cost_per_token": 0, + "max_input_tokens": 32768, + "max_output_tokens": 0, + "max_tokens": 32768, + "mode": "moderation", + "output_cost_per_token": 0, + "provider": "openai" + }, + "openai.gpt-oss-120b-1:0": { + "input_cost_per_token": 1.5e-7, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-7, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "provider": "bedrock_converse" + }, + "openai.gpt-oss-20b-1:0": { + "input_cost_per_token": 7e-8, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3e-7, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "provider": "bedrock_converse" + }, + "openrouter/anthropic/claude-2": { + "input_cost_per_token": 0.00001102, + "max_output_tokens": 8191, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 0.00003268, + "supports_tool_choice": true, + "provider": "openrouter" + }, + "openrouter/anthropic/claude-3-5-haiku": { + "input_cost_per_token": 0.000001, + "max_tokens": 200000, + "mode": "chat", + "output_cost_per_token": 0.000005, + "supports_function_calling": true, + "supports_tool_choice": true, + "provider": "openrouter" + }, + "openrouter/anthropic/claude-3-5-haiku-20241022": { + "input_cost_per_token": 0.000001, + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.000005, + "supports_function_calling": true, + "supports_tool_choice": true, + "tool_use_system_prompt_tokens": 264, + "provider": "openrouter" + }, + "openrouter/anthropic/claude-3-haiku": { + "input_cost_per_image": 0.0004, + "input_cost_per_token": 2.5e-7, + "max_tokens": 200000, + "mode": "chat", + "output_cost_per_token": 0.00000125, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "openrouter" + }, + "openrouter/anthropic/claude-3-haiku-20240307": { + "input_cost_per_token": 2.5e-7, + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.00000125, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 264, + "provider": "openrouter" + }, + "openrouter/anthropic/claude-3-opus": { + "input_cost_per_token": 0.000015, + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.000075, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 395, + "provider": "openrouter" + }, + "openrouter/anthropic/claude-3-sonnet": { + "input_cost_per_image": 0.0048, + "input_cost_per_token": 0.000003, + "max_tokens": 200000, + "mode": "chat", + "output_cost_per_token": 0.000015, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "openrouter" + }, + "openrouter/anthropic/claude-3.5-sonnet": { + "input_cost_per_token": 0.000003, + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.000015, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159, + "provider": "openrouter" + }, + "openrouter/anthropic/claude-3.5-sonnet:beta": { + "input_cost_per_token": 0.000003, + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.000015, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159, + "provider": "openrouter" + }, + "openrouter/anthropic/claude-3.7-sonnet": { + "input_cost_per_image": 0.0048, + "input_cost_per_token": 0.000003, + "max_input_tokens": 200000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.000015, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159, + "provider": "openrouter" + }, + "openrouter/anthropic/claude-3.7-sonnet:beta": { + "input_cost_per_image": 0.0048, + "input_cost_per_token": 0.000003, + "max_input_tokens": 200000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.000015, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159, + "provider": "openrouter" + }, + "openrouter/anthropic/claude-instant-v1": { + "input_cost_per_token": 0.00000163, + "max_output_tokens": 8191, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 0.00000551, + "supports_tool_choice": true, + "provider": "openrouter" + }, + "openrouter/anthropic/claude-opus-4": { + "input_cost_per_image": 0.0048, + "cache_creation_input_token_cost": 0.00001875, + "cache_read_input_token_cost": 0.0000015, + "input_cost_per_token": 0.000015, + "max_input_tokens": 200000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 0.000075, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159, + "provider": "openrouter" + }, + "openrouter/anthropic/claude-opus-4.1": { + "input_cost_per_image": 0.0048, + "cache_creation_input_token_cost": 0.00001875, + "cache_creation_input_token_cost_above_1hr": 0.00003, + "cache_read_input_token_cost": 0.0000015, + "input_cost_per_token": 0.000015, + "max_input_tokens": 200000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 0.000075, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159, + "provider": "openrouter" + }, + "openrouter/anthropic/claude-sonnet-4": { + "input_cost_per_image": 0.0048, + "cache_creation_input_token_cost": 0.00000375, + "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, + "cache_read_input_token_cost": 3e-7, + "cache_read_input_token_cost_above_200k_tokens": 6e-7, + "input_cost_per_token": 0.000003, + "input_cost_per_token_above_200k_tokens": 0.000006, + "output_cost_per_token_above_200k_tokens": 0.0000225, + "max_input_tokens": 1000000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 0.000015, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159, + "provider": "openrouter" + }, + "openrouter/anthropic/claude-sonnet-4.5": { + "input_cost_per_image": 0.0048, + "cache_creation_input_token_cost": 0.00000375, + "cache_read_input_token_cost": 3e-7, + "input_cost_per_token": 0.000003, + "input_cost_per_token_above_200k_tokens": 0.000006, + "output_cost_per_token_above_200k_tokens": 0.0000225, + "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, + "cache_read_input_token_cost_above_200k_tokens": 6e-7, + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 0.000015, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159, + "provider": "openrouter" + }, + "openrouter/anthropic/claude-haiku-4.5": { + "cache_creation_input_token_cost": 0.00000125, + "cache_read_input_token_cost": 1e-7, + "input_cost_per_token": 0.000001, + "max_input_tokens": 200000, + "max_output_tokens": 200000, + "max_tokens": 200000, + "mode": "chat", + "output_cost_per_token": 0.000005, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 346, + "provider": "openrouter" + }, + "openrouter/bytedance/ui-tars-1.5-7b": { + "input_cost_per_token": 1e-7, + "max_input_tokens": 131072, + "max_output_tokens": 2048, + "max_tokens": 2048, + "mode": "chat", + "output_cost_per_token": 2e-7, + "source": "https://openrouter.ai/api/v1/models/bytedance/ui-tars-1.5-7b", + "supports_tool_choice": true, + "provider": "openrouter" + }, + "openrouter/cognitivecomputations/dolphin-mixtral-8x7b": { + "input_cost_per_token": 5e-7, + "max_tokens": 32769, + "mode": "chat", + "output_cost_per_token": 5e-7, + "supports_tool_choice": true, + "provider": "openrouter" + }, + "openrouter/cohere/command-r-plus": { + "input_cost_per_token": 0.000003, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.000015, + "supports_tool_choice": true, + "provider": "openrouter" + }, + "openrouter/databricks/dbrx-instruct": { + "input_cost_per_token": 6e-7, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 6e-7, + "supports_tool_choice": true, + "provider": "openrouter" + }, + "openrouter/deepseek/deepseek-chat": { + "input_cost_per_token": 1.4e-7, + "max_input_tokens": 65536, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2.8e-7, + "supports_prompt_caching": true, + "supports_tool_choice": true, + "provider": "openrouter" + }, + "openrouter/deepseek/deepseek-chat-v3-0324": { + "input_cost_per_token": 1.4e-7, + "max_input_tokens": 65536, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2.8e-7, + "supports_prompt_caching": true, + "supports_tool_choice": true, + "provider": "openrouter" + }, + "openrouter/deepseek/deepseek-chat-v3.1": { + "input_cost_per_token": 2e-7, + "input_cost_per_token_cache_hit": 2e-8, + "max_input_tokens": 163840, + "max_output_tokens": 163840, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 8e-7, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "provider": "openrouter" + }, + "openrouter/deepseek/deepseek-v3.2-exp": { + "input_cost_per_token": 2e-7, + "input_cost_per_token_cache_hit": 2e-8, + "max_input_tokens": 163840, + "max_output_tokens": 163840, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 4e-7, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": false, + "supports_tool_choice": true, + "provider": "openrouter" + }, + "openrouter/deepseek/deepseek-coder": { + "input_cost_per_token": 1.4e-7, + "max_input_tokens": 66000, + "max_output_tokens": 4096, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2.8e-7, + "supports_prompt_caching": true, + "supports_tool_choice": true, + "provider": "openrouter" + }, + "openrouter/deepseek/deepseek-r1": { + "input_cost_per_token": 5.5e-7, + "input_cost_per_token_cache_hit": 1.4e-7, + "max_input_tokens": 65336, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.00000219, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "provider": "openrouter" + }, + "openrouter/deepseek/deepseek-r1-0528": { + "input_cost_per_token": 5e-7, + "input_cost_per_token_cache_hit": 1.4e-7, + "max_input_tokens": 65336, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.00000215, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "provider": "openrouter" + }, + "openrouter/fireworks/firellava-13b": { + "input_cost_per_token": 2e-7, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2e-7, + "supports_tool_choice": true, + "provider": "openrouter" + }, + "openrouter/google/gemini-2.0-flash-001": { + "input_cost_per_audio_token": 7e-7, + "input_cost_per_token": 1e-7, + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 4e-7, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "openrouter" + }, + "openrouter/google/gemini-2.5-flash": { + "input_cost_per_audio_token": 7e-7, + "input_cost_per_token": 3e-7, + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 0.0000025, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "openrouter" + }, + "openrouter/google/gemini-2.5-pro": { + "input_cost_per_audio_token": 7e-7, + "input_cost_per_token": 0.00000125, + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 0.00001, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "openrouter" + }, + "openrouter/google/gemini-3-pro-preview": { + "cache_read_input_token_cost": 2e-7, + "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": 0.000002, + "input_cost_per_token_above_200k_tokens": 0.000004, + "input_cost_per_token_batches": 0.000001, + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 0.000012, + "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_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "provider": "openrouter" + }, + "openrouter/google/gemini-pro-1.5": { + "input_cost_per_image": 0.00265, + "input_cost_per_token": 0.0000025, + "max_input_tokens": 1000000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.0000075, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "openrouter" + }, + "openrouter/google/gemini-pro-vision": { + "input_cost_per_image": 0.0025, + "input_cost_per_token": 1.25e-7, + "max_tokens": 45875, + "mode": "chat", + "output_cost_per_token": 3.75e-7, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "openrouter" + }, + "openrouter/google/palm-2-chat-bison": { + "input_cost_per_token": 5e-7, + "max_tokens": 25804, + "mode": "chat", + "output_cost_per_token": 5e-7, + "supports_tool_choice": true, + "provider": "openrouter" + }, + "openrouter/google/palm-2-codechat-bison": { + "input_cost_per_token": 5e-7, + "max_tokens": 20070, + "mode": "chat", + "output_cost_per_token": 5e-7, + "supports_tool_choice": true, + "provider": "openrouter" + }, + "openrouter/gryphe/mythomax-l2-13b": { + "input_cost_per_token": 0.000001875, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.000001875, + "supports_tool_choice": true, + "provider": "openrouter" + }, + "openrouter/jondurbin/airoboros-l2-70b-2.1": { + "input_cost_per_token": 0.000013875, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.000013875, + "supports_tool_choice": true, + "provider": "openrouter" + }, + "openrouter/mancer/weaver": { + "input_cost_per_token": 0.000005625, + "max_tokens": 8000, + "mode": "chat", + "output_cost_per_token": 0.000005625, + "supports_tool_choice": true, + "provider": "openrouter" + }, + "openrouter/meta-llama/codellama-34b-instruct": { + "input_cost_per_token": 5e-7, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 5e-7, + "supports_tool_choice": true, + "provider": "openrouter" + }, + "openrouter/meta-llama/llama-2-13b-chat": { + "input_cost_per_token": 2e-7, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2e-7, + "supports_tool_choice": true, + "provider": "openrouter" + }, + "openrouter/meta-llama/llama-2-70b-chat": { + "input_cost_per_token": 0.0000015, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.0000015, + "supports_tool_choice": true, + "provider": "openrouter" + }, + "openrouter/meta-llama/llama-3-70b-instruct": { + "input_cost_per_token": 5.9e-7, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 7.9e-7, + "supports_tool_choice": true, + "provider": "openrouter" + }, + "openrouter/meta-llama/llama-3-70b-instruct:nitro": { + "input_cost_per_token": 9e-7, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 9e-7, + "supports_tool_choice": true, + "provider": "openrouter" + }, + "openrouter/meta-llama/llama-3-8b-instruct:extended": { + "input_cost_per_token": 2.25e-7, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 0.00000225, + "supports_tool_choice": true, + "provider": "openrouter" + }, + "openrouter/meta-llama/llama-3-8b-instruct:free": { + "input_cost_per_token": 0, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0, + "supports_tool_choice": true, + "provider": "openrouter" + }, + "openrouter/microsoft/wizardlm-2-8x22b:nitro": { + "input_cost_per_token": 0.000001, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 0.000001, + "supports_tool_choice": true, + "provider": "openrouter" + }, + "openrouter/minimax/minimax-m2": { + "input_cost_per_token": 2.55e-7, + "max_input_tokens": 204800, + "max_output_tokens": 204800, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0.00000102, + "supports_function_calling": true, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_tool_choice": true, + "provider": "openrouter" + }, + "openrouter/mistralai/mistral-7b-instruct": { + "input_cost_per_token": 1.3e-7, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.3e-7, + "supports_tool_choice": true, + "provider": "openrouter" + }, + "openrouter/mistralai/mistral-7b-instruct:free": { + "input_cost_per_token": 0, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0, + "supports_tool_choice": true, + "provider": "openrouter" + }, + "openrouter/mistralai/mistral-large": { + "input_cost_per_token": 0.000008, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 0.000024, + "supports_tool_choice": true, + "provider": "openrouter" + }, + "openrouter/mistralai/mistral-small-3.1-24b-instruct": { + "input_cost_per_token": 1e-7, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 3e-7, + "supports_tool_choice": true, + "provider": "openrouter" + }, + "openrouter/mistralai/mistral-small-3.2-24b-instruct": { + "input_cost_per_token": 1e-7, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 3e-7, + "supports_tool_choice": true, + "provider": "openrouter" + }, + "openrouter/mistralai/mixtral-8x22b-instruct": { + "input_cost_per_token": 6.5e-7, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 6.5e-7, + "supports_tool_choice": true, + "provider": "openrouter" + }, + "openrouter/nousresearch/nous-hermes-llama2-13b": { + "input_cost_per_token": 2e-7, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2e-7, + "supports_tool_choice": true, + "provider": "openrouter" + }, + "openrouter/openai/gpt-3.5-turbo": { + "input_cost_per_token": 0.0000015, + "max_tokens": 4095, + "mode": "chat", + "output_cost_per_token": 0.000002, + "supports_tool_choice": true, + "provider": "openrouter" + }, + "openrouter/openai/gpt-3.5-turbo-16k": { + "input_cost_per_token": 0.000003, + "max_tokens": 16383, + "mode": "chat", + "output_cost_per_token": 0.000004, + "supports_tool_choice": true, + "provider": "openrouter" + }, + "openrouter/openai/gpt-4": { + "input_cost_per_token": 0.00003, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.00006, + "supports_tool_choice": true, + "provider": "openrouter" + }, + "openrouter/openai/gpt-4-vision-preview": { + "input_cost_per_image": 0.01445, + "input_cost_per_token": 0.00001, + "max_tokens": 130000, + "mode": "chat", + "output_cost_per_token": 0.00003, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "openrouter" + }, + "openrouter/openai/gpt-4.1": { + "cache_read_input_token_cost": 5e-7, + "input_cost_per_token": 0.000002, + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0.000008, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "openrouter" + }, + "openrouter/openai/gpt-4.1-2025-04-14": { + "cache_read_input_token_cost": 5e-7, + "input_cost_per_token": 0.000002, + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0.000008, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "openrouter" + }, + "openrouter/openai/gpt-4.1-mini": { + "cache_read_input_token_cost": 1e-7, + "input_cost_per_token": 4e-7, + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0.0000016, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "openrouter" + }, + "openrouter/openai/gpt-4.1-mini-2025-04-14": { + "cache_read_input_token_cost": 1e-7, + "input_cost_per_token": 4e-7, + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0.0000016, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "openrouter" + }, + "openrouter/openai/gpt-4.1-nano": { + "cache_read_input_token_cost": 2.5e-8, + "input_cost_per_token": 1e-7, + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 4e-7, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "openrouter" + }, + "openrouter/openai/gpt-4.1-nano-2025-04-14": { + "cache_read_input_token_cost": 2.5e-8, + "input_cost_per_token": 1e-7, + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 4e-7, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "openrouter" + }, + "openrouter/openai/gpt-4o": { + "input_cost_per_token": 0.0000025, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.00001, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "openrouter" + }, + "openrouter/openai/gpt-4o-2024-05-13": { + "input_cost_per_token": 0.000005, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.000015, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "openrouter" + }, + "openrouter/openai/gpt-5-chat": { + "cache_read_input_token_cost": 1.25e-7, + "input_cost_per_token": 0.00000125, + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.00001, + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], + "supports_reasoning": true, + "supports_tool_choice": true, + "provider": "openrouter" + }, + "openrouter/openai/gpt-5-codex": { + "cache_read_input_token_cost": 1.25e-7, + "input_cost_per_token": 0.00000125, + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.00001, + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], + "supports_reasoning": true, + "supports_tool_choice": true, + "provider": "openrouter" + }, + "openrouter/openai/gpt-5": { + "cache_read_input_token_cost": 1.25e-7, + "input_cost_per_token": 0.00000125, + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.00001, + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], + "supports_reasoning": true, + "supports_tool_choice": true, + "provider": "openrouter" + }, + "openrouter/openai/gpt-5-mini": { + "cache_read_input_token_cost": 2.5e-8, + "input_cost_per_token": 2.5e-7, + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.000002, + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], + "supports_reasoning": true, + "supports_tool_choice": true, + "provider": "openrouter" + }, + "openrouter/openai/gpt-5-nano": { + "cache_read_input_token_cost": 5e-9, + "input_cost_per_token": 5e-8, + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4e-7, + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text"], + "supports_reasoning": true, + "supports_tool_choice": true, + "provider": "openrouter" + }, + "openrouter/openai/gpt-oss-120b": { + "input_cost_per_token": 1.8e-7, + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 8e-7, + "source": "https://openrouter.ai/openai/gpt-oss-120b", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "provider": "openrouter" + }, + "openrouter/openai/gpt-oss-20b": { + "input_cost_per_token": 1.8e-7, + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 8e-7, + "source": "https://openrouter.ai/openai/gpt-oss-20b", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "provider": "openrouter" + }, + "openrouter/openai/o1": { + "cache_read_input_token_cost": 0.0000075, + "input_cost_per_token": 0.000015, + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 0.00006, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "openrouter" + }, + "openrouter/openai/o1-mini": { + "input_cost_per_token": 0.000003, + "max_input_tokens": 128000, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 0.000012, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "supports_vision": false, + "provider": "openrouter" + }, + "openrouter/openai/o1-mini-2024-09-12": { + "input_cost_per_token": 0.000003, + "max_input_tokens": 128000, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 0.000012, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "supports_vision": false, + "provider": "openrouter" + }, + "openrouter/openai/o1-preview": { + "input_cost_per_token": 0.000015, + "max_input_tokens": 128000, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0.00006, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "supports_vision": false, + "provider": "openrouter" + }, + "openrouter/openai/o1-preview-2024-09-12": { + "input_cost_per_token": 0.000015, + "max_input_tokens": 128000, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0.00006, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "supports_vision": false, + "provider": "openrouter" + }, + "openrouter/openai/o3-mini": { + "input_cost_per_token": 0.0000011, + "max_input_tokens": 128000, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 0.0000044, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false, + "provider": "openrouter" + }, + "openrouter/openai/o3-mini-high": { + "input_cost_per_token": 0.0000011, + "max_input_tokens": 128000, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 0.0000044, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false, + "provider": "openrouter" + }, + "openrouter/pygmalionai/mythalion-13b": { + "input_cost_per_token": 0.000001875, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.000001875, + "supports_tool_choice": true, + "provider": "openrouter" + }, + "openrouter/qwen/qwen-2.5-coder-32b-instruct": { + "input_cost_per_token": 1.8e-7, + "max_input_tokens": 33792, + "max_output_tokens": 33792, + "max_tokens": 33792, + "mode": "chat", + "output_cost_per_token": 1.8e-7, + "supports_tool_choice": true, + "provider": "openrouter" + }, + "openrouter/qwen/qwen-vl-plus": { + "input_cost_per_token": 2.1e-7, + "max_input_tokens": 8192, + "max_output_tokens": 2048, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 6.3e-7, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "openrouter" + }, + "openrouter/qwen/qwen3-coder": { + "input_cost_per_token": 2.2e-7, + "max_input_tokens": 262100, + "max_output_tokens": 262100, + "max_tokens": 262100, + "mode": "chat", + "output_cost_per_token": 9.5e-7, + "source": "https://openrouter.ai/qwen/qwen3-coder", + "supports_tool_choice": true, + "supports_function_calling": true, + "provider": "openrouter" + }, + "openrouter/switchpoint/router": { + "input_cost_per_token": 8.5e-7, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 0.0000034, + "source": "https://openrouter.ai/switchpoint/router", + "supports_tool_choice": true, + "provider": "openrouter" + }, + "openrouter/undi95/remm-slerp-l2-13b": { + "input_cost_per_token": 0.000001875, + "max_tokens": 6144, + "mode": "chat", + "output_cost_per_token": 0.000001875, + "supports_tool_choice": true, + "provider": "openrouter" + }, + "openrouter/x-ai/grok-4": { + "input_cost_per_token": 0.000003, + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 0.000015, + "source": "https://openrouter.ai/x-ai/grok-4", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_web_search": true, + "provider": "openrouter" + }, + "openrouter/x-ai/grok-4-fast:free": { + "input_cost_per_token": 0, + "max_input_tokens": 2000000, + "max_output_tokens": 30000, + "max_tokens": 2000000, + "mode": "chat", + "output_cost_per_token": 0, + "source": "https://openrouter.ai/x-ai/grok-4-fast:free", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_web_search": false, + "provider": "openrouter" + }, + "openrouter/z-ai/glm-4.6": { + "input_cost_per_token": 4e-7, + "max_input_tokens": 202800, + "max_output_tokens": 131000, + "max_tokens": 202800, + "mode": "chat", + "output_cost_per_token": 0.00000175, + "source": "https://openrouter.ai/z-ai/glm-4.6", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "provider": "openrouter" + }, + "openrouter/z-ai/glm-4.6:exacto": { + "input_cost_per_token": 4.5e-7, + "max_input_tokens": 202800, + "max_output_tokens": 131000, + "max_tokens": 202800, + "mode": "chat", + "output_cost_per_token": 0.0000019, + "source": "https://openrouter.ai/z-ai/glm-4.6:exacto", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "provider": "openrouter" + }, + "ovhcloud/DeepSeek-R1-Distill-Llama-70B": { + "input_cost_per_token": 6.7e-7, + "max_input_tokens": 131000, + "max_output_tokens": 131000, + "max_tokens": 131000, + "mode": "chat", + "output_cost_per_token": 6.7e-7, + "source": "https://endpoints.ai.cloud.ovh.net/models/deepseek-r1-distill-llama-70b", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "provider": "ovhcloud" + }, + "ovhcloud/Llama-3.1-8B-Instruct": { + "input_cost_per_token": 1e-7, + "max_input_tokens": 131000, + "max_output_tokens": 131000, + "max_tokens": 131000, + "mode": "chat", + "output_cost_per_token": 1e-7, + "source": "https://endpoints.ai.cloud.ovh.net/models/llama-3-1-8b-instruct", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "provider": "ovhcloud" + }, + "ovhcloud/Meta-Llama-3_1-70B-Instruct": { + "input_cost_per_token": 6.7e-7, + "max_input_tokens": 131000, + "max_output_tokens": 131000, + "max_tokens": 131000, + "mode": "chat", + "output_cost_per_token": 6.7e-7, + "source": "https://endpoints.ai.cloud.ovh.net/models/meta-llama-3-1-70b-instruct", + "supports_function_calling": false, + "supports_response_schema": false, + "supports_tool_choice": false, + "provider": "ovhcloud" + }, + "ovhcloud/Meta-Llama-3_3-70B-Instruct": { + "input_cost_per_token": 6.7e-7, + "max_input_tokens": 131000, + "max_output_tokens": 131000, + "max_tokens": 131000, + "mode": "chat", + "output_cost_per_token": 6.7e-7, + "source": "https://endpoints.ai.cloud.ovh.net/models/meta-llama-3-3-70b-instruct", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "provider": "ovhcloud" + }, + "ovhcloud/Mistral-7B-Instruct-v0.3": { + "input_cost_per_token": 1e-7, + "max_input_tokens": 127000, + "max_output_tokens": 127000, + "max_tokens": 127000, + "mode": "chat", + "output_cost_per_token": 1e-7, + "source": "https://endpoints.ai.cloud.ovh.net/models/mistral-7b-instruct-v0-3", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "provider": "ovhcloud" + }, + "ovhcloud/Mistral-Nemo-Instruct-2407": { + "input_cost_per_token": 1.3e-7, + "max_input_tokens": 118000, + "max_output_tokens": 118000, + "max_tokens": 118000, + "mode": "chat", + "output_cost_per_token": 1.3e-7, + "source": "https://endpoints.ai.cloud.ovh.net/models/mistral-nemo-instruct-2407", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "provider": "ovhcloud" + }, + "ovhcloud/Mistral-Small-3.2-24B-Instruct-2506": { + "input_cost_per_token": 9e-8, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.8e-7, + "source": "https://endpoints.ai.cloud.ovh.net/models/mistral-small-3-2-24b-instruct-2506", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "ovhcloud" + }, + "ovhcloud/Mixtral-8x7B-Instruct-v0.1": { + "input_cost_per_token": 6.3e-7, + "max_input_tokens": 32000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 6.3e-7, + "source": "https://endpoints.ai.cloud.ovh.net/models/mixtral-8x7b-instruct-v0-1", + "supports_function_calling": false, + "supports_response_schema": true, + "supports_tool_choice": false, + "provider": "ovhcloud" + }, + "ovhcloud/Qwen2.5-Coder-32B-Instruct": { + "input_cost_per_token": 8.7e-7, + "max_input_tokens": 32000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 8.7e-7, + "source": "https://endpoints.ai.cloud.ovh.net/models/qwen2-5-coder-32b-instruct", + "supports_function_calling": false, + "supports_response_schema": true, + "supports_tool_choice": false, + "provider": "ovhcloud" + }, + "ovhcloud/Qwen2.5-VL-72B-Instruct": { + "input_cost_per_token": 9.1e-7, + "max_input_tokens": 32000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 9.1e-7, + "source": "https://endpoints.ai.cloud.ovh.net/models/qwen2-5-vl-72b-instruct", + "supports_function_calling": false, + "supports_response_schema": true, + "supports_tool_choice": false, + "supports_vision": true, + "provider": "ovhcloud" + }, + "ovhcloud/Qwen3-32B": { + "input_cost_per_token": 8e-8, + "max_input_tokens": 32000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 2.3e-7, + "source": "https://endpoints.ai.cloud.ovh.net/models/qwen3-32b", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "provider": "ovhcloud" + }, + "ovhcloud/gpt-oss-120b": { + "input_cost_per_token": 8e-8, + "max_input_tokens": 131000, + "max_output_tokens": 131000, + "max_tokens": 131000, + "mode": "chat", + "output_cost_per_token": 4e-7, + "source": "https://endpoints.ai.cloud.ovh.net/models/gpt-oss-120b", + "supports_function_calling": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": false, + "provider": "ovhcloud" + }, + "ovhcloud/gpt-oss-20b": { + "input_cost_per_token": 4e-8, + "max_input_tokens": 131000, + "max_output_tokens": 131000, + "max_tokens": 131000, + "mode": "chat", + "output_cost_per_token": 1.5e-7, + "source": "https://endpoints.ai.cloud.ovh.net/models/gpt-oss-20b", + "supports_function_calling": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": false, + "provider": "ovhcloud" + }, + "ovhcloud/llava-v1.6-mistral-7b-hf": { + "input_cost_per_token": 2.9e-7, + "max_input_tokens": 32000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 2.9e-7, + "source": "https://endpoints.ai.cloud.ovh.net/models/llava-next-mistral-7b", + "supports_function_calling": false, + "supports_response_schema": true, + "supports_tool_choice": false, + "supports_vision": true, + "provider": "ovhcloud" + }, + "ovhcloud/mamba-codestral-7B-v0.1": { + "input_cost_per_token": 1.9e-7, + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 1.9e-7, + "source": "https://endpoints.ai.cloud.ovh.net/models/mamba-codestral-7b-v0-1", + "supports_function_calling": false, + "supports_response_schema": true, + "supports_tool_choice": false, + "provider": "ovhcloud" + }, + "palm/chat-bison": { + "input_cost_per_token": 1.25e-7, + "max_input_tokens": 8192, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.25e-7, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "provider": "palm" + }, + "palm/chat-bison-001": { + "input_cost_per_token": 1.25e-7, + "max_input_tokens": 8192, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.25e-7, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "provider": "palm" + }, + "palm/text-bison": { + "input_cost_per_token": 1.25e-7, + "max_input_tokens": 8192, + "max_output_tokens": 1024, + "max_tokens": 1024, + "mode": "completion", + "output_cost_per_token": 1.25e-7, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "provider": "palm" + }, + "palm/text-bison-001": { + "input_cost_per_token": 1.25e-7, + "max_input_tokens": 8192, + "max_output_tokens": 1024, + "max_tokens": 1024, + "mode": "completion", + "output_cost_per_token": 1.25e-7, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "provider": "palm" + }, + "palm/text-bison-safety-off": { + "input_cost_per_token": 1.25e-7, + "max_input_tokens": 8192, + "max_output_tokens": 1024, + "max_tokens": 1024, + "mode": "completion", + "output_cost_per_token": 1.25e-7, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "provider": "palm" + }, + "palm/text-bison-safety-recitation-off": { + "input_cost_per_token": 1.25e-7, + "max_input_tokens": 8192, + "max_output_tokens": 1024, + "max_tokens": 1024, + "mode": "completion", + "output_cost_per_token": 1.25e-7, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "provider": "palm" + }, + "parallel_ai/search": { + "input_cost_per_query": 0.004, + "mode": "search", + "provider": "parallel_ai" + }, + "parallel_ai/search-pro": { + "input_cost_per_query": 0.009, + "mode": "search", + "provider": "parallel_ai" + }, + "perplexity/codellama-34b-instruct": { + "input_cost_per_token": 3.5e-7, + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 0.0000014, + "provider": "perplexity" + }, + "perplexity/codellama-70b-instruct": { + "input_cost_per_token": 7e-7, + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 0.0000028, + "provider": "perplexity" + }, + "perplexity/llama-2-70b-chat": { + "input_cost_per_token": 7e-7, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.0000028, + "provider": "perplexity" + }, + "perplexity/llama-3.1-70b-instruct": { + "input_cost_per_token": 0.000001, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 0.000001, + "provider": "perplexity" + }, + "perplexity/llama-3.1-8b-instruct": { + "input_cost_per_token": 2e-7, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2e-7, + "provider": "perplexity" + }, + "perplexity/llama-3.1-sonar-huge-128k-online": { + "deprecation_date": "2025-02-22", + "input_cost_per_token": 0.000005, + "max_input_tokens": 127072, + "max_output_tokens": 127072, + "max_tokens": 127072, + "mode": "chat", + "output_cost_per_token": 0.000005, + "provider": "perplexity" + }, + "perplexity/llama-3.1-sonar-large-128k-chat": { + "deprecation_date": "2025-02-22", + "input_cost_per_token": 0.000001, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 0.000001, + "provider": "perplexity" + }, + "perplexity/llama-3.1-sonar-large-128k-online": { + "deprecation_date": "2025-02-22", + "input_cost_per_token": 0.000001, + "max_input_tokens": 127072, + "max_output_tokens": 127072, + "max_tokens": 127072, + "mode": "chat", + "output_cost_per_token": 0.000001, + "provider": "perplexity" + }, + "perplexity/llama-3.1-sonar-small-128k-chat": { + "deprecation_date": "2025-02-22", + "input_cost_per_token": 2e-7, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2e-7, + "provider": "perplexity" + }, + "perplexity/llama-3.1-sonar-small-128k-online": { + "deprecation_date": "2025-02-22", + "input_cost_per_token": 2e-7, + "max_input_tokens": 127072, + "max_output_tokens": 127072, + "max_tokens": 127072, + "mode": "chat", + "output_cost_per_token": 2e-7, + "provider": "perplexity" + }, + "perplexity/mistral-7b-instruct": { + "input_cost_per_token": 7e-8, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2.8e-7, + "provider": "perplexity" + }, + "perplexity/mixtral-8x7b-instruct": { + "input_cost_per_token": 7e-8, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2.8e-7, + "provider": "perplexity" + }, + "perplexity/pplx-70b-chat": { + "input_cost_per_token": 7e-7, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.0000028, + "provider": "perplexity" + }, + "perplexity/pplx-70b-online": { + "input_cost_per_request": 0.005, + "input_cost_per_token": 0, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.0000028, + "provider": "perplexity" + }, + "perplexity/pplx-7b-chat": { + "input_cost_per_token": 7e-8, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2.8e-7, + "provider": "perplexity" + }, + "perplexity/pplx-7b-online": { + "input_cost_per_request": 0.005, + "input_cost_per_token": 0, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2.8e-7, + "provider": "perplexity" + }, + "perplexity/sonar": { + "input_cost_per_token": 0.000001, + "max_input_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.000001, + "search_context_cost_per_query": { + "search_context_size_high": 0.012, + "search_context_size_low": 0.005, + "search_context_size_medium": 0.008 + }, + "supports_web_search": true, + "provider": "perplexity" + }, + "perplexity/sonar-deep-research": { + "citation_cost_per_token": 0.000002, + "input_cost_per_token": 0.000002, + "max_input_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_reasoning_token": 0.000003, + "output_cost_per_token": 0.000008, + "search_context_cost_per_query": { + "search_context_size_high": 0.005, + "search_context_size_low": 0.005, + "search_context_size_medium": 0.005 + }, + "supports_reasoning": true, + "supports_web_search": true, + "provider": "perplexity" + }, + "perplexity/sonar-medium-chat": { + "input_cost_per_token": 6e-7, + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 0.0000018, + "provider": "perplexity" + }, + "perplexity/sonar-medium-online": { + "input_cost_per_request": 0.005, + "input_cost_per_token": 0, + "max_input_tokens": 12000, + "max_output_tokens": 12000, + "max_tokens": 12000, + "mode": "chat", + "output_cost_per_token": 0.0000018, + "provider": "perplexity" + }, + "perplexity/sonar-pro": { + "input_cost_per_token": 0.000003, + "max_input_tokens": 200000, + "max_output_tokens": 8000, + "max_tokens": 8000, + "mode": "chat", + "output_cost_per_token": 0.000015, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.006, + "search_context_size_medium": 0.01 + }, + "supports_web_search": true, + "provider": "perplexity" + }, + "perplexity/sonar-reasoning": { + "input_cost_per_token": 0.000001, + "max_input_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.000005, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.005, + "search_context_size_medium": 0.008 + }, + "supports_reasoning": true, + "supports_web_search": true, + "provider": "perplexity" + }, + "perplexity/sonar-reasoning-pro": { + "input_cost_per_token": 0.000002, + "max_input_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.000008, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.006, + "search_context_size_medium": 0.01 + }, + "supports_reasoning": true, + "supports_web_search": true, + "provider": "perplexity" + }, + "perplexity/sonar-small-chat": { + "input_cost_per_token": 7e-8, + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 2.8e-7, + "provider": "perplexity" + }, + "perplexity/sonar-small-online": { + "input_cost_per_request": 0.005, + "input_cost_per_token": 0, + "max_input_tokens": 12000, + "max_output_tokens": 12000, + "max_tokens": 12000, + "mode": "chat", + "output_cost_per_token": 2.8e-7, + "provider": "perplexity" + }, + "qwen.qwen3-coder-480b-a35b-v1:0": { + "input_cost_per_token": 2.2e-7, + "max_input_tokens": 262000, + "max_output_tokens": 65536, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 0.0000018, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "provider": "bedrock_converse" + }, + "qwen.qwen3-235b-a22b-2507-v1:0": { + "input_cost_per_token": 2.2e-7, + "max_input_tokens": 262144, + "max_output_tokens": 131072, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 8.8e-7, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "provider": "bedrock_converse" + }, + "qwen.qwen3-coder-30b-a3b-v1:0": { + "input_cost_per_token": 1.5e-7, + "max_input_tokens": 262144, + "max_output_tokens": 131072, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 6e-7, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "provider": "bedrock_converse" + }, + "qwen.qwen3-32b-v1:0": { + "input_cost_per_token": 1.5e-7, + "max_input_tokens": 131072, + "max_output_tokens": 16384, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 6e-7, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "provider": "bedrock_converse" + }, + "recraft/recraftv2": { + "mode": "image_generation", + "output_cost_per_image": 0.022, + "source": "https://www.recraft.ai/docs#pricing", + "supported_endpoints": ["/v1/images/generations"], + "provider": "recraft" + }, + "recraft/recraftv3": { + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://www.recraft.ai/docs#pricing", + "supported_endpoints": ["/v1/images/generations"], + "provider": "recraft" + }, + "replicate/meta/llama-2-13b": { + "input_cost_per_token": 1e-7, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 5e-7, + "supports_tool_choice": true, + "provider": "replicate" + }, + "replicate/meta/llama-2-13b-chat": { + "input_cost_per_token": 1e-7, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 5e-7, + "supports_tool_choice": true, + "provider": "replicate" + }, + "replicate/meta/llama-2-70b": { + "input_cost_per_token": 6.5e-7, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.00000275, + "supports_tool_choice": true, + "provider": "replicate" + }, + "replicate/meta/llama-2-70b-chat": { + "input_cost_per_token": 6.5e-7, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.00000275, + "supports_tool_choice": true, + "provider": "replicate" + }, + "replicate/meta/llama-2-7b": { + "input_cost_per_token": 5e-8, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2.5e-7, + "supports_tool_choice": true, + "provider": "replicate" + }, + "replicate/meta/llama-2-7b-chat": { + "input_cost_per_token": 5e-8, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2.5e-7, + "supports_tool_choice": true, + "provider": "replicate" + }, + "replicate/meta/llama-3-70b": { + "input_cost_per_token": 6.5e-7, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.00000275, + "supports_tool_choice": true, + "provider": "replicate" + }, + "replicate/meta/llama-3-70b-instruct": { + "input_cost_per_token": 6.5e-7, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.00000275, + "supports_tool_choice": true, + "provider": "replicate" + }, + "replicate/meta/llama-3-8b": { + "input_cost_per_token": 5e-8, + "max_input_tokens": 8086, + "max_output_tokens": 8086, + "max_tokens": 8086, + "mode": "chat", + "output_cost_per_token": 2.5e-7, + "supports_tool_choice": true, + "provider": "replicate" + }, + "replicate/meta/llama-3-8b-instruct": { + "input_cost_per_token": 5e-8, + "max_input_tokens": 8086, + "max_output_tokens": 8086, + "max_tokens": 8086, + "mode": "chat", + "output_cost_per_token": 2.5e-7, + "supports_tool_choice": true, + "provider": "replicate" + }, + "replicate/mistralai/mistral-7b-instruct-v0.2": { + "input_cost_per_token": 5e-8, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2.5e-7, + "supports_tool_choice": true, + "provider": "replicate" + }, + "replicate/mistralai/mistral-7b-v0.1": { + "input_cost_per_token": 5e-8, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2.5e-7, + "supports_tool_choice": true, + "provider": "replicate" + }, + "replicate/mistralai/mixtral-8x7b-instruct-v0.1": { + "input_cost_per_token": 3e-7, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.000001, + "supports_tool_choice": true, + "provider": "replicate" + }, + "rerank-english-v2.0": { + "input_cost_per_query": 0.002, + "input_cost_per_token": 0, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_query_tokens": 2048, + "max_tokens": 4096, + "mode": "rerank", + "output_cost_per_token": 0, + "provider": "cohere" + }, + "rerank-english-v3.0": { + "input_cost_per_query": 0.002, + "input_cost_per_token": 0, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_query_tokens": 2048, + "max_tokens": 4096, + "mode": "rerank", + "output_cost_per_token": 0, + "provider": "cohere" + }, + "rerank-multilingual-v2.0": { + "input_cost_per_query": 0.002, + "input_cost_per_token": 0, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_query_tokens": 2048, + "max_tokens": 4096, + "mode": "rerank", + "output_cost_per_token": 0, + "provider": "cohere" + }, + "rerank-multilingual-v3.0": { + "input_cost_per_query": 0.002, + "input_cost_per_token": 0, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_query_tokens": 2048, + "max_tokens": 4096, + "mode": "rerank", + "output_cost_per_token": 0, + "provider": "cohere" + }, + "rerank-v3.5": { + "input_cost_per_query": 0.002, + "input_cost_per_token": 0, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_query_tokens": 2048, + "max_tokens": 4096, + "mode": "rerank", + "output_cost_per_token": 0, + "provider": "cohere" + }, + "nvidia_nim/nvidia/nv-rerankqa-mistral-4b-v3": { + "input_cost_per_query": 0, + "input_cost_per_token": 0, + "mode": "rerank", + "output_cost_per_token": 0, + "provider": "nvidia_nim" + }, + "nvidia_nim/nvidia/llama-3_2-nv-rerankqa-1b-v2": { + "input_cost_per_query": 0, + "input_cost_per_token": 0, + "mode": "rerank", + "output_cost_per_token": 0, + "provider": "nvidia_nim" + }, + "sagemaker/meta-textgeneration-llama-2-13b": { + "input_cost_per_token": 0, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "completion", + "output_cost_per_token": 0, + "provider": "sagemaker" + }, + "sagemaker/meta-textgeneration-llama-2-13b-f": { + "input_cost_per_token": 0, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0, + "provider": "sagemaker" + }, + "sagemaker/meta-textgeneration-llama-2-70b": { + "input_cost_per_token": 0, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "completion", + "output_cost_per_token": 0, + "provider": "sagemaker" + }, + "sagemaker/meta-textgeneration-llama-2-70b-b-f": { + "input_cost_per_token": 0, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0, + "provider": "sagemaker" + }, + "sagemaker/meta-textgeneration-llama-2-7b": { + "input_cost_per_token": 0, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "completion", + "output_cost_per_token": 0, + "provider": "sagemaker" + }, + "sagemaker/meta-textgeneration-llama-2-7b-f": { + "input_cost_per_token": 0, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0, + "provider": "sagemaker" + }, + "sambanova/DeepSeek-R1": { + "input_cost_per_token": 0.000005, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0.000007, + "source": "https://cloud.sambanova.ai/plans/pricing", + "provider": "sambanova" + }, + "sambanova/DeepSeek-R1-Distill-Llama-70B": { + "input_cost_per_token": 7e-7, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 0.0000014, + "source": "https://cloud.sambanova.ai/plans/pricing", + "provider": "sambanova" + }, + "sambanova/DeepSeek-V3-0324": { + "input_cost_per_token": 0.000003, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0.0000045, + "source": "https://cloud.sambanova.ai/plans/pricing", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "provider": "sambanova" + }, + "sambanova/Llama-4-Maverick-17B-128E-Instruct": { + "input_cost_per_token": 6.3e-7, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "metadata": { + "notes": "For vision models, images are converted to 6432 input tokens and are billed at that amount" + }, + "mode": "chat", + "output_cost_per_token": 0.0000018, + "source": "https://cloud.sambanova.ai/plans/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "sambanova" + }, + "sambanova/Llama-4-Scout-17B-16E-Instruct": { + "input_cost_per_token": 4e-7, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "metadata": { + "notes": "For vision models, images are converted to 6432 input tokens and are billed at that amount" + }, + "mode": "chat", + "output_cost_per_token": 7e-7, + "source": "https://cloud.sambanova.ai/plans/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "provider": "sambanova" + }, + "sambanova/Meta-Llama-3.1-405B-Instruct": { + "input_cost_per_token": 0.000005, + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 0.00001, + "source": "https://cloud.sambanova.ai/plans/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "provider": "sambanova" + }, + "sambanova/Meta-Llama-3.1-8B-Instruct": { + "input_cost_per_token": 1e-7, + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 2e-7, + "source": "https://cloud.sambanova.ai/plans/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "provider": "sambanova" + }, + "sambanova/Meta-Llama-3.2-1B-Instruct": { + "input_cost_per_token": 4e-8, + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 8e-8, + "source": "https://cloud.sambanova.ai/plans/pricing", + "provider": "sambanova" + }, + "sambanova/Meta-Llama-3.2-3B-Instruct": { + "input_cost_per_token": 8e-8, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.6e-7, + "source": "https://cloud.sambanova.ai/plans/pricing", + "provider": "sambanova" + }, + "sambanova/Meta-Llama-3.3-70B-Instruct": { + "input_cost_per_token": 6e-7, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 0.0000012, + "source": "https://cloud.sambanova.ai/plans/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "provider": "sambanova" + }, + "sambanova/Meta-Llama-Guard-3-8B": { + "input_cost_per_token": 3e-7, + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 3e-7, + "source": "https://cloud.sambanova.ai/plans/pricing", + "provider": "sambanova" + }, + "sambanova/QwQ-32B": { + "input_cost_per_token": 5e-7, + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 0.000001, + "source": "https://cloud.sambanova.ai/plans/pricing", + "provider": "sambanova" + }, + "sambanova/Qwen2-Audio-7B-Instruct": { + "input_cost_per_token": 5e-7, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.0001, + "source": "https://cloud.sambanova.ai/plans/pricing", + "supports_audio_input": true, + "provider": "sambanova" + }, + "sambanova/Qwen3-32B": { + "input_cost_per_token": 4e-7, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 8e-7, + "source": "https://cloud.sambanova.ai/plans/pricing", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "provider": "sambanova" + }, + "sambanova/DeepSeek-V3.1": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 0.000003, + "output_cost_per_token": 0.0000045, + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "source": "https://cloud.sambanova.ai/plans/pricing", + "provider": "sambanova" + }, + "sambanova/gpt-oss-120b": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 0.000003, + "output_cost_per_token": 0.0000045, + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "source": "https://cloud.sambanova.ai/plans/pricing", + "provider": "sambanova" + }, + "snowflake/claude-3-5-sonnet": { + "max_input_tokens": 18000, + "max_output_tokens": 8192, + "max_tokens": 18000, + "mode": "chat", + "supports_computer_use": true, + "provider": "snowflake" + }, + "snowflake/deepseek-r1": { + "max_input_tokens": 32768, + "max_output_tokens": 8192, + "max_tokens": 32768, + "mode": "chat", + "supports_reasoning": true, + "provider": "snowflake" + }, + "snowflake/gemma-7b": { + "max_input_tokens": 8000, + "max_output_tokens": 8192, + "max_tokens": 8000, + "mode": "chat", + "provider": "snowflake" + }, + "snowflake/jamba-1.5-large": { + "max_input_tokens": 256000, + "max_output_tokens": 8192, + "max_tokens": 256000, + "mode": "chat", + "provider": "snowflake" + }, + "snowflake/jamba-1.5-mini": { + "max_input_tokens": 256000, + "max_output_tokens": 8192, + "max_tokens": 256000, + "mode": "chat", + "provider": "snowflake" + }, + "snowflake/jamba-instruct": { + "max_input_tokens": 256000, + "max_output_tokens": 8192, + "max_tokens": 256000, + "mode": "chat", + "provider": "snowflake" + }, + "snowflake/llama2-70b-chat": { + "max_input_tokens": 4096, + "max_output_tokens": 8192, + "max_tokens": 4096, + "mode": "chat", + "provider": "snowflake" + }, + "snowflake/llama3-70b": { + "max_input_tokens": 8000, + "max_output_tokens": 8192, + "max_tokens": 8000, + "mode": "chat", + "provider": "snowflake" + }, + "snowflake/llama3-8b": { + "max_input_tokens": 8000, + "max_output_tokens": 8192, + "max_tokens": 8000, + "mode": "chat", + "provider": "snowflake" + }, + "snowflake/llama3.1-405b": { + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 128000, + "mode": "chat", + "provider": "snowflake" + }, + "snowflake/llama3.1-70b": { + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 128000, + "mode": "chat", + "provider": "snowflake" + }, + "snowflake/llama3.1-8b": { + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 128000, + "mode": "chat", + "provider": "snowflake" + }, + "snowflake/llama3.2-1b": { + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 128000, + "mode": "chat", + "provider": "snowflake" + }, + "snowflake/llama3.2-3b": { + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 128000, + "mode": "chat", + "provider": "snowflake" + }, + "snowflake/llama3.3-70b": { + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 128000, + "mode": "chat", + "provider": "snowflake" + }, + "snowflake/mistral-7b": { + "max_input_tokens": 32000, + "max_output_tokens": 8192, + "max_tokens": 32000, + "mode": "chat", + "provider": "snowflake" + }, + "snowflake/mistral-large": { + "max_input_tokens": 32000, + "max_output_tokens": 8192, + "max_tokens": 32000, + "mode": "chat", + "provider": "snowflake" + }, + "snowflake/mistral-large2": { + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 128000, + "mode": "chat", + "provider": "snowflake" + }, + "snowflake/mixtral-8x7b": { + "max_input_tokens": 32000, + "max_output_tokens": 8192, + "max_tokens": 32000, + "mode": "chat", + "provider": "snowflake" + }, + "snowflake/reka-core": { + "max_input_tokens": 32000, + "max_output_tokens": 8192, + "max_tokens": 32000, + "mode": "chat", + "provider": "snowflake" + }, + "snowflake/reka-flash": { + "max_input_tokens": 100000, + "max_output_tokens": 8192, + "max_tokens": 100000, + "mode": "chat", + "provider": "snowflake" + }, + "snowflake/snowflake-arctic": { + "max_input_tokens": 4096, + "max_output_tokens": 8192, + "max_tokens": 4096, + "mode": "chat", + "provider": "snowflake" + }, + "snowflake/snowflake-llama-3.1-405b": { + "max_input_tokens": 8000, + "max_output_tokens": 8192, + "max_tokens": 8000, + "mode": "chat", + "provider": "snowflake" + }, + "snowflake/snowflake-llama-3.3-70b": { + "max_input_tokens": 8000, + "max_output_tokens": 8192, + "max_tokens": 8000, + "mode": "chat", + "provider": "snowflake" + }, + "stability.sd3-5-large-v1:0": { + "max_input_tokens": 77, + "max_tokens": 77, + "mode": "image_generation", + "output_cost_per_image": 0.08, + "provider": "bedrock" + }, + "stability.sd3-large-v1:0": { + "max_input_tokens": 77, + "max_tokens": 77, + "mode": "image_generation", + "output_cost_per_image": 0.08, + "provider": "bedrock" + }, + "stability.stable-image-core-v1:0": { + "max_input_tokens": 77, + "max_tokens": 77, + "mode": "image_generation", + "output_cost_per_image": 0.04, + "provider": "bedrock" + }, + "stability.stable-image-core-v1:1": { + "max_input_tokens": 77, + "max_tokens": 77, + "mode": "image_generation", + "output_cost_per_image": 0.04, + "provider": "bedrock" + }, + "stability.stable-image-ultra-v1:0": { + "max_input_tokens": 77, + "max_tokens": 77, + "mode": "image_generation", + "output_cost_per_image": 0.14, + "provider": "bedrock" + }, + "stability.stable-image-ultra-v1:1": { + "max_input_tokens": 77, + "max_tokens": 77, + "mode": "image_generation", + "output_cost_per_image": 0.14, + "provider": "bedrock" + }, + "standard/1024-x-1024/dall-e-3": { + "input_cost_per_pixel": 3.81469e-8, + "mode": "image_generation", + "output_cost_per_pixel": 0, + "provider": "openai" + }, + "standard/1024-x-1792/dall-e-3": { + "input_cost_per_pixel": 4.359e-8, + "mode": "image_generation", + "output_cost_per_pixel": 0, + "provider": "openai" + }, + "standard/1792-x-1024/dall-e-3": { + "input_cost_per_pixel": 4.359e-8, + "mode": "image_generation", + "output_cost_per_pixel": 0, + "provider": "openai" + }, + "tavily/search": { + "input_cost_per_query": 0.008, + "mode": "search", + "provider": "tavily" + }, + "tavily/search-advanced": { + "input_cost_per_query": 0.016, + "mode": "search", + "provider": "tavily" + }, + "text-bison": { + "input_cost_per_character": 2.5e-7, + "max_input_tokens": 8192, + "max_output_tokens": 2048, + "max_tokens": 2048, + "mode": "completion", + "output_cost_per_character": 5e-7, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "provider": "vertex_ai-text-models" + }, + "text-bison32k": { + "input_cost_per_character": 2.5e-7, + "input_cost_per_token": 1.25e-7, + "max_input_tokens": 8192, + "max_output_tokens": 1024, + "max_tokens": 1024, + "mode": "completion", + "output_cost_per_character": 5e-7, + "output_cost_per_token": 1.25e-7, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "provider": "vertex_ai-text-models" + }, + "text-bison32k@002": { + "input_cost_per_character": 2.5e-7, + "input_cost_per_token": 1.25e-7, + "max_input_tokens": 8192, + "max_output_tokens": 1024, + "max_tokens": 1024, + "mode": "completion", + "output_cost_per_character": 5e-7, + "output_cost_per_token": 1.25e-7, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "provider": "vertex_ai-text-models" + }, + "text-bison@001": { + "input_cost_per_character": 2.5e-7, + "max_input_tokens": 8192, + "max_output_tokens": 1024, + "max_tokens": 1024, + "mode": "completion", + "output_cost_per_character": 5e-7, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "provider": "vertex_ai-text-models" + }, + "text-bison@002": { + "input_cost_per_character": 2.5e-7, + "max_input_tokens": 8192, + "max_output_tokens": 1024, + "max_tokens": 1024, + "mode": "completion", + "output_cost_per_character": 5e-7, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "provider": "vertex_ai-text-models" + }, + "text-completion-codestral/codestral-2405": { + "input_cost_per_token": 0, + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "completion", + "output_cost_per_token": 0, + "source": "https://docs.mistral.ai/capabilities/code_generation/", + "provider": "text-completion-codestral" + }, + "text-completion-codestral/codestral-latest": { + "input_cost_per_token": 0, + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "completion", + "output_cost_per_token": 0, + "source": "https://docs.mistral.ai/capabilities/code_generation/", + "provider": "text-completion-codestral" + }, + "text-embedding-004": { + "input_cost_per_character": 2.5e-8, + "input_cost_per_token": 1e-7, + "max_input_tokens": 2048, + "max_tokens": 2048, + "mode": "embedding", + "output_cost_per_token": 0, + "output_vector_size": 768, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models", + "provider": "vertex_ai-embedding-models" + }, + "text-embedding-005": { + "input_cost_per_character": 2.5e-8, + "input_cost_per_token": 1e-7, + "max_input_tokens": 2048, + "max_tokens": 2048, + "mode": "embedding", + "output_cost_per_token": 0, + "output_vector_size": 768, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models", + "provider": "vertex_ai-embedding-models" + }, + "text-embedding-3-large": { + "input_cost_per_token": 1.3e-7, + "input_cost_per_token_batches": 6.5e-8, + "max_input_tokens": 8191, + "max_tokens": 8191, + "mode": "embedding", + "output_cost_per_token": 0, + "output_cost_per_token_batches": 0, + "output_vector_size": 3072, + "provider": "openai" + }, + "text-embedding-3-small": { + "input_cost_per_token": 2e-8, + "input_cost_per_token_batches": 1e-8, + "max_input_tokens": 8191, + "max_tokens": 8191, + "mode": "embedding", + "output_cost_per_token": 0, + "output_cost_per_token_batches": 0, + "output_vector_size": 1536, + "provider": "openai" + }, + "text-embedding-ada-002": { + "input_cost_per_token": 1e-7, + "max_input_tokens": 8191, + "max_tokens": 8191, + "mode": "embedding", + "output_cost_per_token": 0, + "output_vector_size": 1536, + "provider": "openai" + }, + "text-embedding-ada-002-v2": { + "input_cost_per_token": 1e-7, + "input_cost_per_token_batches": 5e-8, + "max_input_tokens": 8191, + "max_tokens": 8191, + "mode": "embedding", + "output_cost_per_token": 0, + "output_cost_per_token_batches": 0, + "provider": "openai" + }, + "text-embedding-large-exp-03-07": { + "input_cost_per_character": 2.5e-8, + "input_cost_per_token": 1e-7, + "max_input_tokens": 8192, + "max_tokens": 8192, + "mode": "embedding", + "output_cost_per_token": 0, + "output_vector_size": 3072, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models", + "provider": "vertex_ai-embedding-models" + }, + "text-embedding-preview-0409": { + "input_cost_per_token": 6.25e-9, + "input_cost_per_token_batch_requests": 5e-9, + "max_input_tokens": 3072, + "max_tokens": 3072, + "mode": "embedding", + "output_cost_per_token": 0, + "output_vector_size": 768, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "provider": "vertex_ai-embedding-models" + }, + "text-moderation-007": { + "input_cost_per_token": 0, + "max_input_tokens": 32768, + "max_output_tokens": 0, + "max_tokens": 32768, + "mode": "moderation", + "output_cost_per_token": 0, + "provider": "openai" + }, + "text-moderation-latest": { + "input_cost_per_token": 0, + "max_input_tokens": 32768, + "max_output_tokens": 0, + "max_tokens": 32768, + "mode": "moderation", + "output_cost_per_token": 0, + "provider": "openai" + }, + "text-moderation-stable": { + "input_cost_per_token": 0, + "max_input_tokens": 32768, + "max_output_tokens": 0, + "max_tokens": 32768, + "mode": "moderation", + "output_cost_per_token": 0, + "provider": "openai" + }, + "text-multilingual-embedding-002": { + "input_cost_per_character": 2.5e-8, + "input_cost_per_token": 1e-7, + "max_input_tokens": 2048, + "max_tokens": 2048, + "mode": "embedding", + "output_cost_per_token": 0, + "output_vector_size": 768, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models", + "provider": "vertex_ai-embedding-models" + }, + "text-multilingual-embedding-preview-0409": { + "input_cost_per_token": 6.25e-9, + "max_input_tokens": 3072, + "max_tokens": 3072, + "mode": "embedding", + "output_cost_per_token": 0, + "output_vector_size": 768, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "provider": "vertex_ai-embedding-models" + }, + "text-unicorn": { + "input_cost_per_token": 0.00001, + "max_input_tokens": 8192, + "max_output_tokens": 1024, + "max_tokens": 1024, + "mode": "completion", + "output_cost_per_token": 0.000028, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "provider": "vertex_ai-text-models" + }, + "text-unicorn@001": { + "input_cost_per_token": 0.00001, + "max_input_tokens": 8192, + "max_output_tokens": 1024, + "max_tokens": 1024, + "mode": "completion", + "output_cost_per_token": 0.000028, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "provider": "vertex_ai-text-models" + }, + "textembedding-gecko": { + "input_cost_per_character": 2.5e-8, + "input_cost_per_token": 1e-7, + "max_input_tokens": 3072, + "max_tokens": 3072, + "mode": "embedding", + "output_cost_per_token": 0, + "output_vector_size": 768, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "provider": "vertex_ai-embedding-models" + }, + "textembedding-gecko-multilingual": { + "input_cost_per_character": 2.5e-8, + "input_cost_per_token": 1e-7, + "max_input_tokens": 3072, + "max_tokens": 3072, + "mode": "embedding", + "output_cost_per_token": 0, + "output_vector_size": 768, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "provider": "vertex_ai-embedding-models" + }, + "textembedding-gecko-multilingual@001": { + "input_cost_per_character": 2.5e-8, + "input_cost_per_token": 1e-7, + "max_input_tokens": 3072, + "max_tokens": 3072, + "mode": "embedding", + "output_cost_per_token": 0, + "output_vector_size": 768, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "provider": "vertex_ai-embedding-models" + }, + "textembedding-gecko@001": { + "input_cost_per_character": 2.5e-8, + "input_cost_per_token": 1e-7, + "max_input_tokens": 3072, + "max_tokens": 3072, + "mode": "embedding", + "output_cost_per_token": 0, + "output_vector_size": 768, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "provider": "vertex_ai-embedding-models" + }, + "textembedding-gecko@003": { + "input_cost_per_character": 2.5e-8, + "input_cost_per_token": 1e-7, + "max_input_tokens": 3072, + "max_tokens": 3072, + "mode": "embedding", + "output_cost_per_token": 0, + "output_vector_size": 768, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "provider": "vertex_ai-embedding-models" + }, + "together-ai-21.1b-41b": { + "input_cost_per_token": 8e-7, + "mode": "chat", + "output_cost_per_token": 8e-7, + "provider": "together_ai" + }, + "together-ai-4.1b-8b": { + "input_cost_per_token": 2e-7, + "mode": "chat", + "output_cost_per_token": 2e-7, + "provider": "together_ai" + }, + "together-ai-41.1b-80b": { + "input_cost_per_token": 9e-7, + "mode": "chat", + "output_cost_per_token": 9e-7, + "provider": "together_ai" + }, + "together-ai-8.1b-21b": { + "input_cost_per_token": 3e-7, + "max_tokens": 1000, + "mode": "chat", + "output_cost_per_token": 3e-7, + "provider": "together_ai" + }, + "together-ai-81.1b-110b": { + "input_cost_per_token": 0.0000018, + "mode": "chat", + "output_cost_per_token": 0.0000018, + "provider": "together_ai" + }, + "together-ai-embedding-151m-to-350m": { + "input_cost_per_token": 1.6e-8, + "mode": "embedding", + "output_cost_per_token": 0, + "provider": "together_ai" + }, + "together-ai-embedding-up-to-150m": { + "input_cost_per_token": 8e-9, + "mode": "embedding", + "output_cost_per_token": 0, + "provider": "together_ai" + }, + "together_ai/baai/bge-base-en-v1.5": { + "input_cost_per_token": 8e-9, + "max_input_tokens": 512, + "mode": "embedding", + "output_cost_per_token": 0, + "output_vector_size": 768, + "provider": "together_ai" + }, + "together_ai/BAAI/bge-base-en-v1.5": { + "input_cost_per_token": 8e-9, + "max_input_tokens": 512, + "mode": "embedding", + "output_cost_per_token": 0, + "output_vector_size": 768, + "provider": "together_ai" + }, + "together-ai-up-to-4b": { + "input_cost_per_token": 1e-7, + "mode": "chat", + "output_cost_per_token": 1e-7, + "provider": "together_ai" + }, + "together_ai/Qwen/Qwen2.5-72B-Instruct-Turbo": { + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "provider": "together_ai" + }, + "together_ai/Qwen/Qwen2.5-7B-Instruct-Turbo": { + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "provider": "together_ai" + }, + "together_ai/Qwen/Qwen3-235B-A22B-Instruct-2507-tput": { + "input_cost_per_token": 2e-7, + "max_input_tokens": 262000, + "mode": "chat", + "output_cost_per_token": 0.000006, + "source": "https://www.together.ai/models/qwen3-235b-a22b-instruct-2507-fp8", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "provider": "together_ai" + }, + "together_ai/Qwen/Qwen3-235B-A22B-Thinking-2507": { + "input_cost_per_token": 6.5e-7, + "max_input_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 0.000003, + "source": "https://www.together.ai/models/qwen3-235b-a22b-thinking-2507", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "provider": "together_ai" + }, + "together_ai/Qwen/Qwen3-235B-A22B-fp8-tput": { + "input_cost_per_token": 2e-7, + "max_input_tokens": 40000, + "mode": "chat", + "output_cost_per_token": 6e-7, + "source": "https://www.together.ai/models/qwen3-235b-a22b-fp8-tput", + "supports_function_calling": false, + "supports_parallel_function_calling": false, + "supports_tool_choice": false, + "provider": "together_ai" + }, + "together_ai/Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8": { + "input_cost_per_token": 0.000002, + "max_input_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 0.000002, + "source": "https://www.together.ai/models/qwen3-coder-480b-a35b-instruct", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "provider": "together_ai" + }, + "together_ai/deepseek-ai/DeepSeek-R1": { + "input_cost_per_token": 0.000003, + "max_input_tokens": 128000, + "max_output_tokens": 20480, + "max_tokens": 20480, + "mode": "chat", + "output_cost_per_token": 0.000007, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "provider": "together_ai" + }, + "together_ai/deepseek-ai/DeepSeek-R1-0528-tput": { + "input_cost_per_token": 5.5e-7, + "max_input_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.00000219, + "source": "https://www.together.ai/models/deepseek-r1-0528-throughput", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "provider": "together_ai" + }, + "together_ai/deepseek-ai/DeepSeek-V3": { + "input_cost_per_token": 0.00000125, + "max_input_tokens": 65536, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.00000125, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "provider": "together_ai" + }, + "together_ai/deepseek-ai/DeepSeek-V3.1": { + "input_cost_per_token": 6e-7, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.0000017, + "source": "https://www.together.ai/models/deepseek-v3-1", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "provider": "together_ai" + }, + "together_ai/meta-llama/Llama-3.2-3B-Instruct-Turbo": { + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "provider": "together_ai" + }, + "together_ai/meta-llama/Llama-3.3-70B-Instruct-Turbo": { + "input_cost_per_token": 8.8e-7, + "mode": "chat", + "output_cost_per_token": 8.8e-7, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "provider": "together_ai" + }, + "together_ai/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free": { + "input_cost_per_token": 0, + "mode": "chat", + "output_cost_per_token": 0, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "provider": "together_ai" + }, + "together_ai/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8": { + "input_cost_per_token": 2.7e-7, + "mode": "chat", + "output_cost_per_token": 8.5e-7, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "provider": "together_ai" + }, + "together_ai/meta-llama/Llama-4-Scout-17B-16E-Instruct": { + "input_cost_per_token": 1.8e-7, + "mode": "chat", + "output_cost_per_token": 5.9e-7, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "provider": "together_ai" + }, + "together_ai/meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo": { + "input_cost_per_token": 0.0000035, + "mode": "chat", + "output_cost_per_token": 0.0000035, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "provider": "together_ai" + }, + "together_ai/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo": { + "input_cost_per_token": 8.8e-7, + "mode": "chat", + "output_cost_per_token": 8.8e-7, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "provider": "together_ai" + }, + "together_ai/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo": { + "input_cost_per_token": 1.8e-7, + "mode": "chat", + "output_cost_per_token": 1.8e-7, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "provider": "together_ai" + }, + "together_ai/mistralai/Mistral-7B-Instruct-v0.1": { + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "provider": "together_ai" + }, + "together_ai/mistralai/Mistral-Small-24B-Instruct-2501": { + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "provider": "together_ai" + }, + "together_ai/mistralai/Mixtral-8x7B-Instruct-v0.1": { + "input_cost_per_token": 6e-7, + "mode": "chat", + "output_cost_per_token": 6e-7, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "provider": "together_ai" + }, + "together_ai/moonshotai/Kimi-K2-Instruct": { + "input_cost_per_token": 0.000001, + "mode": "chat", + "output_cost_per_token": 0.000003, + "source": "https://www.together.ai/models/kimi-k2-instruct", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "provider": "together_ai" + }, + "together_ai/openai/gpt-oss-120b": { + "input_cost_per_token": 1.5e-7, + "max_input_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-7, + "source": "https://www.together.ai/models/gpt-oss-120b", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "provider": "together_ai" + }, + "together_ai/openai/gpt-oss-20b": { + "input_cost_per_token": 5e-8, + "max_input_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2e-7, + "source": "https://www.together.ai/models/gpt-oss-20b", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "provider": "together_ai" + }, + "together_ai/togethercomputer/CodeLlama-34b-Instruct": { + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "provider": "together_ai" + }, + "together_ai/zai-org/GLM-4.5-Air-FP8": { + "input_cost_per_token": 2e-7, + "max_input_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.0000011, + "source": "https://www.together.ai/models/glm-4-5-air", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "provider": "together_ai" + }, + "together_ai/zai-org/GLM-4.6": { + "input_cost_per_token": 6e-7, + "max_input_tokens": 200000, + "max_output_tokens": 200000, + "max_tokens": 200000, + "mode": "chat", + "output_cost_per_token": 0.0000022, + "source": "https://www.together.ai/models/glm-4-6", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "provider": "together_ai" + }, + "together_ai/moonshotai/Kimi-K2-Instruct-0905": { + "input_cost_per_token": 0.000001, + "max_input_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 0.000003, + "source": "https://www.together.ai/models/kimi-k2-0905", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "provider": "together_ai" + }, + "together_ai/Qwen/Qwen3-Next-80B-A3B-Instruct": { + "input_cost_per_token": 1.5e-7, + "max_input_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 0.0000015, + "source": "https://www.together.ai/models/qwen3-next-80b-a3b-instruct", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "provider": "together_ai" + }, + "together_ai/Qwen/Qwen3-Next-80B-A3B-Thinking": { + "input_cost_per_token": 1.5e-7, + "max_input_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 0.0000015, + "source": "https://www.together.ai/models/qwen3-next-80b-a3b-thinking", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "provider": "together_ai" + }, + "tts-1": { + "input_cost_per_character": 0.000015, + "mode": "audio_speech", + "supported_endpoints": ["/v1/audio/speech"], + "provider": "openai" + }, + "tts-1-hd": { + "input_cost_per_character": 0.00003, + "mode": "audio_speech", + "supported_endpoints": ["/v1/audio/speech"], + "provider": "openai" + }, + "us.amazon.nova-lite-v1:0": { + "input_cost_per_token": 6e-8, + "max_input_tokens": 300000, + "max_output_tokens": 10000, + "max_tokens": 10000, + "mode": "chat", + "output_cost_per_token": 2.4e-7, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_vision": true, + "provider": "bedrock_converse" + }, + "us.amazon.nova-micro-v1:0": { + "input_cost_per_token": 3.5e-8, + "max_input_tokens": 128000, + "max_output_tokens": 10000, + "max_tokens": 10000, + "mode": "chat", + "output_cost_per_token": 1.4e-7, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "provider": "bedrock_converse" + }, + "us.amazon.nova-premier-v1:0": { + "input_cost_per_token": 0.0000025, + "max_input_tokens": 1000000, + "max_output_tokens": 10000, + "max_tokens": 10000, + "mode": "chat", + "output_cost_per_token": 0.0000125, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": false, + "supports_response_schema": true, + "supports_vision": true, + "provider": "bedrock_converse" + }, + "us.amazon.nova-pro-v1:0": { + "input_cost_per_token": 8e-7, + "max_input_tokens": 300000, + "max_output_tokens": 10000, + "max_tokens": 10000, + "mode": "chat", + "output_cost_per_token": 0.0000032, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_vision": true, + "provider": "bedrock_converse" + }, + "us.anthropic.claude-3-5-haiku-20241022-v1:0": { + "cache_creation_input_token_cost": 0.000001, + "cache_read_input_token_cost": 8e-8, + "input_cost_per_token": 8e-7, + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.000004, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "provider": "bedrock" + }, + "us.anthropic.claude-haiku-4-5-20251001-v1:0": { + "cache_creation_input_token_cost": 0.000001375, + "cache_read_input_token_cost": 1.1e-7, + "input_cost_per_token": 0.0000011, + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 0.0000055, + "source": "https://aws.amazon.com/about-aws/whats-new/2025/10/claude-4-5-haiku-anthropic-amazon-bedrock", + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 346, + "provider": "bedrock_converse" + }, + "us.anthropic.claude-3-5-sonnet-20240620-v1:0": { + "input_cost_per_token": 0.000003, + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.000015, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "bedrock" + }, + "us.anthropic.claude-3-5-sonnet-20241022-v2:0": { + "cache_creation_input_token_cost": 0.00000375, + "cache_read_input_token_cost": 3e-7, + "input_cost_per_token": 0.000003, + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.000015, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "bedrock" + }, + "us.anthropic.claude-3-7-sonnet-20250219-v1:0": { + "cache_creation_input_token_cost": 0.00000375, + "cache_read_input_token_cost": 3e-7, + "input_cost_per_token": 0.000003, + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.000015, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "bedrock_converse" + }, + "us.anthropic.claude-3-haiku-20240307-v1:0": { + "input_cost_per_token": 2.5e-7, + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.00000125, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "bedrock" + }, + "us.anthropic.claude-3-opus-20240229-v1:0": { + "input_cost_per_token": 0.000015, + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.000075, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "bedrock" + }, + "us.anthropic.claude-3-sonnet-20240229-v1:0": { + "input_cost_per_token": 0.000003, + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.000015, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "bedrock" + }, + "us.anthropic.claude-opus-4-1-20250805-v1:0": { + "cache_creation_input_token_cost": 0.00001875, + "cache_read_input_token_cost": 0.0000015, + "input_cost_per_token": 0.000015, + "max_input_tokens": 200000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 0.000075, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159, + "provider": "bedrock_converse" + }, + "us.anthropic.claude-sonnet-4-5-20250929-v1:0": { + "cache_creation_input_token_cost": 0.000004125, + "cache_read_input_token_cost": 3.3e-7, + "input_cost_per_token": 0.0000033, + "input_cost_per_token_above_200k_tokens": 0.0000066, + "output_cost_per_token_above_200k_tokens": 0.00002475, + "cache_creation_input_token_cost_above_200k_tokens": 0.00000825, + "cache_read_input_token_cost_above_200k_tokens": 6.6e-7, + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 0.0000165, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 346, + "provider": "bedrock_converse" + }, + "au.anthropic.claude-haiku-4-5-20251001-v1:0": { + "cache_creation_input_token_cost": 0.000001375, + "cache_read_input_token_cost": 1.1e-7, + "input_cost_per_token": 0.0000011, + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 0.0000055, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 346, + "provider": "bedrock_converse" + }, + "us.anthropic.claude-opus-4-20250514-v1:0": { + "cache_creation_input_token_cost": 0.00001875, + "cache_read_input_token_cost": 0.0000015, + "input_cost_per_token": 0.000015, + "max_input_tokens": 200000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 0.000075, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159, + "provider": "bedrock_converse" + }, + "us.anthropic.claude-sonnet-4-20250514-v1:0": { + "cache_creation_input_token_cost": 0.00000375, + "cache_read_input_token_cost": 3e-7, + "input_cost_per_token": 0.000003, + "input_cost_per_token_above_200k_tokens": 0.000006, + "output_cost_per_token_above_200k_tokens": 0.0000225, + "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, + "cache_read_input_token_cost_above_200k_tokens": 6e-7, + "max_input_tokens": 1000000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 0.000015, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159, + "provider": "bedrock_converse" + }, + "us.deepseek.r1-v1:0": { + "input_cost_per_token": 0.00000135, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.0000054, + "supports_function_calling": false, + "supports_reasoning": true, + "supports_tool_choice": false, + "provider": "bedrock_converse" + }, + "us.meta.llama3-1-405b-instruct-v1:0": { + "input_cost_per_token": 0.00000532, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.000016, + "supports_function_calling": true, + "supports_tool_choice": false, + "provider": "bedrock" + }, + "us.meta.llama3-1-70b-instruct-v1:0": { + "input_cost_per_token": 9.9e-7, + "max_input_tokens": 128000, + "max_output_tokens": 2048, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 9.9e-7, + "supports_function_calling": true, + "supports_tool_choice": false, + "provider": "bedrock" + }, + "us.meta.llama3-1-8b-instruct-v1:0": { + "input_cost_per_token": 2.2e-7, + "max_input_tokens": 128000, + "max_output_tokens": 2048, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.2e-7, + "supports_function_calling": true, + "supports_tool_choice": false, + "provider": "bedrock" + }, + "us.meta.llama3-2-11b-instruct-v1:0": { + "input_cost_per_token": 3.5e-7, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3.5e-7, + "supports_function_calling": true, + "supports_tool_choice": false, + "supports_vision": true, + "provider": "bedrock" + }, + "us.meta.llama3-2-1b-instruct-v1:0": { + "input_cost_per_token": 1e-7, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-7, + "supports_function_calling": true, + "supports_tool_choice": false, + "provider": "bedrock" + }, + "us.meta.llama3-2-3b-instruct-v1:0": { + "input_cost_per_token": 1.5e-7, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.5e-7, + "supports_function_calling": true, + "supports_tool_choice": false, + "provider": "bedrock" + }, + "us.meta.llama3-2-90b-instruct-v1:0": { + "input_cost_per_token": 0.000002, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.000002, + "supports_function_calling": true, + "supports_tool_choice": false, + "supports_vision": true, + "provider": "bedrock" + }, + "us.meta.llama3-3-70b-instruct-v1:0": { + "input_cost_per_token": 7.2e-7, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 7.2e-7, + "supports_function_calling": true, + "supports_tool_choice": false, + "provider": "bedrock_converse" + }, + "us.meta.llama4-maverick-17b-instruct-v1:0": { + "input_cost_per_token": 2.4e-7, + "input_cost_per_token_batches": 1.2e-7, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 9.7e-7, + "output_cost_per_token_batches": 4.85e-7, + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text", "code"], + "supports_function_calling": true, + "supports_tool_choice": false, + "provider": "bedrock_converse" + }, + "us.meta.llama4-scout-17b-instruct-v1:0": { + "input_cost_per_token": 1.7e-7, + "input_cost_per_token_batches": 8.5e-8, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 6.6e-7, + "output_cost_per_token_batches": 3.3e-7, + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text", "code"], + "supports_function_calling": true, + "supports_tool_choice": false, + "provider": "bedrock_converse" + }, + "us.mistral.pixtral-large-2502-v1:0": { + "input_cost_per_token": 0.000002, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.000006, + "supports_function_calling": true, + "supports_tool_choice": false, + "provider": "bedrock_converse" + }, + "v0/v0-1.0-md": { + "input_cost_per_token": 0.000003, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.000015, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "v0" + }, + "v0/v0-1.5-lg": { + "input_cost_per_token": 0.000015, + "max_input_tokens": 512000, + "max_output_tokens": 512000, + "max_tokens": 512000, + "mode": "chat", + "output_cost_per_token": 0.000075, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "v0" + }, + "v0/v0-1.5-md": { + "input_cost_per_token": 0.000003, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.000015, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "v0" + }, + "vercel_ai_gateway/alibaba/qwen-3-14b": { + "input_cost_per_token": 8e-8, + "max_input_tokens": 40960, + "max_output_tokens": 16384, + "max_tokens": 40960, + "mode": "chat", + "output_cost_per_token": 2.4e-7, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/alibaba/qwen-3-235b": { + "input_cost_per_token": 2e-7, + "max_input_tokens": 40960, + "max_output_tokens": 16384, + "max_tokens": 40960, + "mode": "chat", + "output_cost_per_token": 6e-7, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/alibaba/qwen-3-30b": { + "input_cost_per_token": 1e-7, + "max_input_tokens": 40960, + "max_output_tokens": 16384, + "max_tokens": 40960, + "mode": "chat", + "output_cost_per_token": 3e-7, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/alibaba/qwen-3-32b": { + "input_cost_per_token": 1e-7, + "max_input_tokens": 40960, + "max_output_tokens": 16384, + "max_tokens": 40960, + "mode": "chat", + "output_cost_per_token": 3e-7, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/alibaba/qwen3-coder": { + "input_cost_per_token": 4e-7, + "max_input_tokens": 262144, + "max_output_tokens": 66536, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 0.0000016, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/amazon/nova-lite": { + "input_cost_per_token": 6e-8, + "max_input_tokens": 300000, + "max_output_tokens": 8192, + "max_tokens": 300000, + "mode": "chat", + "output_cost_per_token": 2.4e-7, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/amazon/nova-micro": { + "input_cost_per_token": 3.5e-8, + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.4e-7, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/amazon/nova-pro": { + "input_cost_per_token": 8e-7, + "max_input_tokens": 300000, + "max_output_tokens": 8192, + "max_tokens": 300000, + "mode": "chat", + "output_cost_per_token": 0.0000032, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/amazon/titan-embed-text-v2": { + "input_cost_per_token": 2e-8, + "max_input_tokens": 0, + "max_output_tokens": 0, + "max_tokens": 0, + "mode": "chat", + "output_cost_per_token": 0, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/anthropic/claude-3-haiku": { + "cache_creation_input_token_cost": 3e-7, + "cache_read_input_token_cost": 3e-8, + "input_cost_per_token": 2.5e-7, + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 200000, + "mode": "chat", + "output_cost_per_token": 0.00000125, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/anthropic/claude-3-opus": { + "cache_creation_input_token_cost": 0.00001875, + "cache_read_input_token_cost": 0.0000015, + "input_cost_per_token": 0.000015, + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 200000, + "mode": "chat", + "output_cost_per_token": 0.000075, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/anthropic/claude-3.5-haiku": { + "cache_creation_input_token_cost": 0.000001, + "cache_read_input_token_cost": 8e-8, + "input_cost_per_token": 8e-7, + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 200000, + "mode": "chat", + "output_cost_per_token": 0.000004, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/anthropic/claude-3.5-sonnet": { + "cache_creation_input_token_cost": 0.00000375, + "cache_read_input_token_cost": 3e-7, + "input_cost_per_token": 0.000003, + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 200000, + "mode": "chat", + "output_cost_per_token": 0.000015, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/anthropic/claude-3.7-sonnet": { + "cache_creation_input_token_cost": 0.00000375, + "cache_read_input_token_cost": 3e-7, + "input_cost_per_token": 0.000003, + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 200000, + "mode": "chat", + "output_cost_per_token": 0.000015, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/anthropic/claude-4-opus": { + "cache_creation_input_token_cost": 0.00001875, + "cache_read_input_token_cost": 0.0000015, + "input_cost_per_token": 0.000015, + "max_input_tokens": 200000, + "max_output_tokens": 32000, + "max_tokens": 200000, + "mode": "chat", + "output_cost_per_token": 0.000075, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/anthropic/claude-4-sonnet": { + "cache_creation_input_token_cost": 0.00000375, + "cache_read_input_token_cost": 3e-7, + "input_cost_per_token": 0.000003, + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 200000, + "mode": "chat", + "output_cost_per_token": 0.000015, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/cohere/command-a": { + "input_cost_per_token": 0.0000025, + "max_input_tokens": 256000, + "max_output_tokens": 8000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 0.00001, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/cohere/command-r": { + "input_cost_per_token": 1.5e-7, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-7, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/cohere/command-r-plus": { + "input_cost_per_token": 0.0000025, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.00001, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/cohere/embed-v4.0": { + "input_cost_per_token": 1.2e-7, + "max_input_tokens": 0, + "max_output_tokens": 0, + "max_tokens": 0, + "mode": "chat", + "output_cost_per_token": 0, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/deepseek/deepseek-r1": { + "input_cost_per_token": 5.5e-7, + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.00000219, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/deepseek/deepseek-r1-distill-llama-70b": { + "input_cost_per_token": 7.5e-7, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 9.9e-7, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/deepseek/deepseek-v3": { + "input_cost_per_token": 9e-7, + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 9e-7, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/google/gemini-2.0-flash": { + "input_cost_per_token": 1.5e-7, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 6e-7, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/google/gemini-2.0-flash-lite": { + "input_cost_per_token": 7.5e-8, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 3e-7, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/google/gemini-2.5-flash": { + "input_cost_per_token": 3e-7, + "max_input_tokens": 1000000, + "max_output_tokens": 65536, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 0.0000025, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/google/gemini-2.5-pro": { + "input_cost_per_token": 0.0000025, + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 0.00001, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/google/gemini-embedding-001": { + "input_cost_per_token": 1.5e-7, + "max_input_tokens": 0, + "max_output_tokens": 0, + "max_tokens": 0, + "mode": "embedding", + "output_cost_per_token": 0, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/google/gemma-2-9b": { + "input_cost_per_token": 2e-7, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2e-7, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/google/text-embedding-005": { + "input_cost_per_token": 2.5e-8, + "max_input_tokens": 0, + "max_output_tokens": 0, + "max_tokens": 0, + "mode": "embedding", + "output_cost_per_token": 0, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/google/text-multilingual-embedding-002": { + "input_cost_per_token": 2.5e-8, + "max_input_tokens": 0, + "max_output_tokens": 0, + "max_tokens": 0, + "mode": "embedding", + "output_cost_per_token": 0, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/inception/mercury-coder-small": { + "input_cost_per_token": 2.5e-7, + "max_input_tokens": 32000, + "max_output_tokens": 16384, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 0.000001, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/meta/llama-3-70b": { + "input_cost_per_token": 5.9e-7, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 7.9e-7, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/meta/llama-3-8b": { + "input_cost_per_token": 5e-8, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 8e-8, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/meta/llama-3.1-70b": { + "input_cost_per_token": 7.2e-7, + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 7.2e-7, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/meta/llama-3.1-8b": { + "input_cost_per_token": 5e-8, + "max_input_tokens": 131000, + "max_output_tokens": 131072, + "max_tokens": 131000, + "mode": "chat", + "output_cost_per_token": 8e-8, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/meta/llama-3.2-11b": { + "input_cost_per_token": 1.6e-7, + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.6e-7, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/meta/llama-3.2-1b": { + "input_cost_per_token": 1e-7, + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-7, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/meta/llama-3.2-3b": { + "input_cost_per_token": 1.5e-7, + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.5e-7, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/meta/llama-3.2-90b": { + "input_cost_per_token": 7.2e-7, + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 7.2e-7, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/meta/llama-3.3-70b": { + "input_cost_per_token": 7.2e-7, + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 7.2e-7, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/meta/llama-4-maverick": { + "input_cost_per_token": 2e-7, + "max_input_tokens": 131072, + "max_output_tokens": 8192, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 6e-7, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/meta/llama-4-scout": { + "input_cost_per_token": 1e-7, + "max_input_tokens": 131072, + "max_output_tokens": 8192, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 3e-7, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/mistral/codestral": { + "input_cost_per_token": 3e-7, + "max_input_tokens": 256000, + "max_output_tokens": 4000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 9e-7, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/mistral/codestral-embed": { + "input_cost_per_token": 1.5e-7, + "max_input_tokens": 0, + "max_output_tokens": 0, + "max_tokens": 0, + "mode": "chat", + "output_cost_per_token": 0, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/mistral/devstral-small": { + "input_cost_per_token": 7e-8, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.8e-7, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/mistral/magistral-medium": { + "input_cost_per_token": 0.000002, + "max_input_tokens": 128000, + "max_output_tokens": 64000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.000005, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/mistral/magistral-small": { + "input_cost_per_token": 5e-7, + "max_input_tokens": 128000, + "max_output_tokens": 64000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.0000015, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/mistral/ministral-3b": { + "input_cost_per_token": 4e-8, + "max_input_tokens": 128000, + "max_output_tokens": 4000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4e-8, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/mistral/ministral-8b": { + "input_cost_per_token": 1e-7, + "max_input_tokens": 128000, + "max_output_tokens": 4000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-7, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/mistral/mistral-embed": { + "input_cost_per_token": 1e-7, + "max_input_tokens": 0, + "max_output_tokens": 0, + "max_tokens": 0, + "mode": "chat", + "output_cost_per_token": 0, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/mistral/mistral-large": { + "input_cost_per_token": 0.000002, + "max_input_tokens": 32000, + "max_output_tokens": 4000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 0.000006, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/mistral/mistral-saba-24b": { + "input_cost_per_token": 7.9e-7, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 7.9e-7, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/mistral/mistral-small": { + "input_cost_per_token": 1e-7, + "max_input_tokens": 32000, + "max_output_tokens": 4000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 3e-7, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/mistral/mixtral-8x22b-instruct": { + "input_cost_per_token": 0.0000012, + "max_input_tokens": 65536, + "max_output_tokens": 2048, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 0.0000012, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/mistral/pixtral-12b": { + "input_cost_per_token": 1.5e-7, + "max_input_tokens": 128000, + "max_output_tokens": 4000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.5e-7, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/mistral/pixtral-large": { + "input_cost_per_token": 0.000002, + "max_input_tokens": 128000, + "max_output_tokens": 4000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.000006, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/moonshotai/kimi-k2": { + "input_cost_per_token": 5.5e-7, + "max_input_tokens": 131072, + "max_output_tokens": 16384, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 0.0000022, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/morph/morph-v3-fast": { + "input_cost_per_token": 8e-7, + "max_input_tokens": 32768, + "max_output_tokens": 16384, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0.0000012, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/morph/morph-v3-large": { + "input_cost_per_token": 9e-7, + "max_input_tokens": 32768, + "max_output_tokens": 16384, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0.0000019, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/openai/gpt-3.5-turbo": { + "input_cost_per_token": 5e-7, + "max_input_tokens": 16385, + "max_output_tokens": 4096, + "max_tokens": 16385, + "mode": "chat", + "output_cost_per_token": 0.0000015, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/openai/gpt-3.5-turbo-instruct": { + "input_cost_per_token": 0.0000015, + "max_input_tokens": 8192, + "max_output_tokens": 4096, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.000002, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/openai/gpt-4-turbo": { + "input_cost_per_token": 0.00001, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.00003, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/openai/gpt-4.1": { + "cache_creation_input_token_cost": 0, + "cache_read_input_token_cost": 5e-7, + "input_cost_per_token": 0.000002, + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 1047576, + "mode": "chat", + "output_cost_per_token": 0.000008, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/openai/gpt-4.1-mini": { + "cache_creation_input_token_cost": 0, + "cache_read_input_token_cost": 1e-7, + "input_cost_per_token": 4e-7, + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 1047576, + "mode": "chat", + "output_cost_per_token": 0.0000016, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/openai/gpt-4.1-nano": { + "cache_creation_input_token_cost": 0, + "cache_read_input_token_cost": 2.5e-8, + "input_cost_per_token": 1e-7, + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 1047576, + "mode": "chat", + "output_cost_per_token": 4e-7, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/openai/gpt-4o": { + "cache_creation_input_token_cost": 0, + "cache_read_input_token_cost": 0.00000125, + "input_cost_per_token": 0.0000025, + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.00001, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/openai/gpt-4o-mini": { + "cache_creation_input_token_cost": 0, + "cache_read_input_token_cost": 7.5e-8, + "input_cost_per_token": 1.5e-7, + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-7, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/openai/o1": { + "cache_creation_input_token_cost": 0, + "cache_read_input_token_cost": 0.0000075, + "input_cost_per_token": 0.000015, + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 200000, + "mode": "chat", + "output_cost_per_token": 0.00006, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/openai/o3": { + "cache_creation_input_token_cost": 0, + "cache_read_input_token_cost": 5e-7, + "input_cost_per_token": 0.000002, + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 200000, + "mode": "chat", + "output_cost_per_token": 0.000008, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/openai/o3-mini": { + "cache_creation_input_token_cost": 0, + "cache_read_input_token_cost": 5.5e-7, + "input_cost_per_token": 0.0000011, + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 200000, + "mode": "chat", + "output_cost_per_token": 0.0000044, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/openai/o4-mini": { + "cache_creation_input_token_cost": 0, + "cache_read_input_token_cost": 2.75e-7, + "input_cost_per_token": 0.0000011, + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 200000, + "mode": "chat", + "output_cost_per_token": 0.0000044, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/openai/text-embedding-3-large": { + "input_cost_per_token": 1.3e-7, + "max_input_tokens": 0, + "max_output_tokens": 0, + "max_tokens": 0, + "mode": "embedding", + "output_cost_per_token": 0, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/openai/text-embedding-3-small": { + "input_cost_per_token": 2e-8, + "max_input_tokens": 0, + "max_output_tokens": 0, + "max_tokens": 0, + "mode": "embedding", + "output_cost_per_token": 0, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/openai/text-embedding-ada-002": { + "input_cost_per_token": 1e-7, + "max_input_tokens": 0, + "max_output_tokens": 0, + "max_tokens": 0, + "mode": "embedding", + "output_cost_per_token": 0, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/perplexity/sonar": { + "input_cost_per_token": 0.000001, + "max_input_tokens": 127000, + "max_output_tokens": 8000, + "max_tokens": 127000, + "mode": "chat", + "output_cost_per_token": 0.000001, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/perplexity/sonar-pro": { + "input_cost_per_token": 0.000003, + "max_input_tokens": 200000, + "max_output_tokens": 8000, + "max_tokens": 200000, + "mode": "chat", + "output_cost_per_token": 0.000015, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/perplexity/sonar-reasoning": { + "input_cost_per_token": 0.000001, + "max_input_tokens": 127000, + "max_output_tokens": 8000, + "max_tokens": 127000, + "mode": "chat", + "output_cost_per_token": 0.000005, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/perplexity/sonar-reasoning-pro": { + "input_cost_per_token": 0.000002, + "max_input_tokens": 127000, + "max_output_tokens": 8000, + "max_tokens": 127000, + "mode": "chat", + "output_cost_per_token": 0.000008, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/vercel/v0-1.0-md": { + "input_cost_per_token": 0.000003, + "max_input_tokens": 128000, + "max_output_tokens": 32000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.000015, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/vercel/v0-1.5-md": { + "input_cost_per_token": 0.000003, + "max_input_tokens": 128000, + "max_output_tokens": 32768, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.000015, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/xai/grok-2": { + "input_cost_per_token": 0.000002, + "max_input_tokens": 131072, + "max_output_tokens": 4000, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 0.00001, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/xai/grok-2-vision": { + "input_cost_per_token": 0.000002, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0.00001, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/xai/grok-3": { + "input_cost_per_token": 0.000003, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 0.000015, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/xai/grok-3-fast": { + "input_cost_per_token": 0.000005, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 0.000025, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/xai/grok-3-mini": { + "input_cost_per_token": 3e-7, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 5e-7, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/xai/grok-3-mini-fast": { + "input_cost_per_token": 6e-7, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 0.000004, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/xai/grok-4": { + "input_cost_per_token": 0.000003, + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 0.000015, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/zai/glm-4.5": { + "input_cost_per_token": 6e-7, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 0.0000022, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/zai/glm-4.5-air": { + "input_cost_per_token": 2e-7, + "max_input_tokens": 128000, + "max_output_tokens": 96000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.0000011, + "provider": "vercel_ai_gateway" + }, + "vercel_ai_gateway/zai/glm-4.6": { + "cache_read_input_token_cost": 1.1e-7, + "input_cost_per_token": 4.5e-7, + "max_input_tokens": 200000, + "max_output_tokens": 200000, + "max_tokens": 200000, + "mode": "chat", + "output_cost_per_token": 0.0000018, + "source": "https://vercel.com/ai-gateway/models/glm-4.6", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "provider": "vercel_ai_gateway" + }, + "vertex_ai/claude-3-5-haiku": { + "input_cost_per_token": 0.000001, + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.000005, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_tool_choice": true, + "provider": "vertex_ai-anthropic_models" + }, + "vertex_ai/claude-3-5-haiku@20241022": { + "input_cost_per_token": 0.000001, + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.000005, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_tool_choice": true, + "provider": "vertex_ai-anthropic_models" + }, + "vertex_ai/claude-haiku-4-5@20251001": { + "cache_creation_input_token_cost": 0.00000125, + "cache_read_input_token_cost": 1e-7, + "input_cost_per_token": 0.000001, + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.000005, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/partner-models/claude/haiku-4-5", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "provider": "vertex_ai-anthropic_models" + }, + "vertex_ai/claude-3-5-sonnet": { + "input_cost_per_token": 0.000003, + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.000015, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "vertex_ai-anthropic_models" + }, + "vertex_ai/claude-3-5-sonnet-v2": { + "input_cost_per_token": 0.000003, + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.000015, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "vertex_ai-anthropic_models" + }, + "vertex_ai/claude-3-5-sonnet-v2@20241022": { + "input_cost_per_token": 0.000003, + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.000015, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "vertex_ai-anthropic_models" + }, + "vertex_ai/claude-3-5-sonnet@20240620": { + "input_cost_per_token": 0.000003, + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.000015, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "vertex_ai-anthropic_models" + }, + "vertex_ai/claude-3-7-sonnet@20250219": { + "cache_creation_input_token_cost": 0.00000375, + "cache_read_input_token_cost": 3e-7, + "deprecation_date": "2025-06-01", + "input_cost_per_token": 0.000003, + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.000015, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159, + "provider": "vertex_ai-anthropic_models" + }, + "vertex_ai/claude-3-haiku": { + "input_cost_per_token": 2.5e-7, + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.00000125, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "vertex_ai-anthropic_models" + }, + "vertex_ai/claude-3-haiku@20240307": { + "input_cost_per_token": 2.5e-7, + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.00000125, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "vertex_ai-anthropic_models" + }, + "vertex_ai/claude-3-opus": { + "input_cost_per_token": 0.000015, + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.000075, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "vertex_ai-anthropic_models" + }, + "vertex_ai/claude-3-opus@20240229": { + "input_cost_per_token": 0.000015, + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.000075, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "vertex_ai-anthropic_models" + }, + "vertex_ai/claude-3-sonnet": { + "input_cost_per_token": 0.000003, + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.000015, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "vertex_ai-anthropic_models" + }, + "vertex_ai/claude-3-sonnet@20240229": { + "input_cost_per_token": 0.000003, + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.000015, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "vertex_ai-anthropic_models" + }, + "vertex_ai/claude-opus-4": { + "cache_creation_input_token_cost": 0.00001875, + "cache_read_input_token_cost": 0.0000015, + "input_cost_per_token": 0.000015, + "max_input_tokens": 200000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 0.000075, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159, + "provider": "vertex_ai-anthropic_models" + }, + "vertex_ai/claude-opus-4-1": { + "cache_creation_input_token_cost": 0.00001875, + "cache_read_input_token_cost": 0.0000015, + "input_cost_per_token": 0.000015, + "input_cost_per_token_batches": 0.0000075, + "max_input_tokens": 200000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 0.000075, + "output_cost_per_token_batches": 0.0000375, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "vertex_ai-anthropic_models" + }, + "vertex_ai/claude-opus-4-1@20250805": { + "cache_creation_input_token_cost": 0.00001875, + "cache_read_input_token_cost": 0.0000015, + "input_cost_per_token": 0.000015, + "input_cost_per_token_batches": 0.0000075, + "max_input_tokens": 200000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 0.000075, + "output_cost_per_token_batches": 0.0000375, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "vertex_ai-anthropic_models" + }, + "vertex_ai/claude-sonnet-4-5": { + "cache_creation_input_token_cost": 0.00000375, + "cache_read_input_token_cost": 3e-7, + "input_cost_per_token": 0.000003, + "input_cost_per_token_above_200k_tokens": 0.000006, + "output_cost_per_token_above_200k_tokens": 0.0000225, + "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, + "cache_read_input_token_cost_above_200k_tokens": 6e-7, + "input_cost_per_token_batches": 0.0000015, + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 0.000015, + "output_cost_per_token_batches": 0.0000075, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "vertex_ai-anthropic_models" + }, + "vertex_ai/claude-sonnet-4-5@20250929": { + "cache_creation_input_token_cost": 0.00000375, + "cache_read_input_token_cost": 3e-7, + "input_cost_per_token": 0.000003, + "input_cost_per_token_above_200k_tokens": 0.000006, + "output_cost_per_token_above_200k_tokens": 0.0000225, + "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, + "cache_read_input_token_cost_above_200k_tokens": 6e-7, + "input_cost_per_token_batches": 0.0000015, + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 0.000015, + "output_cost_per_token_batches": 0.0000075, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "vertex_ai-anthropic_models" + }, + "vertex_ai/claude-opus-4@20250514": { + "cache_creation_input_token_cost": 0.00001875, + "cache_read_input_token_cost": 0.0000015, + "input_cost_per_token": 0.000015, + "max_input_tokens": 200000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 0.000075, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159, + "provider": "vertex_ai-anthropic_models" + }, + "vertex_ai/claude-sonnet-4": { + "cache_creation_input_token_cost": 0.00000375, + "cache_read_input_token_cost": 3e-7, + "input_cost_per_token": 0.000003, + "input_cost_per_token_above_200k_tokens": 0.000006, + "output_cost_per_token_above_200k_tokens": 0.0000225, + "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, + "cache_read_input_token_cost_above_200k_tokens": 6e-7, + "max_input_tokens": 1000000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 0.000015, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159, + "provider": "vertex_ai-anthropic_models" + }, + "vertex_ai/claude-sonnet-4@20250514": { + "cache_creation_input_token_cost": 0.00000375, + "cache_read_input_token_cost": 3e-7, + "input_cost_per_token": 0.000003, + "input_cost_per_token_above_200k_tokens": 0.000006, + "output_cost_per_token_above_200k_tokens": 0.0000225, + "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, + "cache_read_input_token_cost_above_200k_tokens": 6e-7, + "max_input_tokens": 1000000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 0.000015, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159, + "provider": "vertex_ai-anthropic_models" + }, + "vertex_ai/mistralai/codestral-2@001": { + "input_cost_per_token": 3e-7, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 9e-7, + "supports_function_calling": true, + "supports_tool_choice": true, + "provider": "vertex_ai-mistral_models" + }, + "vertex_ai/codestral-2": { + "input_cost_per_token": 3e-7, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 9e-7, + "supports_function_calling": true, + "supports_tool_choice": true, + "provider": "vertex_ai-mistral_models" + }, + "vertex_ai/codestral-2@001": { + "input_cost_per_token": 3e-7, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 9e-7, + "supports_function_calling": true, + "supports_tool_choice": true, + "provider": "vertex_ai-mistral_models" + }, + "vertex_ai/mistralai/codestral-2": { + "input_cost_per_token": 3e-7, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 9e-7, + "supports_function_calling": true, + "supports_tool_choice": true, + "provider": "vertex_ai-mistral_models" + }, + "vertex_ai/codestral-2501": { + "input_cost_per_token": 2e-7, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-7, + "supports_function_calling": true, + "supports_tool_choice": true, + "provider": "vertex_ai-mistral_models" + }, + "vertex_ai/codestral@2405": { + "input_cost_per_token": 2e-7, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-7, + "supports_function_calling": true, + "supports_tool_choice": true, + "provider": "vertex_ai-mistral_models" + }, + "vertex_ai/codestral@latest": { + "input_cost_per_token": 2e-7, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-7, + "supports_function_calling": true, + "supports_tool_choice": true, + "provider": "vertex_ai-mistral_models" + }, + "vertex_ai/deepseek-ai/deepseek-v3.1-maas": { + "input_cost_per_token": 0.00000135, + "max_input_tokens": 163840, + "max_output_tokens": 32768, + "max_tokens": 163840, + "mode": "chat", + "output_cost_per_token": 0.0000054, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", + "supported_regions": ["us-west2"], + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "provider": "vertex_ai-deepseek_models" + }, + "vertex_ai/deepseek-ai/deepseek-r1-0528-maas": { + "input_cost_per_token": 0.00000135, + "max_input_tokens": 65336, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.0000054, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "provider": "vertex_ai-deepseek_models" + }, + "vertex_ai/gemini-2.5-flash-image": { + "cache_read_input_token_cost": 3e-8, + "input_cost_per_audio_token": 0.000001, + "input_cost_per_token": 3e-7, + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "max_pdf_size_mb": 30, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "image_generation", + "output_cost_per_image": 0.039, + "output_cost_per_reasoning_token": 0.0000025, + "output_cost_per_token": 0.0000025, + "rpm": 100000, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/image-generation#edit-an-image", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": ["text", "image", "audio", "video"], + "supported_output_modalities": ["text", "image"], + "supports_audio_output": false, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": false, + "tpm": 8000000, + "provider": "vertex_ai-language-models" + }, + "vertex_ai/gemini-3-pro-image-preview": { + "input_cost_per_image": 0.0011, + "input_cost_per_token": 0.000002, + "input_cost_per_token_batches": 0.000001, + "max_input_tokens": 65536, + "max_output_tokens": 32768, + "max_tokens": 65536, + "mode": "image_generation", + "output_cost_per_image": 0.134, + "output_cost_per_token": 0.000012, + "output_cost_per_token_batches": 0.000006, + "source": "https://docs.cloud.google.com/vertex-ai/generative-ai/docs/models/gemini/3-pro-image", + "provider": "vertex_ai-language-models" + }, + "vertex_ai/imagegeneration@006": { + "mode": "image_generation", + "output_cost_per_image": 0.02, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "provider": "vertex_ai-image-models" + }, + "vertex_ai/imagen-3.0-fast-generate-001": { + "mode": "image_generation", + "output_cost_per_image": 0.02, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "provider": "vertex_ai-image-models" + }, + "vertex_ai/imagen-3.0-generate-001": { + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "provider": "vertex_ai-image-models" + }, + "vertex_ai/imagen-3.0-generate-002": { + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "provider": "vertex_ai-image-models" + }, + "vertex_ai/imagen-3.0-capability-001": { + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/image/edit-insert-objects", + "provider": "vertex_ai-image-models" + }, + "vertex_ai/imagen-4.0-fast-generate-001": { + "mode": "image_generation", + "output_cost_per_image": 0.02, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "provider": "vertex_ai-image-models" + }, + "vertex_ai/imagen-4.0-generate-001": { + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "provider": "vertex_ai-image-models" + }, + "vertex_ai/imagen-4.0-ultra-generate-001": { + "mode": "image_generation", + "output_cost_per_image": 0.06, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "provider": "vertex_ai-image-models" + }, + "vertex_ai/jamba-1.5": { + "input_cost_per_token": 2e-7, + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 4e-7, + "supports_tool_choice": true, + "provider": "vertex_ai-ai21_models" + }, + "vertex_ai/jamba-1.5-large": { + "input_cost_per_token": 0.000002, + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 0.000008, + "supports_tool_choice": true, + "provider": "vertex_ai-ai21_models" + }, + "vertex_ai/jamba-1.5-large@001": { + "input_cost_per_token": 0.000002, + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 0.000008, + "supports_tool_choice": true, + "provider": "vertex_ai-ai21_models" + }, + "vertex_ai/jamba-1.5-mini": { + "input_cost_per_token": 2e-7, + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 4e-7, + "supports_tool_choice": true, + "provider": "vertex_ai-ai21_models" + }, + "vertex_ai/jamba-1.5-mini@001": { + "input_cost_per_token": 2e-7, + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 4e-7, + "supports_tool_choice": true, + "provider": "vertex_ai-ai21_models" + }, + "vertex_ai/meta/llama-3.1-405b-instruct-maas": { + "input_cost_per_token": 0.000005, + "max_input_tokens": 128000, + "max_output_tokens": 2048, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.000016, + "source": "https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-3.2-90b-vision-instruct-maas", + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "vertex_ai-llama_models" + }, + "vertex_ai/meta/llama-3.1-70b-instruct-maas": { + "input_cost_per_token": 0, + "max_input_tokens": 128000, + "max_output_tokens": 2048, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0, + "source": "https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-3.2-90b-vision-instruct-maas", + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "vertex_ai-llama_models" + }, + "vertex_ai/meta/llama-3.1-8b-instruct-maas": { + "input_cost_per_token": 0, + "max_input_tokens": 128000, + "max_output_tokens": 2048, + "max_tokens": 128000, + "metadata": { + "notes": "VertexAI states that The Llama 3.1 API service for llama-3.1-70b-instruct-maas and llama-3.1-8b-instruct-maas are in public preview and at no cost." + }, + "mode": "chat", + "output_cost_per_token": 0, + "source": "https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-3.2-90b-vision-instruct-maas", + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "vertex_ai-llama_models" + }, + "vertex_ai/meta/llama-3.2-90b-vision-instruct-maas": { + "input_cost_per_token": 0, + "max_input_tokens": 128000, + "max_output_tokens": 2048, + "max_tokens": 128000, + "metadata": { + "notes": "VertexAI states that The Llama 3.2 API service is at no cost during public preview, and will be priced as per dollar-per-1M-tokens at GA." + }, + "mode": "chat", + "output_cost_per_token": 0, + "source": "https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-3.2-90b-vision-instruct-maas", + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "vertex_ai-llama_models" + }, + "vertex_ai/meta/llama-4-maverick-17b-128e-instruct-maas": { + "input_cost_per_token": 3.5e-7, + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 0.00000115, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text", "code"], + "supports_function_calling": true, + "supports_tool_choice": true, + "provider": "vertex_ai-llama_models" + }, + "vertex_ai/meta/llama-4-maverick-17b-16e-instruct-maas": { + "input_cost_per_token": 3.5e-7, + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 0.00000115, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text", "code"], + "supports_function_calling": true, + "supports_tool_choice": true, + "provider": "vertex_ai-llama_models" + }, + "vertex_ai/meta/llama-4-scout-17b-128e-instruct-maas": { + "input_cost_per_token": 2.5e-7, + "max_input_tokens": 10000000, + "max_output_tokens": 10000000, + "max_tokens": 10000000, + "mode": "chat", + "output_cost_per_token": 7e-7, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text", "code"], + "supports_function_calling": true, + "supports_tool_choice": true, + "provider": "vertex_ai-llama_models" + }, + "vertex_ai/meta/llama-4-scout-17b-16e-instruct-maas": { + "input_cost_per_token": 2.5e-7, + "max_input_tokens": 10000000, + "max_output_tokens": 10000000, + "max_tokens": 10000000, + "mode": "chat", + "output_cost_per_token": 7e-7, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["text", "code"], + "supports_function_calling": true, + "supports_tool_choice": true, + "provider": "vertex_ai-llama_models" + }, + "vertex_ai/meta/llama3-405b-instruct-maas": { + "input_cost_per_token": 0, + "max_input_tokens": 32000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 0, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", + "supports_tool_choice": true, + "provider": "vertex_ai-llama_models" + }, + "vertex_ai/meta/llama3-70b-instruct-maas": { + "input_cost_per_token": 0, + "max_input_tokens": 32000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 0, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", + "supports_tool_choice": true, + "provider": "vertex_ai-llama_models" + }, + "vertex_ai/meta/llama3-8b-instruct-maas": { + "input_cost_per_token": 0, + "max_input_tokens": 32000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 0, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", + "supports_tool_choice": true, + "provider": "vertex_ai-llama_models" + }, + "vertex_ai/minimaxai/minimax-m2-maas": { + "input_cost_per_token": 3e-7, + "max_input_tokens": 196608, + "max_output_tokens": 196608, + "max_tokens": 196608, + "mode": "chat", + "output_cost_per_token": 0.0000012, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", + "supports_function_calling": true, + "supports_tool_choice": true, + "provider": "vertex_ai-minimax_models" + }, + "vertex_ai/moonshotai/kimi-k2-thinking-maas": { + "input_cost_per_token": 6e-7, + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 0.0000025, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_web_search": true, + "provider": "vertex_ai-moonshot_models" + }, + "vertex_ai/mistral-medium-3": { + "input_cost_per_token": 4e-7, + "max_input_tokens": 128000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 0.000002, + "supports_function_calling": true, + "supports_tool_choice": true, + "provider": "vertex_ai-mistral_models" + }, + "vertex_ai/mistral-medium-3@001": { + "input_cost_per_token": 4e-7, + "max_input_tokens": 128000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 0.000002, + "supports_function_calling": true, + "supports_tool_choice": true, + "provider": "vertex_ai-mistral_models" + }, + "vertex_ai/mistralai/mistral-medium-3": { + "input_cost_per_token": 4e-7, + "max_input_tokens": 128000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 0.000002, + "supports_function_calling": true, + "supports_tool_choice": true, + "provider": "vertex_ai-mistral_models" + }, + "vertex_ai/mistralai/mistral-medium-3@001": { + "input_cost_per_token": 4e-7, + "max_input_tokens": 128000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 0.000002, + "supports_function_calling": true, + "supports_tool_choice": true, + "provider": "vertex_ai-mistral_models" + }, + "vertex_ai/mistral-large-2411": { + "input_cost_per_token": 0.000002, + "max_input_tokens": 128000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 0.000006, + "supports_function_calling": true, + "supports_tool_choice": true, + "provider": "vertex_ai-mistral_models" + }, + "vertex_ai/mistral-large@2407": { + "input_cost_per_token": 0.000002, + "max_input_tokens": 128000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 0.000006, + "supports_function_calling": true, + "supports_tool_choice": true, + "provider": "vertex_ai-mistral_models" + }, + "vertex_ai/mistral-large@2411-001": { + "input_cost_per_token": 0.000002, + "max_input_tokens": 128000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 0.000006, + "supports_function_calling": true, + "supports_tool_choice": true, + "provider": "vertex_ai-mistral_models" + }, + "vertex_ai/mistral-large@latest": { + "input_cost_per_token": 0.000002, + "max_input_tokens": 128000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 0.000006, + "supports_function_calling": true, + "supports_tool_choice": true, + "provider": "vertex_ai-mistral_models" + }, + "vertex_ai/mistral-nemo@2407": { + "input_cost_per_token": 0.000003, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.000003, + "supports_function_calling": true, + "supports_tool_choice": true, + "provider": "vertex_ai-mistral_models" + }, + "vertex_ai/mistral-nemo@latest": { + "input_cost_per_token": 1.5e-7, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.5e-7, + "supports_function_calling": true, + "supports_tool_choice": true, + "provider": "vertex_ai-mistral_models" + }, + "vertex_ai/mistral-small-2503": { + "input_cost_per_token": 0.000001, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.000003, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true, + "provider": "vertex_ai-mistral_models" + }, + "vertex_ai/mistral-small-2503@001": { + "input_cost_per_token": 0.000001, + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 0.000003, + "supports_function_calling": true, + "supports_tool_choice": true, + "provider": "vertex_ai-mistral_models" + }, + "vertex_ai/mistral-ocr-2505": { + "mode": "ocr", + "ocr_cost_per_page": 0.0005, + "supported_endpoints": ["/v1/ocr"], + "source": "https://cloud.google.com/generative-ai-app-builder/pricing", + "provider": "vertex_ai" + }, + "vertex_ai/openai/gpt-oss-120b-maas": { + "input_cost_per_token": 1.5e-7, + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 6e-7, + "source": "https://console.cloud.google.com/vertex-ai/publishers/openai/model-garden/gpt-oss-120b-maas", + "supports_reasoning": true, + "provider": "vertex_ai-openai_models" + }, + "vertex_ai/openai/gpt-oss-20b-maas": { + "input_cost_per_token": 7.5e-8, + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 3e-7, + "source": "https://console.cloud.google.com/vertex-ai/publishers/openai/model-garden/gpt-oss-120b-maas", + "supports_reasoning": true, + "provider": "vertex_ai-openai_models" + }, + "vertex_ai/qwen/qwen3-235b-a22b-instruct-2507-maas": { + "input_cost_per_token": 2.5e-7, + "max_input_tokens": 262144, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 0.000001, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "supports_function_calling": true, + "supports_tool_choice": true, + "provider": "vertex_ai-qwen_models" + }, + "vertex_ai/qwen/qwen3-coder-480b-a35b-instruct-maas": { + "input_cost_per_token": 0.000001, + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0.000004, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "supports_function_calling": true, + "supports_tool_choice": true, + "provider": "vertex_ai-qwen_models" + }, + "vertex_ai/qwen/qwen3-next-80b-a3b-instruct-maas": { + "input_cost_per_token": 1.5e-7, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 0.0000012, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "supports_function_calling": true, + "supports_tool_choice": true, + "provider": "vertex_ai-qwen_models" + }, + "vertex_ai/qwen/qwen3-next-80b-a3b-thinking-maas": { + "input_cost_per_token": 1.5e-7, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 0.0000012, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "supports_function_calling": true, + "supports_tool_choice": true, + "provider": "vertex_ai-qwen_models" + }, + "vertex_ai/veo-2.0-generate-001": { + "max_input_tokens": 1024, + "max_tokens": 1024, + "mode": "video_generation", + "output_cost_per_second": 0.35, + "source": "https://ai.google.dev/gemini-api/docs/video", + "supported_modalities": ["text"], + "supported_output_modalities": ["video"], + "provider": "vertex_ai-video-models" + }, + "vertex_ai/veo-3.0-fast-generate-preview": { + "max_input_tokens": 1024, + "max_tokens": 1024, + "mode": "video_generation", + "output_cost_per_second": 0.15, + "source": "https://ai.google.dev/gemini-api/docs/video", + "supported_modalities": ["text"], + "supported_output_modalities": ["video"], + "provider": "vertex_ai-video-models" + }, + "vertex_ai/veo-3.0-generate-preview": { + "max_input_tokens": 1024, + "max_tokens": 1024, + "mode": "video_generation", + "output_cost_per_second": 0.4, + "source": "https://ai.google.dev/gemini-api/docs/video", + "supported_modalities": ["text"], + "supported_output_modalities": ["video"], + "provider": "vertex_ai-video-models" + }, + "vertex_ai/veo-3.0-fast-generate-001": { + "max_input_tokens": 1024, + "max_tokens": 1024, + "mode": "video_generation", + "output_cost_per_second": 0.15, + "source": "https://ai.google.dev/gemini-api/docs/video", + "supported_modalities": ["text"], + "supported_output_modalities": ["video"], + "provider": "vertex_ai-video-models" + }, + "vertex_ai/veo-3.0-generate-001": { + "max_input_tokens": 1024, + "max_tokens": 1024, + "mode": "video_generation", + "output_cost_per_second": 0.4, + "source": "https://ai.google.dev/gemini-api/docs/video", + "supported_modalities": ["text"], + "supported_output_modalities": ["video"], + "provider": "vertex_ai-video-models" + }, + "vertex_ai/veo-3.1-generate-preview": { + "max_input_tokens": 1024, + "max_tokens": 1024, + "mode": "video_generation", + "output_cost_per_second": 0.4, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/veo", + "supported_modalities": ["text"], + "supported_output_modalities": ["video"], + "provider": "vertex_ai-video-models" + }, + "vertex_ai/veo-3.1-fast-generate-preview": { + "max_input_tokens": 1024, + "max_tokens": 1024, + "mode": "video_generation", + "output_cost_per_second": 0.15, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/veo", + "supported_modalities": ["text"], + "supported_output_modalities": ["video"], + "provider": "vertex_ai-video-models" + }, + "voyage/rerank-2": { + "input_cost_per_query": 5e-8, + "input_cost_per_token": 5e-8, + "max_input_tokens": 16000, + "max_output_tokens": 16000, + "max_query_tokens": 16000, + "max_tokens": 16000, + "mode": "rerank", + "output_cost_per_token": 0, + "provider": "voyage" + }, + "voyage/rerank-2-lite": { + "input_cost_per_query": 2e-8, + "input_cost_per_token": 2e-8, + "max_input_tokens": 8000, + "max_output_tokens": 8000, + "max_query_tokens": 8000, + "max_tokens": 8000, + "mode": "rerank", + "output_cost_per_token": 0, + "provider": "voyage" + }, + "voyage/voyage-2": { + "input_cost_per_token": 1e-7, + "max_input_tokens": 4000, + "max_tokens": 4000, + "mode": "embedding", + "output_cost_per_token": 0, + "provider": "voyage" + }, + "voyage/voyage-3": { + "input_cost_per_token": 6e-8, + "max_input_tokens": 32000, + "max_tokens": 32000, + "mode": "embedding", + "output_cost_per_token": 0, + "provider": "voyage" + }, + "voyage/voyage-3-large": { + "input_cost_per_token": 1.8e-7, + "max_input_tokens": 32000, + "max_tokens": 32000, + "mode": "embedding", + "output_cost_per_token": 0, + "provider": "voyage" + }, + "voyage/voyage-3-lite": { + "input_cost_per_token": 2e-8, + "max_input_tokens": 32000, + "max_tokens": 32000, + "mode": "embedding", + "output_cost_per_token": 0, + "provider": "voyage" + }, + "voyage/voyage-3.5": { + "input_cost_per_token": 6e-8, + "max_input_tokens": 32000, + "max_tokens": 32000, + "mode": "embedding", + "output_cost_per_token": 0, + "provider": "voyage" + }, + "voyage/voyage-3.5-lite": { + "input_cost_per_token": 2e-8, + "max_input_tokens": 32000, + "max_tokens": 32000, + "mode": "embedding", + "output_cost_per_token": 0, + "provider": "voyage" + }, + "voyage/voyage-code-2": { + "input_cost_per_token": 1.2e-7, + "max_input_tokens": 16000, + "max_tokens": 16000, + "mode": "embedding", + "output_cost_per_token": 0, + "provider": "voyage" + }, + "voyage/voyage-code-3": { + "input_cost_per_token": 1.8e-7, + "max_input_tokens": 32000, + "max_tokens": 32000, + "mode": "embedding", + "output_cost_per_token": 0, + "provider": "voyage" + }, + "voyage/voyage-context-3": { + "input_cost_per_token": 1.8e-7, + "max_input_tokens": 120000, + "max_tokens": 120000, + "mode": "embedding", + "output_cost_per_token": 0, + "provider": "voyage" + }, + "voyage/voyage-finance-2": { + "input_cost_per_token": 1.2e-7, + "max_input_tokens": 32000, + "max_tokens": 32000, + "mode": "embedding", + "output_cost_per_token": 0, + "provider": "voyage" + }, + "voyage/voyage-large-2": { + "input_cost_per_token": 1.2e-7, + "max_input_tokens": 16000, + "max_tokens": 16000, + "mode": "embedding", + "output_cost_per_token": 0, + "provider": "voyage" + }, + "voyage/voyage-law-2": { + "input_cost_per_token": 1.2e-7, + "max_input_tokens": 16000, + "max_tokens": 16000, + "mode": "embedding", + "output_cost_per_token": 0, + "provider": "voyage" + }, + "voyage/voyage-lite-01": { + "input_cost_per_token": 1e-7, + "max_input_tokens": 4096, + "max_tokens": 4096, + "mode": "embedding", + "output_cost_per_token": 0, + "provider": "voyage" + }, + "voyage/voyage-lite-02-instruct": { + "input_cost_per_token": 1e-7, + "max_input_tokens": 4000, + "max_tokens": 4000, + "mode": "embedding", + "output_cost_per_token": 0, + "provider": "voyage" + }, + "voyage/voyage-multimodal-3": { + "input_cost_per_token": 1.2e-7, + "max_input_tokens": 32000, + "max_tokens": 32000, + "mode": "embedding", + "output_cost_per_token": 0, + "provider": "voyage" + }, + "wandb/openai/gpt-oss-120b": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 0.015, + "output_cost_per_token": 0.06, + "mode": "chat", + "provider": "wandb" + }, + "wandb/openai/gpt-oss-20b": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 0.005, + "output_cost_per_token": 0.02, + "mode": "chat", + "provider": "wandb" + }, + "wandb/zai-org/GLM-4.5": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 0.055, + "output_cost_per_token": 0.2, + "mode": "chat", + "provider": "wandb" + }, + "wandb/Qwen/Qwen3-235B-A22B-Instruct-2507": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "input_cost_per_token": 0.01, + "output_cost_per_token": 0.01, + "mode": "chat", + "provider": "wandb" + }, + "wandb/Qwen/Qwen3-Coder-480B-A35B-Instruct": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "input_cost_per_token": 0.1, + "output_cost_per_token": 0.15, + "mode": "chat", + "provider": "wandb" + }, + "wandb/Qwen/Qwen3-235B-A22B-Thinking-2507": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "input_cost_per_token": 0.01, + "output_cost_per_token": 0.01, + "mode": "chat", + "provider": "wandb" + }, + "wandb/moonshotai/Kimi-K2-Instruct": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 0.135, + "output_cost_per_token": 0.4, + "mode": "chat", + "provider": "wandb" + }, + "wandb/meta-llama/Llama-3.1-8B-Instruct": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 0.022, + "output_cost_per_token": 0.022, + "mode": "chat", + "provider": "wandb" + }, + "wandb/deepseek-ai/DeepSeek-V3.1": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 0.055, + "output_cost_per_token": 0.165, + "mode": "chat", + "provider": "wandb" + }, + "wandb/deepseek-ai/DeepSeek-R1-0528": { + "max_tokens": 161000, + "max_input_tokens": 161000, + "max_output_tokens": 161000, + "input_cost_per_token": 0.135, + "output_cost_per_token": 0.54, + "mode": "chat", + "provider": "wandb" + }, + "wandb/deepseek-ai/DeepSeek-V3-0324": { + "max_tokens": 161000, + "max_input_tokens": 161000, + "max_output_tokens": 161000, + "input_cost_per_token": 0.114, + "output_cost_per_token": 0.275, + "mode": "chat", + "provider": "wandb" + }, + "wandb/meta-llama/Llama-3.3-70B-Instruct": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 0.071, + "output_cost_per_token": 0.071, + "mode": "chat", + "provider": "wandb" + }, + "wandb/meta-llama/Llama-4-Scout-17B-16E-Instruct": { + "max_tokens": 64000, + "max_input_tokens": 64000, + "max_output_tokens": 64000, + "input_cost_per_token": 0.017, + "output_cost_per_token": 0.066, + "mode": "chat", + "provider": "wandb" + }, + "wandb/microsoft/Phi-4-mini-instruct": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 0.008, + "output_cost_per_token": 0.035, + "mode": "chat", + "provider": "wandb" + }, + "watsonx/ibm/granite-3-8b-instruct": { + "input_cost_per_token": 2e-7, + "max_input_tokens": 8192, + "max_output_tokens": 1024, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2e-7, + "supports_audio_input": false, + "supports_audio_output": false, + "supports_function_calling": true, + "supports_parallel_function_calling": false, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false, + "provider": "watsonx" + }, + "watsonx/mistralai/mistral-large": { + "input_cost_per_token": 0.000003, + "max_input_tokens": 131072, + "max_output_tokens": 16384, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 0.00001, + "supports_audio_input": false, + "supports_audio_output": false, + "supports_function_calling": true, + "supports_parallel_function_calling": false, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false, + "provider": "watsonx" + }, + "watsonx/bigscience/mt0-xxl-13b": { + "max_tokens": 8192, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "input_cost_per_token": 0.0005, + "output_cost_per_token": 0.002, + "mode": "chat", + "supports_function_calling": false, + "supports_parallel_function_calling": false, + "supports_vision": false, + "provider": "watsonx" + }, + "watsonx/core42/jais-13b-chat": { + "max_tokens": 8192, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "input_cost_per_token": 0.0005, + "output_cost_per_token": 0.002, + "mode": "chat", + "supports_function_calling": false, + "supports_parallel_function_calling": false, + "supports_vision": false, + "provider": "watsonx" + }, + "watsonx/google/flan-t5-xl-3b": { + "max_tokens": 8192, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "input_cost_per_token": 6e-7, + "output_cost_per_token": 6e-7, + "mode": "chat", + "supports_function_calling": false, + "supports_parallel_function_calling": false, + "supports_vision": false, + "provider": "watsonx" + }, + "watsonx/ibm/granite-13b-chat-v2": { + "max_tokens": 8192, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "input_cost_per_token": 6e-7, + "output_cost_per_token": 6e-7, + "mode": "chat", + "supports_function_calling": false, + "supports_parallel_function_calling": false, + "supports_vision": false, + "provider": "watsonx" + }, + "watsonx/ibm/granite-13b-instruct-v2": { + "max_tokens": 8192, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "input_cost_per_token": 6e-7, + "output_cost_per_token": 6e-7, + "mode": "chat", + "supports_function_calling": false, + "supports_parallel_function_calling": false, + "supports_vision": false, + "provider": "watsonx" + }, + "watsonx/ibm/granite-3-3-8b-instruct": { + "max_tokens": 8192, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "input_cost_per_token": 2e-7, + "output_cost_per_token": 2e-7, + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_vision": false, + "provider": "watsonx" + }, + "watsonx/ibm/granite-4-h-small": { + "max_tokens": 20480, + "max_input_tokens": 20480, + "max_output_tokens": 20480, + "input_cost_per_token": 6e-8, + "output_cost_per_token": 2.5e-7, + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_vision": false, + "provider": "watsonx" + }, + "watsonx/ibm/granite-guardian-3-2-2b": { + "max_tokens": 8192, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "input_cost_per_token": 1e-7, + "output_cost_per_token": 1e-7, + "mode": "chat", + "supports_function_calling": false, + "supports_parallel_function_calling": false, + "supports_vision": false, + "provider": "watsonx" + }, + "watsonx/ibm/granite-guardian-3-3-8b": { + "max_tokens": 8192, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "input_cost_per_token": 2e-7, + "output_cost_per_token": 2e-7, + "mode": "chat", + "supports_function_calling": false, + "supports_parallel_function_calling": false, + "supports_vision": false, + "provider": "watsonx" + }, + "watsonx/ibm/granite-ttm-1024-96-r2": { + "max_tokens": 512, + "max_input_tokens": 512, + "max_output_tokens": 512, + "input_cost_per_token": 3.8e-7, + "output_cost_per_token": 3.8e-7, + "mode": "chat", + "supports_function_calling": false, + "supports_parallel_function_calling": false, + "supports_vision": false, + "provider": "watsonx" + }, + "watsonx/ibm/granite-ttm-1536-96-r2": { + "max_tokens": 512, + "max_input_tokens": 512, + "max_output_tokens": 512, + "input_cost_per_token": 3.8e-7, + "output_cost_per_token": 3.8e-7, + "mode": "chat", + "supports_function_calling": false, + "supports_parallel_function_calling": false, + "supports_vision": false, + "provider": "watsonx" + }, + "watsonx/ibm/granite-ttm-512-96-r2": { + "max_tokens": 512, + "max_input_tokens": 512, + "max_output_tokens": 512, + "input_cost_per_token": 3.8e-7, + "output_cost_per_token": 3.8e-7, + "mode": "chat", + "supports_function_calling": false, + "supports_parallel_function_calling": false, + "supports_vision": false, + "provider": "watsonx" + }, + "watsonx/ibm/granite-vision-3-2-2b": { + "max_tokens": 8192, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "input_cost_per_token": 1e-7, + "output_cost_per_token": 1e-7, + "mode": "chat", + "supports_function_calling": false, + "supports_parallel_function_calling": false, + "supports_vision": true, + "provider": "watsonx" + }, + "watsonx/meta-llama/llama-3-2-11b-vision-instruct": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 3.5e-7, + "output_cost_per_token": 3.5e-7, + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_vision": true, + "provider": "watsonx" + }, + "watsonx/meta-llama/llama-3-2-1b-instruct": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 1e-7, + "output_cost_per_token": 1e-7, + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_vision": false, + "provider": "watsonx" + }, + "watsonx/meta-llama/llama-3-2-3b-instruct": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 1.5e-7, + "output_cost_per_token": 1.5e-7, + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_vision": false, + "provider": "watsonx" + }, + "watsonx/meta-llama/llama-3-2-90b-vision-instruct": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 0.000002, + "output_cost_per_token": 0.000002, + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_vision": true, + "provider": "watsonx" + }, + "watsonx/meta-llama/llama-3-3-70b-instruct": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 7.1e-7, + "output_cost_per_token": 7.1e-7, + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_vision": false, + "provider": "watsonx" + }, + "watsonx/meta-llama/llama-4-maverick-17b": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 3.5e-7, + "output_cost_per_token": 0.0000014, + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_vision": false, + "provider": "watsonx" + }, + "watsonx/meta-llama/llama-guard-3-11b-vision": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 3.5e-7, + "output_cost_per_token": 3.5e-7, + "mode": "chat", + "supports_function_calling": false, + "supports_parallel_function_calling": false, + "supports_vision": true, + "provider": "watsonx" + }, + "watsonx/mistralai/mistral-medium-2505": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 0.000003, + "output_cost_per_token": 0.00001, + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_vision": false, + "provider": "watsonx" + }, + "watsonx/mistralai/mistral-small-2503": { + "max_tokens": 32000, + "max_input_tokens": 32000, + "max_output_tokens": 32000, + "input_cost_per_token": 1e-7, + "output_cost_per_token": 3e-7, + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_vision": false, + "provider": "watsonx" + }, + "watsonx/mistralai/mistral-small-3-1-24b-instruct-2503": { + "max_tokens": 32000, + "max_input_tokens": 32000, + "max_output_tokens": 32000, + "input_cost_per_token": 1e-7, + "output_cost_per_token": 3e-7, + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_vision": false, + "provider": "watsonx" + }, + "watsonx/mistralai/pixtral-12b-2409": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 3.5e-7, + "output_cost_per_token": 3.5e-7, + "mode": "chat", + "supports_function_calling": false, + "supports_parallel_function_calling": false, + "supports_vision": true, + "provider": "watsonx" + }, + "watsonx/openai/gpt-oss-120b": { + "max_tokens": 8192, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "input_cost_per_token": 1.5e-7, + "output_cost_per_token": 6e-7, + "mode": "chat", + "supports_function_calling": false, + "supports_parallel_function_calling": false, + "supports_vision": false, + "provider": "watsonx" + }, + "watsonx/sdaia/allam-1-13b-instruct": { + "max_tokens": 8192, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "input_cost_per_token": 0.0000018, + "output_cost_per_token": 0.0000018, + "mode": "chat", + "supports_function_calling": false, + "supports_parallel_function_calling": false, + "supports_vision": false, + "provider": "watsonx" + }, + "whisper-1": { + "input_cost_per_second": 0.0001, + "mode": "audio_transcription", + "output_cost_per_second": 0.0001, + "supported_endpoints": ["/v1/audio/transcriptions"], + "provider": "openai" + }, + "xai/grok-2": { + "input_cost_per_token": 0.000002, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 0.00001, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_web_search": true, + "provider": "xai" + }, + "xai/grok-2-1212": { + "input_cost_per_token": 0.000002, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 0.00001, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_web_search": true, + "provider": "xai" + }, + "xai/grok-2-latest": { + "input_cost_per_token": 0.000002, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 0.00001, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_web_search": true, + "provider": "xai" + }, + "xai/grok-2-vision": { + "input_cost_per_image": 0.000002, + "input_cost_per_token": 0.000002, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0.00001, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "provider": "xai" + }, + "xai/grok-2-vision-1212": { + "input_cost_per_image": 0.000002, + "input_cost_per_token": 0.000002, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0.00001, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "provider": "xai" + }, + "xai/grok-2-vision-latest": { + "input_cost_per_image": 0.000002, + "input_cost_per_token": 0.000002, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0.00001, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "provider": "xai" + }, + "xai/grok-3": { + "input_cost_per_token": 0.000003, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 0.000015, + "source": "https://x.ai/api#pricing", + "supports_function_calling": true, + "supports_response_schema": false, + "supports_tool_choice": true, + "supports_web_search": true, + "provider": "xai" + }, + "xai/grok-3-beta": { + "input_cost_per_token": 0.000003, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 0.000015, + "source": "https://x.ai/api#pricing", + "supports_function_calling": true, + "supports_response_schema": false, + "supports_tool_choice": true, + "supports_web_search": true, + "provider": "xai" + }, + "xai/grok-3-fast-beta": { + "input_cost_per_token": 0.000005, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 0.000025, + "source": "https://x.ai/api#pricing", + "supports_function_calling": true, + "supports_response_schema": false, + "supports_tool_choice": true, + "supports_web_search": true, + "provider": "xai" + }, + "xai/grok-3-fast-latest": { + "input_cost_per_token": 0.000005, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 0.000025, + "source": "https://x.ai/api#pricing", + "supports_function_calling": true, + "supports_response_schema": false, + "supports_tool_choice": true, + "supports_web_search": true, + "provider": "xai" + }, + "xai/grok-3-latest": { + "input_cost_per_token": 0.000003, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 0.000015, + "source": "https://x.ai/api#pricing", + "supports_function_calling": true, + "supports_response_schema": false, + "supports_tool_choice": true, + "supports_web_search": true, + "provider": "xai" + }, + "xai/grok-3-mini": { + "input_cost_per_token": 3e-7, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 5e-7, + "source": "https://x.ai/api#pricing", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_tool_choice": true, + "supports_web_search": true, + "provider": "xai" + }, + "xai/grok-3-mini-beta": { + "input_cost_per_token": 3e-7, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 5e-7, + "source": "https://x.ai/api#pricing", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_tool_choice": true, + "supports_web_search": true, + "provider": "xai" + }, + "xai/grok-3-mini-fast": { + "input_cost_per_token": 6e-7, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 0.000004, + "source": "https://x.ai/api#pricing", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_tool_choice": true, + "supports_web_search": true, + "provider": "xai" + }, + "xai/grok-3-mini-fast-beta": { + "input_cost_per_token": 6e-7, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 0.000004, + "source": "https://x.ai/api#pricing", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_tool_choice": true, + "supports_web_search": true, + "provider": "xai" + }, + "xai/grok-3-mini-fast-latest": { + "input_cost_per_token": 6e-7, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 0.000004, + "source": "https://x.ai/api#pricing", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_tool_choice": true, + "supports_web_search": true, + "provider": "xai" + }, + "xai/grok-3-mini-latest": { + "input_cost_per_token": 3e-7, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 5e-7, + "source": "https://x.ai/api#pricing", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_tool_choice": true, + "supports_web_search": true, + "provider": "xai" + }, + "xai/grok-4": { + "input_cost_per_token": 0.000003, + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 0.000015, + "source": "https://docs.x.ai/docs/models", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_web_search": true, + "provider": "xai" + }, + "xai/grok-4-fast-reasoning": { + "max_input_tokens": 2000000, + "max_output_tokens": 2000000, + "max_tokens": 2000000, + "mode": "chat", + "input_cost_per_token": 2e-7, + "input_cost_per_token_above_128k_tokens": 4e-7, + "output_cost_per_token": 5e-7, + "output_cost_per_token_above_128k_tokens": 0.000001, + "cache_read_input_token_cost": 5e-8, + "source": "https://docs.x.ai/docs/models", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_web_search": true, + "provider": "xai" + }, + "xai/grok-4-fast-non-reasoning": { + "max_input_tokens": 2000000, + "max_output_tokens": 2000000, + "cache_read_input_token_cost": 5e-8, + "max_tokens": 2000000, + "mode": "chat", + "input_cost_per_token": 2e-7, + "input_cost_per_token_above_128k_tokens": 4e-7, + "output_cost_per_token": 5e-7, + "output_cost_per_token_above_128k_tokens": 0.000001, + "source": "https://docs.x.ai/docs/models", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_web_search": true, + "provider": "xai" + }, + "xai/grok-4-0709": { + "input_cost_per_token": 0.000003, + "input_cost_per_token_above_128k_tokens": 0.000006, + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 0.000015, + "output_cost_per_token_above_128k_tokens": 0.00003, + "source": "https://docs.x.ai/docs/models", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_web_search": true, + "provider": "xai" + }, + "xai/grok-4-latest": { + "input_cost_per_token": 0.000003, + "input_cost_per_token_above_128k_tokens": 0.000006, + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 0.000015, + "output_cost_per_token_above_128k_tokens": 0.00003, + "source": "https://docs.x.ai/docs/models", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_web_search": true, + "provider": "xai" + }, + "xai/grok-4-1-fast": { + "cache_read_input_token_cost": 5e-8, + "input_cost_per_token": 2e-7, + "input_cost_per_token_above_128k_tokens": 4e-7, + "max_input_tokens": 2000000, + "max_output_tokens": 2000000, + "max_tokens": 2000000, + "mode": "chat", + "output_cost_per_token": 5e-7, + "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_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "provider": "xai" + }, + "xai/grok-4-1-fast-reasoning": { + "cache_read_input_token_cost": 5e-8, + "input_cost_per_token": 2e-7, + "input_cost_per_token_above_128k_tokens": 4e-7, + "max_input_tokens": 2000000, + "max_output_tokens": 2000000, + "max_tokens": 2000000, + "mode": "chat", + "output_cost_per_token": 5e-7, + "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_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "provider": "xai" + }, + "xai/grok-4-1-fast-reasoning-latest": { + "cache_read_input_token_cost": 5e-8, + "input_cost_per_token": 2e-7, + "input_cost_per_token_above_128k_tokens": 4e-7, + "max_input_tokens": 2000000, + "max_output_tokens": 2000000, + "max_tokens": 2000000, + "mode": "chat", + "output_cost_per_token": 5e-7, + "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_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "provider": "xai" + }, + "xai/grok-4-1-fast-non-reasoning": { + "cache_read_input_token_cost": 5e-8, + "input_cost_per_token": 2e-7, + "input_cost_per_token_above_128k_tokens": 4e-7, + "max_input_tokens": 2000000, + "max_output_tokens": 2000000, + "max_tokens": 2000000, + "mode": "chat", + "output_cost_per_token": 5e-7, + "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_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "provider": "xai" + }, + "xai/grok-4-1-fast-non-reasoning-latest": { + "cache_read_input_token_cost": 5e-8, + "input_cost_per_token": 2e-7, + "input_cost_per_token_above_128k_tokens": 4e-7, + "max_input_tokens": 2000000, + "max_output_tokens": 2000000, + "max_tokens": 2000000, + "mode": "chat", + "output_cost_per_token": 5e-7, + "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_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "provider": "xai" + }, + "xai/grok-beta": { + "input_cost_per_token": 0.000005, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 0.000015, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "provider": "xai" + }, + "xai/grok-code-fast": { + "cache_read_input_token_cost": 2e-8, + "input_cost_per_token": 2e-7, + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 0.0000015, + "source": "https://docs.x.ai/docs/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "provider": "xai" + }, + "xai/grok-code-fast-1": { + "cache_read_input_token_cost": 2e-8, + "input_cost_per_token": 2e-7, + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 0.0000015, + "source": "https://docs.x.ai/docs/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "provider": "xai" + }, + "xai/grok-code-fast-1-0825": { + "cache_read_input_token_cost": 2e-8, + "input_cost_per_token": 2e-7, + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 0.0000015, + "source": "https://docs.x.ai/docs/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "provider": "xai" + }, + "xai/grok-vision-beta": { + "input_cost_per_image": 0.000005, + "input_cost_per_token": 0.000005, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.000015, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "provider": "xai" + }, + "vertex_ai/search_api": { + "input_cost_per_query": 0.0015, + "mode": "vector_store", + "provider": "vertex_ai" + }, + "openai/container": { + "code_interpreter_cost_per_session": 0.03, + "mode": "chat", + "provider": "openai" + }, + "openai/sora-2": { + "mode": "video_generation", + "output_cost_per_video_per_second": 0.1, + "source": "https://platform.openai.com/docs/api-reference/videos", + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["video"], + "supported_resolutions": ["720x1280", "1280x720"], + "provider": "openai" + }, + "openai/sora-2-pro": { + "mode": "video_generation", + "output_cost_per_video_per_second": 0.3, + "source": "https://platform.openai.com/docs/api-reference/videos", + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["video"], + "supported_resolutions": ["720x1280", "1280x720"], + "provider": "openai" + }, + "azure/sora-2": { + "mode": "video_generation", + "output_cost_per_video_per_second": 0.1, + "source": "https://azure.microsoft.com/en-us/products/ai-services/video-generation", + "supported_modalities": ["text"], + "supported_output_modalities": ["video"], + "supported_resolutions": ["720x1280", "1280x720"], + "provider": "azure" + }, + "azure/sora-2-pro": { + "mode": "video_generation", + "output_cost_per_video_per_second": 0.3, + "source": "https://azure.microsoft.com/en-us/products/ai-services/video-generation", + "supported_modalities": ["text"], + "supported_output_modalities": ["video"], + "supported_resolutions": ["720x1280", "1280x720"], + "provider": "azure" + }, + "azure/sora-2-pro-high-res": { + "mode": "video_generation", + "output_cost_per_video_per_second": 0.5, + "source": "https://azure.microsoft.com/en-us/products/ai-services/video-generation", + "supported_modalities": ["text"], + "supported_output_modalities": ["video"], + "supported_resolutions": ["1024x1792", "1792x1024"], + "provider": "azure" + }, + "runwayml/gen4_turbo": { + "mode": "video_generation", + "output_cost_per_video_per_second": 0.05, + "source": "https://docs.dev.runwayml.com/guides/pricing/", + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["video"], + "supported_resolutions": ["1280x720", "720x1280"], + "metadata": { + "comment": "5 credits per second @ $0.01 per credit = $0.05 per second" + }, + "provider": "runwayml" + }, + "runwayml/gen4_aleph": { + "mode": "video_generation", + "output_cost_per_video_per_second": 0.15, + "source": "https://docs.dev.runwayml.com/guides/pricing/", + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["video"], + "supported_resolutions": ["1280x720", "720x1280"], + "metadata": { + "comment": "15 credits per second @ $0.01 per credit = $0.15 per second" + }, + "provider": "runwayml" + }, + "runwayml/gen3a_turbo": { + "mode": "video_generation", + "output_cost_per_video_per_second": 0.05, + "source": "https://docs.dev.runwayml.com/guides/pricing/", + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["video"], + "supported_resolutions": ["1280x720", "720x1280"], + "metadata": { + "comment": "5 credits per second @ $0.01 per credit = $0.05 per second" + }, + "provider": "runwayml" + }, + "runwayml/gen4_image": { + "mode": "image_generation", + "input_cost_per_image": 0.05, + "output_cost_per_image": 0.05, + "source": "https://docs.dev.runwayml.com/guides/pricing/", + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["image"], + "supported_resolutions": ["1280x720", "1920x1080"], + "metadata": { + "comment": "5 credits per 720p image or 8 credits per 1080p image @ $0.01 per credit. Using 5 credits ($0.05) as base cost" + }, + "provider": "runwayml" + }, + "runwayml/gen4_image_turbo": { + "mode": "image_generation", + "input_cost_per_image": 0.02, + "output_cost_per_image": 0.02, + "source": "https://docs.dev.runwayml.com/guides/pricing/", + "supported_modalities": ["text", "image"], + "supported_output_modalities": ["image"], + "supported_resolutions": ["1280x720", "1920x1080"], + "metadata": { + "comment": "2 credits per image (any resolution) @ $0.01 per credit = $0.02 per image" + }, + "provider": "runwayml" + }, + "runwayml/eleven_multilingual_v2": { + "mode": "audio_speech", + "input_cost_per_character": 3e-7, + "source": "https://docs.dev.runwayml.com/guides/pricing/", + "metadata": { + "comment": "Estimated cost based on standard TTS pricing. RunwayML uses ElevenLabs models." + }, + "provider": "runwayml" + }, + "cerebras/zai-glm-4.6": { + "provider": "cerebras", + "mode": "chat", + "input_cost_per_token": 0.00000225, + "output_cost_per_token": 0.00000275, + "max_input_tokens": 200000, + "max_output_tokens": 128000, + "max_tokens": 128000 + } +}