commit 16fbadd51a2115153a780248e94897eef8d9b94c Author: shaw Date: Thu Oct 16 10:22:37 2025 +0800 chore: 初始化模型价格镜像 diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json new file mode 100644 index 00000000..3987fe7e --- /dev/null +++ b/model_prices_and_context_window.json @@ -0,0 +1,22423 @@ +{ + "1024-x-1024/50-steps/bedrock/amazon.nova-canvas-v1:0": { + "litellm_provider": "bedrock", + "max_input_tokens": 2600, + "mode": "image_generation", + "output_cost_per_image": 0.06 + }, + "1024-x-1024/50-steps/stability.stable-diffusion-xl-v1": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "max_tokens": 77, + "mode": "image_generation", + "output_cost_per_image": 0.04 + }, + "1024-x-1024/dall-e-2": { + "input_cost_per_pixel": 1.9e-08, + "litellm_provider": "openai", + "mode": "image_generation", + "output_cost_per_pixel": 0.0 + }, + "1024-x-1024/max-steps/stability.stable-diffusion-xl-v1": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "max_tokens": 77, + "mode": "image_generation", + "output_cost_per_image": 0.08 + }, + "256-x-256/dall-e-2": { + "input_cost_per_pixel": 2.4414e-07, + "litellm_provider": "openai", + "mode": "image_generation", + "output_cost_per_pixel": 0.0 + }, + "512-x-512/50-steps/stability.stable-diffusion-xl-v0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "max_tokens": 77, + "mode": "image_generation", + "output_cost_per_image": 0.018 + }, + "512-x-512/dall-e-2": { + "input_cost_per_pixel": 6.86e-08, + "litellm_provider": "openai", + "mode": "image_generation", + "output_cost_per_pixel": 0.0 + }, + "512-x-512/max-steps/stability.stable-diffusion-xl-v0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "max_tokens": 77, + "mode": "image_generation", + "output_cost_per_image": 0.036 + }, + "ai21.j2-mid-v1": { + "input_cost_per_token": 1.25e-05, + "litellm_provider": "bedrock", + "max_input_tokens": 8191, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 1.25e-05 + }, + "ai21.j2-ultra-v1": { + "input_cost_per_token": 1.88e-05, + "litellm_provider": "bedrock", + "max_input_tokens": 8191, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 1.88e-05 + }, + "ai21.jamba-1-5-large-v1:0": { + "input_cost_per_token": 2e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 8e-06 + }, + "ai21.jamba-1-5-mini-v1:0": { + "input_cost_per_token": 2e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 4e-07 + }, + "ai21.jamba-instruct-v1:0": { + "input_cost_per_token": 5e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 70000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 7e-07, + "supports_system_messages": true + }, + "aiml/dall-e-2": { + "litellm_provider": "aiml", + "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" + ] + }, + "aiml/dall-e-3": { + "litellm_provider": "aiml", + "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" + ] + }, + "aiml/flux-pro": { + "litellm_provider": "aiml", + "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" + ] + }, + "aiml/flux-pro/v1.1": { + "litellm_provider": "aiml", + "mode": "image_generation", + "output_cost_per_image": 0.042, + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "aiml/flux-pro/v1.1-ultra": { + "litellm_provider": "aiml", + "mode": "image_generation", + "output_cost_per_image": 0.063, + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "aiml/flux-realism": { + "litellm_provider": "aiml", + "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" + ] + }, + "aiml/flux/dev": { + "litellm_provider": "aiml", + "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" + ] + }, + "aiml/flux/kontext-max/text-to-image": { + "litellm_provider": "aiml", + "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" + ] + }, + "aiml/flux/kontext-pro/text-to-image": { + "litellm_provider": "aiml", + "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" + ] + }, + "aiml/flux/schnell": { + "litellm_provider": "aiml", + "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" + ] + }, + "amazon.nova-lite-v1:0": { + "input_cost_per_token": 6e-08, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 300000, + "max_output_tokens": 10000, + "max_tokens": 10000, + "mode": "chat", + "output_cost_per_token": 2.4e-07, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_vision": true + }, + "amazon.nova-micro-v1:0": { + "input_cost_per_token": 3.5e-08, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 128000, + "max_output_tokens": 10000, + "max_tokens": 10000, + "mode": "chat", + "output_cost_per_token": 1.4e-07, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true + }, + "amazon.nova-pro-v1:0": { + "input_cost_per_token": 8e-07, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 300000, + "max_output_tokens": 10000, + "max_tokens": 10000, + "mode": "chat", + "output_cost_per_token": 3.2e-06, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_vision": true + }, + "amazon.rerank-v1:0": { + "input_cost_per_query": 0.001, + "input_cost_per_token": 0.0, + "litellm_provider": "bedrock", + "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": 0.0 + }, + "amazon.titan-embed-image-v1": { + "input_cost_per_image": 6e-05, + "input_cost_per_token": 8e-07, + "litellm_provider": "bedrock", + "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": 0.0, + "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 + }, + "amazon.titan-embed-text-v1": { + "input_cost_per_token": 1e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 8192, + "max_tokens": 8192, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 1536 + }, + "amazon.titan-embed-text-v2:0": { + "input_cost_per_token": 2e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 8192, + "max_tokens": 8192, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 1024 + }, + "twelvelabs.marengo-embed-2-7-v1:0": { + "input_cost_per_token": 7e-05, + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "max_tokens": 77, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 1024, + "supports_embedding_image_input": true, + "supports_image_input": true + }, + "us.twelvelabs.marengo-embed-2-7-v1:0": { + "input_cost_per_token": 7e-05, + "input_cost_per_video_per_second": 0.0007, + "input_cost_per_audio_per_second": 0.00014, + "input_cost_per_image": 0.0001, + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "max_tokens": 77, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 1024, + "supports_embedding_image_input": true, + "supports_image_input": true + }, + "eu.twelvelabs.marengo-embed-2-7-v1:0": { + "input_cost_per_token": 7e-05, + "input_cost_per_video_per_second": 0.0007, + "input_cost_per_audio_per_second": 0.00014, + "input_cost_per_image": 0.0001, + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "max_tokens": 77, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 1024, + "supports_embedding_image_input": true, + "supports_image_input": true + }, + "twelvelabs.pegasus-1-2-v1:0": { + "input_cost_per_video_per_second": 0.00049, + "output_cost_per_token": 7.5e-06, + "litellm_provider": "bedrock", + "mode": "chat", + "supports_video_input": true + }, + "us.twelvelabs.pegasus-1-2-v1:0": { + "input_cost_per_video_per_second": 0.00049, + "output_cost_per_token": 7.5e-06, + "litellm_provider": "bedrock", + "mode": "chat", + "supports_video_input": true + }, + "eu.twelvelabs.pegasus-1-2-v1:0": { + "input_cost_per_video_per_second": 0.00049, + "output_cost_per_token": 7.5e-06, + "litellm_provider": "bedrock", + "mode": "chat", + "supports_video_input": true + }, + "amazon.titan-text-express-v1": { + "input_cost_per_token": 1.3e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 42000, + "max_output_tokens": 8000, + "max_tokens": 8000, + "mode": "chat", + "output_cost_per_token": 1.7e-06 + }, + "amazon.titan-text-lite-v1": { + "input_cost_per_token": 3e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 42000, + "max_output_tokens": 4000, + "max_tokens": 4000, + "mode": "chat", + "output_cost_per_token": 4e-07 + }, + "amazon.titan-text-premier-v1:0": { + "input_cost_per_token": 5e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 42000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 1.5e-06 + }, + "anthropic.claude-3-5-haiku-20241022-v1:0": { + "cache_creation_input_token_cost": 1e-06, + "cache_read_input_token_cost": 8e-08, + "input_cost_per_token": 8e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 4e-06, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "anthropic.claude-3-5-sonnet-20240620-v1:0": { + "input_cost_per_token": 3e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "anthropic.claude-3-5-sonnet-20241022-v2:0": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "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 + }, + "anthropic.claude-3-7-sonnet-20250219-v1:0": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "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 + }, + "anthropic.claude-3-haiku-20240307-v1:0": { + "input_cost_per_token": 2.5e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.25e-06, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "anthropic.claude-3-opus-20240229-v1:0": { + "input_cost_per_token": 1.5e-05, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "anthropic.claude-3-sonnet-20240229-v1:0": { + "input_cost_per_token": 3e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "anthropic.claude-instant-v1": { + "input_cost_per_token": 8e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 2.4e-06, + "supports_tool_choice": true + }, + "anthropic.claude-opus-4-1-20250805-v1:0": { + "cache_creation_input_token_cost": 1.875e-05, + "cache_read_input_token_cost": 1.5e-06, + "input_cost_per_token": 1.5e-05, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 200000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "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 + }, + "anthropic.claude-opus-4-20250514-v1:0": { + "cache_creation_input_token_cost": 1.875e-05, + "cache_read_input_token_cost": 1.5e-06, + "input_cost_per_token": 1.5e-05, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 200000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "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 + }, + "anthropic.claude-sonnet-4-20250514-v1:0": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "input_cost_per_token_above_200k_tokens": 6e-06, + "output_cost_per_token_above_200k_tokens": 2.25e-05, + "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, + "cache_read_input_token_cost_above_200k_tokens": 6e-07, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "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 + }, + "anthropic.claude-v1": { + "input_cost_per_token": 8e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 2.4e-05 + }, + "anthropic.claude-v2:1": { + "input_cost_per_token": 8e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 2.4e-05, + "supports_tool_choice": true + }, + "anyscale/HuggingFaceH4/zephyr-7b-beta": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "anyscale", + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.5e-07 + }, + "anyscale/codellama/CodeLlama-34b-Instruct-hf": { + "input_cost_per_token": 1e-06, + "litellm_provider": "anyscale", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1e-06 + }, + "anyscale/codellama/CodeLlama-70b-Instruct-hf": { + "input_cost_per_token": 1e-06, + "litellm_provider": "anyscale", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1e-06, + "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/codellama-CodeLlama-70b-Instruct-hf" + }, + "anyscale/google/gemma-7b-it": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "anyscale", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.5e-07, + "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/google-gemma-7b-it" + }, + "anyscale/meta-llama/Llama-2-13b-chat-hf": { + "input_cost_per_token": 2.5e-07, + "litellm_provider": "anyscale", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2.5e-07 + }, + "anyscale/meta-llama/Llama-2-70b-chat-hf": { + "input_cost_per_token": 1e-06, + "litellm_provider": "anyscale", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1e-06 + }, + "anyscale/meta-llama/Llama-2-7b-chat-hf": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "anyscale", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.5e-07 + }, + "anyscale/meta-llama/Meta-Llama-3-70B-Instruct": { + "input_cost_per_token": 1e-06, + "litellm_provider": "anyscale", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1e-06, + "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/meta-llama-Meta-Llama-3-70B-Instruct" + }, + "anyscale/meta-llama/Meta-Llama-3-8B-Instruct": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "anyscale", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.5e-07, + "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/meta-llama-Meta-Llama-3-8B-Instruct" + }, + "anyscale/mistralai/Mistral-7B-Instruct-v0.1": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "anyscale", + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.5e-07, + "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/mistralai-Mistral-7B-Instruct-v0.1", + "supports_function_calling": true + }, + "anyscale/mistralai/Mixtral-8x22B-Instruct-v0.1": { + "input_cost_per_token": 9e-07, + "litellm_provider": "anyscale", + "max_input_tokens": 65536, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 9e-07, + "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/mistralai-Mixtral-8x22B-Instruct-v0.1", + "supports_function_calling": true + }, + "anyscale/mistralai/Mixtral-8x7B-Instruct-v0.1": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "anyscale", + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.5e-07, + "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/mistralai-Mixtral-8x7B-Instruct-v0.1", + "supports_function_calling": true + }, + "apac.amazon.nova-lite-v1:0": { + "input_cost_per_token": 6.3e-08, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 300000, + "max_output_tokens": 10000, + "max_tokens": 10000, + "mode": "chat", + "output_cost_per_token": 2.52e-07, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_vision": true + }, + "apac.amazon.nova-micro-v1:0": { + "input_cost_per_token": 3.7e-08, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 128000, + "max_output_tokens": 10000, + "max_tokens": 10000, + "mode": "chat", + "output_cost_per_token": 1.48e-07, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true + }, + "apac.amazon.nova-pro-v1:0": { + "input_cost_per_token": 8.4e-07, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 300000, + "max_output_tokens": 10000, + "max_tokens": 10000, + "mode": "chat", + "output_cost_per_token": 3.36e-06, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_vision": true + }, + "apac.anthropic.claude-3-5-sonnet-20240620-v1:0": { + "input_cost_per_token": 3e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "apac.anthropic.claude-3-5-sonnet-20241022-v2:0": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "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 + }, + "apac.anthropic.claude-3-haiku-20240307-v1:0": { + "input_cost_per_token": 2.5e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.25e-06, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "apac.anthropic.claude-3-sonnet-20240229-v1:0": { + "input_cost_per_token": 3e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "apac.anthropic.claude-sonnet-4-20250514-v1:0": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "input_cost_per_token_above_200k_tokens": 6e-06, + "output_cost_per_token_above_200k_tokens": 2.25e-05, + "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, + "cache_read_input_token_cost_above_200k_tokens": 6e-07, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "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 + }, + "assemblyai/best": { + "input_cost_per_second": 3.333e-05, + "litellm_provider": "assemblyai", + "mode": "audio_transcription", + "output_cost_per_second": 0.0 + }, + "assemblyai/nano": { + "input_cost_per_second": 0.00010278, + "litellm_provider": "assemblyai", + "mode": "audio_transcription", + "output_cost_per_second": 0.0 + }, + "azure/ada": { + "input_cost_per_token": 1e-07, + "litellm_provider": "azure", + "max_input_tokens": 8191, + "max_tokens": 8191, + "mode": "embedding", + "output_cost_per_token": 0.0 + }, + "azure/codex-mini": { + "cache_read_input_token_cost": 3.75e-07, + "input_cost_per_token": 1.5e-06, + "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "responses", + "output_cost_per_token": 6e-06, + "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 + }, + "azure/command-r-plus": { + "input_cost_per_token": 3e-06, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_function_calling": true + }, + "azure/computer-use-preview": { + "input_cost_per_token": 3e-06, + "litellm_provider": "azure", + "max_input_tokens": 8192, + "max_output_tokens": 1024, + "max_tokens": 1024, + "mode": "chat", + "output_cost_per_token": 1.2e-05, + "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 + }, + "azure/eu/gpt-4o-2024-08-06": { + "cache_read_input_token_cost": 1.375e-06, + "input_cost_per_token": 2.75e-06, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.1e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure/eu/gpt-4o-2024-11-20": { + "cache_creation_input_token_cost": 1.38e-06, + "input_cost_per_token": 2.75e-06, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.1e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure/eu/gpt-4o-mini-2024-07-18": { + "cache_read_input_token_cost": 8.3e-08, + "input_cost_per_token": 1.65e-07, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 6.6e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure/eu/gpt-4o-mini-realtime-preview-2024-12-17": { + "cache_creation_input_audio_token_cost": 3.3e-07, + "cache_read_input_token_cost": 3.3e-07, + "input_cost_per_audio_token": 1.1e-05, + "input_cost_per_token": 6.6e-07, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_audio_token": 2.2e-05, + "output_cost_per_token": 2.64e-06, + "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 + }, + "azure/eu/gpt-4o-realtime-preview-2024-10-01": { + "cache_creation_input_audio_token_cost": 2.2e-05, + "cache_read_input_token_cost": 2.75e-06, + "input_cost_per_audio_token": 0.00011, + "input_cost_per_token": 5.5e-06, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_audio_token": 0.00022, + "output_cost_per_token": 2.2e-05, + "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 + }, + "azure/eu/gpt-4o-realtime-preview-2024-12-17": { + "cache_read_input_audio_token_cost": 2.5e-06, + "cache_read_input_token_cost": 2.75e-06, + "input_cost_per_audio_token": 4.4e-05, + "input_cost_per_token": 5.5e-06, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_audio_token": 8e-05, + "output_cost_per_token": 2.2e-05, + "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 + }, + "azure/eu/o1-2024-12-17": { + "cache_read_input_token_cost": 8.25e-06, + "input_cost_per_token": 1.65e-05, + "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 6.6e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure/eu/o1-mini-2024-09-12": { + "cache_read_input_token_cost": 6.05e-07, + "input_cost_per_token": 1.21e-06, + "input_cost_per_token_batches": 6.05e-07, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 4.84e-06, + "output_cost_per_token_batches": 2.42e-06, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_vision": false + }, + "azure/eu/o1-preview-2024-09-12": { + "cache_read_input_token_cost": 8.25e-06, + "input_cost_per_token": 1.65e-05, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 6.6e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_vision": false + }, + "azure/eu/o3-mini-2025-01-31": { + "cache_read_input_token_cost": 6.05e-07, + "input_cost_per_token": 1.21e-06, + "input_cost_per_token_batches": 6.05e-07, + "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 4.84e-06, + "output_cost_per_token_batches": 2.42e-06, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "azure/global-standard/gpt-4o-2024-08-06": { + "cache_read_input_token_cost": 1.25e-06, + "deprecation_date": "2025-08-20", + "input_cost_per_token": 2.5e-06, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure/global-standard/gpt-4o-2024-11-20": { + "cache_read_input_token_cost": 1.25e-06, + "deprecation_date": "2025-12-20", + "input_cost_per_token": 2.5e-06, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure/global-standard/gpt-4o-mini": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 6e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure/global/gpt-4o-2024-08-06": { + "cache_read_input_token_cost": 1.25e-06, + "input_cost_per_token": 2.5e-06, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure/global/gpt-4o-2024-11-20": { + "cache_read_input_token_cost": 1.25e-06, + "input_cost_per_token": 2.5e-06, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure/gpt-3.5-turbo": { + "input_cost_per_token": 5e-07, + "litellm_provider": "azure", + "max_input_tokens": 4097, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.5e-06, + "supports_function_calling": true, + "supports_tool_choice": true + }, + "azure/gpt-3.5-turbo-0125": { + "deprecation_date": "2025-03-31", + "input_cost_per_token": 5e-07, + "litellm_provider": "azure", + "max_input_tokens": 16384, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.5e-06, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "azure/gpt-3.5-turbo-instruct-0914": { + "input_cost_per_token": 1.5e-06, + "litellm_provider": "azure_text", + "max_input_tokens": 4097, + "max_tokens": 4097, + "mode": "completion", + "output_cost_per_token": 2e-06 + }, + "azure/gpt-35-turbo": { + "input_cost_per_token": 5e-07, + "litellm_provider": "azure", + "max_input_tokens": 4097, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.5e-06, + "supports_function_calling": true, + "supports_tool_choice": true + }, + "azure/gpt-35-turbo-0125": { + "deprecation_date": "2025-05-31", + "input_cost_per_token": 5e-07, + "litellm_provider": "azure", + "max_input_tokens": 16384, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.5e-06, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "azure/gpt-35-turbo-0301": { + "deprecation_date": "2025-02-13", + "input_cost_per_token": 2e-07, + "litellm_provider": "azure", + "max_input_tokens": 4097, + "max_output_tokens": 4096, + "max_tokens": 4097, + "mode": "chat", + "output_cost_per_token": 2e-06, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "azure/gpt-35-turbo-0613": { + "deprecation_date": "2025-02-13", + "input_cost_per_token": 1.5e-06, + "litellm_provider": "azure", + "max_input_tokens": 4097, + "max_output_tokens": 4096, + "max_tokens": 4097, + "mode": "chat", + "output_cost_per_token": 2e-06, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "azure/gpt-35-turbo-1106": { + "deprecation_date": "2025-03-31", + "input_cost_per_token": 1e-06, + "litellm_provider": "azure", + "max_input_tokens": 16384, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2e-06, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "azure/gpt-35-turbo-16k": { + "input_cost_per_token": 3e-06, + "litellm_provider": "azure", + "max_input_tokens": 16385, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 4e-06, + "supports_tool_choice": true + }, + "azure/gpt-35-turbo-16k-0613": { + "input_cost_per_token": 3e-06, + "litellm_provider": "azure", + "max_input_tokens": 16385, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 4e-06, + "supports_function_calling": true, + "supports_tool_choice": true + }, + "azure/gpt-35-turbo-instruct": { + "input_cost_per_token": 1.5e-06, + "litellm_provider": "azure_text", + "max_input_tokens": 4097, + "max_tokens": 4097, + "mode": "completion", + "output_cost_per_token": 2e-06 + }, + "azure/gpt-35-turbo-instruct-0914": { + "input_cost_per_token": 1.5e-06, + "litellm_provider": "azure_text", + "max_input_tokens": 4097, + "max_tokens": 4097, + "mode": "completion", + "output_cost_per_token": 2e-06 + }, + "azure/gpt-4": { + "input_cost_per_token": 3e-05, + "litellm_provider": "azure", + "max_input_tokens": 8192, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 6e-05, + "supports_function_calling": true, + "supports_tool_choice": true + }, + "azure/gpt-4-0125-preview": { + "input_cost_per_token": 1e-05, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 3e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "azure/gpt-4-0613": { + "input_cost_per_token": 3e-05, + "litellm_provider": "azure", + "max_input_tokens": 8192, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 6e-05, + "supports_function_calling": true, + "supports_tool_choice": true + }, + "azure/gpt-4-1106-preview": { + "input_cost_per_token": 1e-05, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 3e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "azure/gpt-4-32k": { + "input_cost_per_token": 6e-05, + "litellm_provider": "azure", + "max_input_tokens": 32768, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.00012, + "supports_tool_choice": true + }, + "azure/gpt-4-32k-0613": { + "input_cost_per_token": 6e-05, + "litellm_provider": "azure", + "max_input_tokens": 32768, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.00012, + "supports_tool_choice": true + }, + "azure/gpt-4-turbo": { + "input_cost_per_token": 1e-05, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 3e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "azure/gpt-4-turbo-2024-04-09": { + "input_cost_per_token": 1e-05, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 3e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure/gpt-4-turbo-vision-preview": { + "input_cost_per_token": 1e-05, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 3e-05, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure/gpt-4.1": { + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_batches": 1e-06, + "litellm_provider": "azure", + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 8e-06, + "output_cost_per_token_batches": 4e-06, + "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 + }, + "azure/gpt-4.1-2025-04-14": { + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_batches": 1e-06, + "litellm_provider": "azure", + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 8e-06, + "output_cost_per_token_batches": 4e-06, + "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 + }, + "azure/gpt-4.1-mini": { + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 4e-07, + "input_cost_per_token_batches": 2e-07, + "litellm_provider": "azure", + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 1.6e-06, + "output_cost_per_token_batches": 8e-07, + "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 + }, + "azure/gpt-4.1-mini-2025-04-14": { + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 4e-07, + "input_cost_per_token_batches": 2e-07, + "litellm_provider": "azure", + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 1.6e-06, + "output_cost_per_token_batches": 8e-07, + "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 + }, + "azure/gpt-4.1-nano": { + "cache_read_input_token_cost": 2.5e-08, + "input_cost_per_token": 1e-07, + "input_cost_per_token_batches": 5e-08, + "litellm_provider": "azure", + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 4e-07, + "output_cost_per_token_batches": 2e-07, + "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 + }, + "azure/gpt-4.1-nano-2025-04-14": { + "cache_read_input_token_cost": 2.5e-08, + "input_cost_per_token": 1e-07, + "input_cost_per_token_batches": 5e-08, + "litellm_provider": "azure", + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 4e-07, + "output_cost_per_token_batches": 2e-07, + "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 + }, + "azure/gpt-4.5-preview": { + "cache_read_input_token_cost": 3.75e-05, + "input_cost_per_token": 7.5e-05, + "input_cost_per_token_batches": 3.75e-05, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 0.00015, + "output_cost_per_token_batches": 7.5e-05, + "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 + }, + "azure/gpt-4o": { + "cache_read_input_token_cost": 1.25e-06, + "input_cost_per_token": 2.5e-06, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure/gpt-4o-2024-05-13": { + "input_cost_per_token": 5e-06, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure/gpt-4o-2024-08-06": { + "cache_read_input_token_cost": 1.25e-06, + "input_cost_per_token": 2.5e-06, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure/gpt-4o-2024-11-20": { + "cache_read_input_token_cost": 1.25e-06, + "input_cost_per_token": 2.75e-06, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.1e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure/gpt-4o-audio-preview-2024-12-17": { + "input_cost_per_audio_token": 4e-05, + "input_cost_per_token": 2.5e-06, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_audio_token": 8e-05, + "output_cost_per_token": 1e-05, + "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 + }, + "azure/gpt-4o-mini": { + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_token": 1.65e-07, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 6.6e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure/gpt-4o-mini-2024-07-18": { + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_token": 1.65e-07, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 6.6e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure/gpt-4o-mini-audio-preview-2024-12-17": { + "input_cost_per_audio_token": 4e-05, + "input_cost_per_token": 2.5e-06, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_audio_token": 8e-05, + "output_cost_per_token": 1e-05, + "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 + }, + "azure/gpt-4o-mini-realtime-preview-2024-12-17": { + "cache_creation_input_audio_token_cost": 3e-07, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_audio_token": 1e-05, + "input_cost_per_token": 6e-07, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_audio_token": 2e-05, + "output_cost_per_token": 2.4e-06, + "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 + }, + "azure/gpt-4o-mini-transcribe": { + "input_cost_per_audio_token": 3e-06, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "azure", + "max_input_tokens": 16000, + "max_output_tokens": 2000, + "mode": "audio_transcription", + "output_cost_per_token": 5e-06, + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "azure/gpt-4o-mini-tts": { + "input_cost_per_token": 2.5e-06, + "litellm_provider": "azure", + "mode": "audio_speech", + "output_cost_per_audio_token": 1.2e-05, + "output_cost_per_second": 0.00025, + "output_cost_per_token": 1e-05, + "supported_endpoints": [ + "/v1/audio/speech" + ], + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "audio" + ] + }, + "azure/gpt-4o-realtime-preview-2024-10-01": { + "cache_creation_input_audio_token_cost": 2e-05, + "cache_read_input_token_cost": 2.5e-06, + "input_cost_per_audio_token": 0.0001, + "input_cost_per_token": 5e-06, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_audio_token": 0.0002, + "output_cost_per_token": 2e-05, + "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 + }, + "azure/gpt-4o-realtime-preview-2024-12-17": { + "cache_read_input_token_cost": 2.5e-06, + "input_cost_per_audio_token": 4e-05, + "input_cost_per_token": 5e-06, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_audio_token": 8e-05, + "output_cost_per_token": 2e-05, + "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 + }, + "azure/gpt-4o-transcribe": { + "input_cost_per_audio_token": 6e-06, + "input_cost_per_token": 2.5e-06, + "litellm_provider": "azure", + "max_input_tokens": 16000, + "max_output_tokens": 2000, + "mode": "audio_transcription", + "output_cost_per_token": 1e-05, + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "azure/gpt-5": { + "cache_read_input_token_cost": 1.25e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "azure", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "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 + }, + "azure/gpt-5-2025-08-07": { + "cache_read_input_token_cost": 1.25e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "azure", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "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 + }, + "azure/gpt-5-chat": { + "cache_read_input_token_cost": 1.25e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "azure", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "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 + }, + "azure/gpt-5-chat-latest": { + "cache_read_input_token_cost": 1.25e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "azure", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "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 + }, + "azure/gpt-5-codex": { + "cache_read_input_token_cost": 1.25e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "azure", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "responses", + "output_cost_per_token": 1e-05, + "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 + }, + "azure/gpt-5-mini": { + "cache_read_input_token_cost": 2.5e-08, + "input_cost_per_token": 2.5e-07, + "litellm_provider": "azure", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2e-06, + "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 + }, + "azure/gpt-5-mini-2025-08-07": { + "cache_read_input_token_cost": 2.5e-08, + "input_cost_per_token": 2.5e-07, + "litellm_provider": "azure", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2e-06, + "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 + }, + "azure/gpt-5-nano": { + "cache_read_input_token_cost": 5e-09, + "input_cost_per_token": 5e-08, + "litellm_provider": "azure", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4e-07, + "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 + }, + "azure/gpt-5-nano-2025-08-07": { + "cache_read_input_token_cost": 5e-09, + "input_cost_per_token": 5e-08, + "litellm_provider": "azure", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4e-07, + "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 + }, + "azure/gpt-image-1": { + "input_cost_per_pixel": 4.0054321e-08, + "litellm_provider": "azure", + "mode": "image_generation", + "output_cost_per_pixel": 0.0, + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "azure/hd/1024-x-1024/dall-e-3": { + "input_cost_per_pixel": 7.629e-08, + "litellm_provider": "azure", + "mode": "image_generation", + "output_cost_per_token": 0.0 + }, + "azure/hd/1024-x-1792/dall-e-3": { + "input_cost_per_pixel": 6.539e-08, + "litellm_provider": "azure", + "mode": "image_generation", + "output_cost_per_token": 0.0 + }, + "azure/hd/1792-x-1024/dall-e-3": { + "input_cost_per_pixel": 6.539e-08, + "litellm_provider": "azure", + "mode": "image_generation", + "output_cost_per_token": 0.0 + }, + "azure/high/1024-x-1024/gpt-image-1": { + "input_cost_per_pixel": 1.59263611e-07, + "litellm_provider": "azure", + "mode": "image_generation", + "output_cost_per_pixel": 0.0, + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "azure/high/1024-x-1536/gpt-image-1": { + "input_cost_per_pixel": 1.58945719e-07, + "litellm_provider": "azure", + "mode": "image_generation", + "output_cost_per_pixel": 0.0, + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "azure/high/1536-x-1024/gpt-image-1": { + "input_cost_per_pixel": 1.58945719e-07, + "litellm_provider": "azure", + "mode": "image_generation", + "output_cost_per_pixel": 0.0, + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "azure/low/1024-x-1024/gpt-image-1": { + "input_cost_per_pixel": 1.0490417e-08, + "litellm_provider": "azure", + "mode": "image_generation", + "output_cost_per_pixel": 0.0, + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "azure/low/1024-x-1536/gpt-image-1": { + "input_cost_per_pixel": 1.0172526e-08, + "litellm_provider": "azure", + "mode": "image_generation", + "output_cost_per_pixel": 0.0, + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "azure/low/1536-x-1024/gpt-image-1": { + "input_cost_per_pixel": 1.0172526e-08, + "litellm_provider": "azure", + "mode": "image_generation", + "output_cost_per_pixel": 0.0, + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "azure/medium/1024-x-1024/gpt-image-1": { + "input_cost_per_pixel": 4.0054321e-08, + "litellm_provider": "azure", + "mode": "image_generation", + "output_cost_per_pixel": 0.0, + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "azure/medium/1024-x-1536/gpt-image-1": { + "input_cost_per_pixel": 4.0054321e-08, + "litellm_provider": "azure", + "mode": "image_generation", + "output_cost_per_pixel": 0.0, + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "azure/medium/1536-x-1024/gpt-image-1": { + "input_cost_per_pixel": 4.0054321e-08, + "litellm_provider": "azure", + "mode": "image_generation", + "output_cost_per_pixel": 0.0, + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "azure/mistral-large-2402": { + "input_cost_per_token": 8e-06, + "litellm_provider": "azure", + "max_input_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 2.4e-05, + "supports_function_calling": true + }, + "azure/mistral-large-latest": { + "input_cost_per_token": 8e-06, + "litellm_provider": "azure", + "max_input_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 2.4e-05, + "supports_function_calling": true + }, + "azure/o1": { + "cache_read_input_token_cost": 7.5e-06, + "input_cost_per_token": 1.5e-05, + "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 6e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure/o1-2024-12-17": { + "cache_read_input_token_cost": 7.5e-06, + "input_cost_per_token": 1.5e-05, + "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 6e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure/o1-mini": { + "cache_read_input_token_cost": 6.05e-07, + "input_cost_per_token": 1.21e-06, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 4.84e-06, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_vision": false + }, + "azure/o1-mini-2024-09-12": { + "cache_read_input_token_cost": 5.5e-07, + "input_cost_per_token": 1.1e-06, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_vision": false + }, + "azure/o1-preview": { + "cache_read_input_token_cost": 7.5e-06, + "input_cost_per_token": 1.5e-05, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 6e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_vision": false + }, + "azure/o1-preview-2024-09-12": { + "cache_read_input_token_cost": 7.5e-06, + "input_cost_per_token": 1.5e-05, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 6e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_vision": false + }, + "azure/o3": { + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 8e-06, + "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 + }, + "azure/o3-2025-04-16": { + "cache_read_input_token_cost": 2.5e-06, + "input_cost_per_token": 1e-05, + "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 4e-05, + "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 + }, + "azure/o3-deep-research": { + "cache_read_input_token_cost": 2.5e-06, + "input_cost_per_token": 1e-05, + "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "responses", + "output_cost_per_token": 4e-05, + "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 + }, + "azure/o3-mini": { + "cache_read_input_token_cost": 5.5e-07, + "input_cost_per_token": 1.1e-06, + "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "azure/o3-mini-2025-01-31": { + "cache_read_input_token_cost": 5.5e-07, + "input_cost_per_token": 1.1e-06, + "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "azure/o3-pro": { + "input_cost_per_token": 2e-05, + "input_cost_per_token_batches": 1e-05, + "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "responses", + "output_cost_per_token": 8e-05, + "output_cost_per_token_batches": 4e-05, + "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 + }, + "azure/o3-pro-2025-06-10": { + "input_cost_per_token": 2e-05, + "input_cost_per_token_batches": 1e-05, + "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "responses", + "output_cost_per_token": 8e-05, + "output_cost_per_token_batches": 4e-05, + "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 + }, + "azure/o4-mini": { + "cache_read_input_token_cost": 2.75e-07, + "input_cost_per_token": 1.1e-06, + "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "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 + }, + "azure/o4-mini-2025-04-16": { + "cache_read_input_token_cost": 2.75e-07, + "input_cost_per_token": 1.1e-06, + "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "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 + }, + "azure/standard/1024-x-1024/dall-e-2": { + "input_cost_per_pixel": 0.0, + "litellm_provider": "azure", + "mode": "image_generation", + "output_cost_per_token": 0.0 + }, + "azure/standard/1024-x-1024/dall-e-3": { + "input_cost_per_pixel": 3.81469e-08, + "litellm_provider": "azure", + "mode": "image_generation", + "output_cost_per_token": 0.0 + }, + "azure/standard/1024-x-1792/dall-e-3": { + "input_cost_per_pixel": 4.359e-08, + "litellm_provider": "azure", + "mode": "image_generation", + "output_cost_per_token": 0.0 + }, + "azure/standard/1792-x-1024/dall-e-3": { + "input_cost_per_pixel": 4.359e-08, + "litellm_provider": "azure", + "mode": "image_generation", + "output_cost_per_token": 0.0 + }, + "azure/text-embedding-3-large": { + "input_cost_per_token": 1.3e-07, + "litellm_provider": "azure", + "max_input_tokens": 8191, + "max_tokens": 8191, + "mode": "embedding", + "output_cost_per_token": 0.0 + }, + "azure/text-embedding-3-small": { + "input_cost_per_token": 2e-08, + "litellm_provider": "azure", + "max_input_tokens": 8191, + "max_tokens": 8191, + "mode": "embedding", + "output_cost_per_token": 0.0 + }, + "azure/text-embedding-ada-002": { + "input_cost_per_token": 1e-07, + "litellm_provider": "azure", + "max_input_tokens": 8191, + "max_tokens": 8191, + "mode": "embedding", + "output_cost_per_token": 0.0 + }, + "azure/tts-1": { + "input_cost_per_character": 1.5e-05, + "litellm_provider": "azure", + "mode": "audio_speech" + }, + "azure/tts-1-hd": { + "input_cost_per_character": 3e-05, + "litellm_provider": "azure", + "mode": "audio_speech" + }, + "azure/us/gpt-4o-2024-08-06": { + "cache_read_input_token_cost": 1.375e-06, + "input_cost_per_token": 2.75e-06, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.1e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure/us/gpt-4o-2024-11-20": { + "cache_creation_input_token_cost": 1.38e-06, + "input_cost_per_token": 2.75e-06, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.1e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure/us/gpt-4o-mini-2024-07-18": { + "cache_read_input_token_cost": 8.3e-08, + "input_cost_per_token": 1.65e-07, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 6.6e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure/us/gpt-4o-mini-realtime-preview-2024-12-17": { + "cache_creation_input_audio_token_cost": 3.3e-07, + "cache_read_input_token_cost": 3.3e-07, + "input_cost_per_audio_token": 1.1e-05, + "input_cost_per_token": 6.6e-07, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_audio_token": 2.2e-05, + "output_cost_per_token": 2.64e-06, + "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 + }, + "azure/us/gpt-4o-realtime-preview-2024-10-01": { + "cache_creation_input_audio_token_cost": 2.2e-05, + "cache_read_input_token_cost": 2.75e-06, + "input_cost_per_audio_token": 0.00011, + "input_cost_per_token": 5.5e-06, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_audio_token": 0.00022, + "output_cost_per_token": 2.2e-05, + "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 + }, + "azure/us/gpt-4o-realtime-preview-2024-12-17": { + "cache_read_input_audio_token_cost": 2.5e-06, + "cache_read_input_token_cost": 2.75e-06, + "input_cost_per_audio_token": 4.4e-05, + "input_cost_per_token": 5.5e-06, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_audio_token": 8e-05, + "output_cost_per_token": 2.2e-05, + "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 + }, + "azure/us/o1-2024-12-17": { + "cache_read_input_token_cost": 8.25e-06, + "input_cost_per_token": 1.65e-05, + "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 6.6e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure/us/o1-mini-2024-09-12": { + "cache_read_input_token_cost": 6.05e-07, + "input_cost_per_token": 1.21e-06, + "input_cost_per_token_batches": 6.05e-07, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 4.84e-06, + "output_cost_per_token_batches": 2.42e-06, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_vision": false + }, + "azure/us/o1-preview-2024-09-12": { + "cache_read_input_token_cost": 8.25e-06, + "input_cost_per_token": 1.65e-05, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 6.6e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_vision": false + }, + "azure/us/o3-mini-2025-01-31": { + "cache_read_input_token_cost": 6.05e-07, + "input_cost_per_token": 1.21e-06, + "input_cost_per_token_batches": 6.05e-07, + "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 4.84e-06, + "output_cost_per_token_batches": 2.42e-06, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "azure/whisper-1": { + "input_cost_per_second": 0.0001, + "litellm_provider": "azure", + "mode": "audio_transcription", + "output_cost_per_second": 0.0001 + }, + "azure_ai/Cohere-embed-v3-english": { + "input_cost_per_token": 1e-07, + "litellm_provider": "azure_ai", + "max_input_tokens": 512, + "max_tokens": 512, + "mode": "embedding", + "output_cost_per_token": 0.0, + "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 + }, + "azure_ai/Cohere-embed-v3-multilingual": { + "input_cost_per_token": 1e-07, + "litellm_provider": "azure_ai", + "max_input_tokens": 512, + "max_tokens": 512, + "mode": "embedding", + "output_cost_per_token": 0.0, + "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 + }, + "azure_ai/FLUX-1.1-pro": { + "litellm_provider": "azure_ai", + "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" + ] + }, + "azure_ai/FLUX.1-Kontext-pro": { + "litellm_provider": "azure_ai", + "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" + ] + }, + "azure_ai/Llama-3.2-11B-Vision-Instruct": { + "input_cost_per_token": 3.7e-07, + "litellm_provider": "azure_ai", + "max_input_tokens": 128000, + "max_output_tokens": 2048, + "max_tokens": 2048, + "mode": "chat", + "output_cost_per_token": 3.7e-07, + "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 + }, + "azure_ai/Llama-3.2-90B-Vision-Instruct": { + "input_cost_per_token": 2.04e-06, + "litellm_provider": "azure_ai", + "max_input_tokens": 128000, + "max_output_tokens": 2048, + "max_tokens": 2048, + "mode": "chat", + "output_cost_per_token": 2.04e-06, + "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 + }, + "azure_ai/Llama-3.3-70B-Instruct": { + "input_cost_per_token": 7.1e-07, + "litellm_provider": "azure_ai", + "max_input_tokens": 128000, + "max_output_tokens": 2048, + "max_tokens": 2048, + "mode": "chat", + "output_cost_per_token": 7.1e-07, + "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 + }, + "azure_ai/Llama-4-Maverick-17B-128E-Instruct-FP8": { + "input_cost_per_token": 1.41e-06, + "litellm_provider": "azure_ai", + "max_input_tokens": 1000000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 3.5e-07, + "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 + }, + "azure_ai/Llama-4-Scout-17B-16E-Instruct": { + "input_cost_per_token": 2e-07, + "litellm_provider": "azure_ai", + "max_input_tokens": 10000000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 7.8e-07, + "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 + }, + "azure_ai/Meta-Llama-3-70B-Instruct": { + "input_cost_per_token": 1.1e-06, + "litellm_provider": "azure_ai", + "max_input_tokens": 8192, + "max_output_tokens": 2048, + "max_tokens": 2048, + "mode": "chat", + "output_cost_per_token": 3.7e-07, + "supports_tool_choice": true + }, + "azure_ai/Meta-Llama-3.1-405B-Instruct": { + "input_cost_per_token": 5.33e-06, + "litellm_provider": "azure_ai", + "max_input_tokens": 128000, + "max_output_tokens": 2048, + "max_tokens": 2048, + "mode": "chat", + "output_cost_per_token": 1.6e-05, + "source": "https://azuremarketplace.microsoft.com/en-us/marketplace/apps/metagenai.meta-llama-3-1-405b-instruct-offer?tab=PlansAndPrice", + "supports_tool_choice": true + }, + "azure_ai/Meta-Llama-3.1-70B-Instruct": { + "input_cost_per_token": 2.68e-06, + "litellm_provider": "azure_ai", + "max_input_tokens": 128000, + "max_output_tokens": 2048, + "max_tokens": 2048, + "mode": "chat", + "output_cost_per_token": 3.54e-06, + "source": "https://azuremarketplace.microsoft.com/en-us/marketplace/apps/metagenai.meta-llama-3-1-70b-instruct-offer?tab=PlansAndPrice", + "supports_tool_choice": true + }, + "azure_ai/Meta-Llama-3.1-8B-Instruct": { + "input_cost_per_token": 3e-07, + "litellm_provider": "azure_ai", + "max_input_tokens": 128000, + "max_output_tokens": 2048, + "max_tokens": 2048, + "mode": "chat", + "output_cost_per_token": 6.1e-07, + "source": "https://azuremarketplace.microsoft.com/en-us/marketplace/apps/metagenai.meta-llama-3-1-8b-instruct-offer?tab=PlansAndPrice", + "supports_tool_choice": true + }, + "azure_ai/Phi-3-medium-128k-instruct": { + "input_cost_per_token": 1.7e-07, + "litellm_provider": "azure_ai", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 6.8e-07, + "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "supports_tool_choice": true, + "supports_vision": false + }, + "azure_ai/Phi-3-medium-4k-instruct": { + "input_cost_per_token": 1.7e-07, + "litellm_provider": "azure_ai", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 6.8e-07, + "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "supports_tool_choice": true, + "supports_vision": false + }, + "azure_ai/Phi-3-mini-128k-instruct": { + "input_cost_per_token": 1.3e-07, + "litellm_provider": "azure_ai", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 5.2e-07, + "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "supports_tool_choice": true, + "supports_vision": false + }, + "azure_ai/Phi-3-mini-4k-instruct": { + "input_cost_per_token": 1.3e-07, + "litellm_provider": "azure_ai", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 5.2e-07, + "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "supports_tool_choice": true, + "supports_vision": false + }, + "azure_ai/Phi-3-small-128k-instruct": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "azure_ai", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 6e-07, + "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "supports_tool_choice": true, + "supports_vision": false + }, + "azure_ai/Phi-3-small-8k-instruct": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "azure_ai", + "max_input_tokens": 8192, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 6e-07, + "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "supports_tool_choice": true, + "supports_vision": false + }, + "azure_ai/Phi-3.5-MoE-instruct": { + "input_cost_per_token": 1.6e-07, + "litellm_provider": "azure_ai", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 6.4e-07, + "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "supports_tool_choice": true, + "supports_vision": false + }, + "azure_ai/Phi-3.5-mini-instruct": { + "input_cost_per_token": 1.3e-07, + "litellm_provider": "azure_ai", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 5.2e-07, + "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "supports_tool_choice": true, + "supports_vision": false + }, + "azure_ai/Phi-3.5-vision-instruct": { + "input_cost_per_token": 1.3e-07, + "litellm_provider": "azure_ai", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 5.2e-07, + "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "supports_tool_choice": true, + "supports_vision": true + }, + "azure_ai/Phi-4": { + "input_cost_per_token": 1.25e-07, + "litellm_provider": "azure_ai", + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 5e-07, + "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 + }, + "azure_ai/Phi-4-mini-instruct": { + "input_cost_per_token": 7.5e-08, + "litellm_provider": "azure_ai", + "max_input_tokens": 131072, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 3e-07, + "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 + }, + "azure_ai/Phi-4-multimodal-instruct": { + "input_cost_per_audio_token": 4e-06, + "input_cost_per_token": 8e-08, + "litellm_provider": "azure_ai", + "max_input_tokens": 131072, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 3.2e-07, + "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 + }, + "azure_ai/cohere-rerank-v3-english": { + "input_cost_per_query": 0.002, + "input_cost_per_token": 0.0, + "litellm_provider": "azure_ai", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_query_tokens": 2048, + "max_tokens": 4096, + "mode": "rerank", + "output_cost_per_token": 0.0 + }, + "azure_ai/cohere-rerank-v3-multilingual": { + "input_cost_per_query": 0.002, + "input_cost_per_token": 0.0, + "litellm_provider": "azure_ai", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_query_tokens": 2048, + "max_tokens": 4096, + "mode": "rerank", + "output_cost_per_token": 0.0 + }, + "azure_ai/cohere-rerank-v3.5": { + "input_cost_per_query": 0.002, + "input_cost_per_token": 0.0, + "litellm_provider": "azure_ai", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_query_tokens": 2048, + "max_tokens": 4096, + "mode": "rerank", + "output_cost_per_token": 0.0 + }, + "azure_ai/deepseek-r1": { + "input_cost_per_token": 1.35e-06, + "litellm_provider": "azure_ai", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 5.4e-06, + "source": "https://techcommunity.microsoft.com/blog/machinelearningblog/deepseek-r1-improved-performance-higher-limits-and-transparent-pricing/4386367", + "supports_reasoning": true, + "supports_tool_choice": true + }, + "azure_ai/deepseek-v3": { + "input_cost_per_token": 1.14e-06, + "litellm_provider": "azure_ai", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 4.56e-06, + "source": "https://techcommunity.microsoft.com/blog/machinelearningblog/announcing-deepseek-v3-on-azure-ai-foundry-and-github/4390438", + "supports_tool_choice": true + }, + "azure_ai/deepseek-v3-0324": { + "input_cost_per_token": 1.14e-06, + "litellm_provider": "azure_ai", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 4.56e-06, + "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 + }, + "azure_ai/embed-v-4-0": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "azure_ai", + "max_input_tokens": 128000, + "max_tokens": 128000, + "mode": "embedding", + "output_cost_per_token": 0.0, + "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 + }, + "azure_ai/global/grok-3": { + "input_cost_per_token": 3e-06, + "litellm_provider": "azure_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "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 + }, + "azure_ai/global/grok-3-mini": { + "input_cost_per_token": 2.5e-07, + "litellm_provider": "azure_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.27e-06, + "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 + }, + "azure_ai/grok-3": { + "input_cost_per_token": 3.3e-06, + "litellm_provider": "azure_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.65e-05, + "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 + }, + "azure_ai/grok-3-mini": { + "input_cost_per_token": 2.75e-07, + "litellm_provider": "azure_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.38e-06, + "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 + }, + "azure_ai/jais-30b-chat": { + "input_cost_per_token": 0.0032, + "litellm_provider": "azure_ai", + "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" + }, + "azure_ai/jamba-instruct": { + "input_cost_per_token": 5e-07, + "litellm_provider": "azure_ai", + "max_input_tokens": 70000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 7e-07, + "supports_tool_choice": true + }, + "azure_ai/ministral-3b": { + "input_cost_per_token": 4e-08, + "litellm_provider": "azure_ai", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 4e-08, + "source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/000-000.ministral-3b-2410-offer?tab=Overview", + "supports_function_calling": true, + "supports_tool_choice": true + }, + "azure_ai/mistral-large": { + "input_cost_per_token": 4e-06, + "litellm_provider": "azure_ai", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 1.2e-05, + "supports_function_calling": true, + "supports_tool_choice": true + }, + "azure_ai/mistral-large-2407": { + "input_cost_per_token": 2e-06, + "litellm_provider": "azure_ai", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 6e-06, + "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 + }, + "azure_ai/mistral-large-latest": { + "input_cost_per_token": 2e-06, + "litellm_provider": "azure_ai", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 6e-06, + "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 + }, + "azure_ai/mistral-medium-2505": { + "input_cost_per_token": 4e-07, + "litellm_provider": "azure_ai", + "max_input_tokens": 131072, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 2e-06, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_tool_choice": true + }, + "azure_ai/mistral-nemo": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "azure_ai", + "max_input_tokens": 131072, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.5e-07, + "source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/000-000.mistral-nemo-12b-2407?tab=PlansAndPrice", + "supports_function_calling": true + }, + "azure_ai/mistral-small": { + "input_cost_per_token": 1e-06, + "litellm_provider": "azure_ai", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 3e-06, + "supports_function_calling": true, + "supports_tool_choice": true + }, + "azure_ai/mistral-small-2503": { + "input_cost_per_token": 1e-06, + "litellm_provider": "azure_ai", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3e-06, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "babbage-002": { + "input_cost_per_token": 4e-07, + "litellm_provider": "text-completion-openai", + "max_input_tokens": 16384, + "max_output_tokens": 4096, + "max_tokens": 16384, + "mode": "completion", + "output_cost_per_token": 4e-07 + }, + "bedrock/*/1-month-commitment/cohere.command-light-text-v14": { + "input_cost_per_second": 0.001902, + "litellm_provider": "bedrock", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_second": 0.001902, + "supports_tool_choice": true + }, + "bedrock/*/1-month-commitment/cohere.command-text-v14": { + "input_cost_per_second": 0.011, + "litellm_provider": "bedrock", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_second": 0.011, + "supports_tool_choice": true + }, + "bedrock/*/6-month-commitment/cohere.command-light-text-v14": { + "input_cost_per_second": 0.0011416, + "litellm_provider": "bedrock", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_second": 0.0011416, + "supports_tool_choice": true + }, + "bedrock/*/6-month-commitment/cohere.command-text-v14": { + "input_cost_per_second": 0.0066027, + "litellm_provider": "bedrock", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_second": 0.0066027, + "supports_tool_choice": true + }, + "bedrock/ap-northeast-1/1-month-commitment/anthropic.claude-instant-v1": { + "input_cost_per_second": 0.01475, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.01475, + "supports_tool_choice": true + }, + "bedrock/ap-northeast-1/1-month-commitment/anthropic.claude-v1": { + "input_cost_per_second": 0.0455, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.0455 + }, + "bedrock/ap-northeast-1/1-month-commitment/anthropic.claude-v2:1": { + "input_cost_per_second": 0.0455, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.0455, + "supports_tool_choice": true + }, + "bedrock/ap-northeast-1/6-month-commitment/anthropic.claude-instant-v1": { + "input_cost_per_second": 0.008194, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.008194, + "supports_tool_choice": true + }, + "bedrock/ap-northeast-1/6-month-commitment/anthropic.claude-v1": { + "input_cost_per_second": 0.02527, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.02527 + }, + "bedrock/ap-northeast-1/6-month-commitment/anthropic.claude-v2:1": { + "input_cost_per_second": 0.02527, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.02527, + "supports_tool_choice": true + }, + "bedrock/ap-northeast-1/anthropic.claude-instant-v1": { + "input_cost_per_token": 2.23e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 7.55e-06, + "supports_tool_choice": true + }, + "bedrock/ap-northeast-1/anthropic.claude-v1": { + "input_cost_per_token": 8e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 2.4e-05, + "supports_tool_choice": true + }, + "bedrock/ap-northeast-1/anthropic.claude-v2:1": { + "input_cost_per_token": 8e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 2.4e-05, + "supports_tool_choice": true + }, + "bedrock/ap-south-1/meta.llama3-70b-instruct-v1:0": { + "input_cost_per_token": 3.18e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 4.2e-06 + }, + "bedrock/ap-south-1/meta.llama3-8b-instruct-v1:0": { + "input_cost_per_token": 3.6e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 7.2e-07 + }, + "bedrock/ca-central-1/meta.llama3-70b-instruct-v1:0": { + "input_cost_per_token": 3.05e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 4.03e-06 + }, + "bedrock/ca-central-1/meta.llama3-8b-instruct-v1:0": { + "input_cost_per_token": 3.5e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 6.9e-07 + }, + "bedrock/eu-central-1/1-month-commitment/anthropic.claude-instant-v1": { + "input_cost_per_second": 0.01635, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.01635, + "supports_tool_choice": true + }, + "bedrock/eu-central-1/1-month-commitment/anthropic.claude-v1": { + "input_cost_per_second": 0.0415, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.0415 + }, + "bedrock/eu-central-1/1-month-commitment/anthropic.claude-v2:1": { + "input_cost_per_second": 0.0415, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.0415, + "supports_tool_choice": true + }, + "bedrock/eu-central-1/6-month-commitment/anthropic.claude-instant-v1": { + "input_cost_per_second": 0.009083, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.009083, + "supports_tool_choice": true + }, + "bedrock/eu-central-1/6-month-commitment/anthropic.claude-v1": { + "input_cost_per_second": 0.02305, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.02305 + }, + "bedrock/eu-central-1/6-month-commitment/anthropic.claude-v2:1": { + "input_cost_per_second": 0.02305, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.02305, + "supports_tool_choice": true + }, + "bedrock/eu-central-1/anthropic.claude-instant-v1": { + "input_cost_per_token": 2.48e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 8.38e-06, + "supports_tool_choice": true + }, + "bedrock/eu-central-1/anthropic.claude-v1": { + "input_cost_per_token": 8e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 2.4e-05 + }, + "bedrock/eu-central-1/anthropic.claude-v2:1": { + "input_cost_per_token": 8e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 2.4e-05, + "supports_tool_choice": true + }, + "bedrock/eu-west-1/meta.llama3-70b-instruct-v1:0": { + "input_cost_per_token": 2.86e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 3.78e-06 + }, + "bedrock/eu-west-1/meta.llama3-8b-instruct-v1:0": { + "input_cost_per_token": 3.2e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 6.5e-07 + }, + "bedrock/eu-west-2/meta.llama3-70b-instruct-v1:0": { + "input_cost_per_token": 3.45e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 4.55e-06 + }, + "bedrock/eu-west-2/meta.llama3-8b-instruct-v1:0": { + "input_cost_per_token": 3.9e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 7.8e-07 + }, + "bedrock/eu-west-3/mistral.mistral-7b-instruct-v0:2": { + "input_cost_per_token": 2e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 2.6e-07, + "supports_tool_choice": true + }, + "bedrock/eu-west-3/mistral.mistral-large-2402-v1:0": { + "input_cost_per_token": 1.04e-05, + "litellm_provider": "bedrock", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 3.12e-05, + "supports_function_calling": true + }, + "bedrock/eu-west-3/mistral.mixtral-8x7b-instruct-v0:1": { + "input_cost_per_token": 5.9e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 9.1e-07, + "supports_tool_choice": true + }, + "bedrock/invoke/anthropic.claude-3-5-sonnet-20240620-v1:0": { + "input_cost_per_token": 3e-06, + "litellm_provider": "bedrock", + "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": 1.5e-05, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "bedrock/sa-east-1/meta.llama3-70b-instruct-v1:0": { + "input_cost_per_token": 4.45e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 5.88e-06 + }, + "bedrock/sa-east-1/meta.llama3-8b-instruct-v1:0": { + "input_cost_per_token": 5e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.01e-06 + }, + "bedrock/us-east-1/1-month-commitment/anthropic.claude-instant-v1": { + "input_cost_per_second": 0.011, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.011, + "supports_tool_choice": true + }, + "bedrock/us-east-1/1-month-commitment/anthropic.claude-v1": { + "input_cost_per_second": 0.0175, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.0175 + }, + "bedrock/us-east-1/1-month-commitment/anthropic.claude-v2:1": { + "input_cost_per_second": 0.0175, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.0175, + "supports_tool_choice": true + }, + "bedrock/us-east-1/6-month-commitment/anthropic.claude-instant-v1": { + "input_cost_per_second": 0.00611, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.00611, + "supports_tool_choice": true + }, + "bedrock/us-east-1/6-month-commitment/anthropic.claude-v1": { + "input_cost_per_second": 0.00972, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.00972 + }, + "bedrock/us-east-1/6-month-commitment/anthropic.claude-v2:1": { + "input_cost_per_second": 0.00972, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.00972, + "supports_tool_choice": true + }, + "bedrock/us-east-1/anthropic.claude-instant-v1": { + "input_cost_per_token": 8e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 2.4e-06, + "supports_tool_choice": true + }, + "bedrock/us-east-1/anthropic.claude-v1": { + "input_cost_per_token": 8e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 2.4e-05, + "supports_tool_choice": true + }, + "bedrock/us-east-1/anthropic.claude-v2:1": { + "input_cost_per_token": 8e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 2.4e-05, + "supports_tool_choice": true + }, + "bedrock/us-east-1/meta.llama3-70b-instruct-v1:0": { + "input_cost_per_token": 2.65e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 3.5e-06 + }, + "bedrock/us-east-1/meta.llama3-8b-instruct-v1:0": { + "input_cost_per_token": 3e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 6e-07 + }, + "bedrock/us-east-1/mistral.mistral-7b-instruct-v0:2": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 2e-07, + "supports_tool_choice": true + }, + "bedrock/us-east-1/mistral.mistral-large-2402-v1:0": { + "input_cost_per_token": 8e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 2.4e-05, + "supports_function_calling": true + }, + "bedrock/us-east-1/mistral.mixtral-8x7b-instruct-v0:1": { + "input_cost_per_token": 4.5e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 7e-07, + "supports_tool_choice": true + }, + "bedrock/us-gov-east-1/amazon.nova-pro-v1:0": { + "input_cost_per_token": 9.6e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 300000, + "max_output_tokens": 10000, + "max_tokens": 10000, + "mode": "chat", + "output_cost_per_token": 3.84e-06, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_vision": true + }, + "bedrock/us-gov-east-1/amazon.titan-embed-text-v1": { + "input_cost_per_token": 1e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 8192, + "max_tokens": 8192, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 1536 + }, + "bedrock/us-gov-east-1/amazon.titan-embed-text-v2:0": { + "input_cost_per_token": 2e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 8192, + "max_tokens": 8192, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 1024 + }, + "bedrock/us-gov-east-1/amazon.titan-text-express-v1": { + "input_cost_per_token": 1.3e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 42000, + "max_output_tokens": 8000, + "max_tokens": 8000, + "mode": "chat", + "output_cost_per_token": 1.7e-06 + }, + "bedrock/us-gov-east-1/amazon.titan-text-lite-v1": { + "input_cost_per_token": 3e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 42000, + "max_output_tokens": 4000, + "max_tokens": 4000, + "mode": "chat", + "output_cost_per_token": 4e-07 + }, + "bedrock/us-gov-east-1/amazon.titan-text-premier-v1:0": { + "input_cost_per_token": 5e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 42000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 1.5e-06 + }, + "bedrock/us-gov-east-1/anthropic.claude-3-5-sonnet-20240620-v1:0": { + "input_cost_per_token": 3.6e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.8e-05, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "bedrock/us-gov-east-1/anthropic.claude-3-haiku-20240307-v1:0": { + "input_cost_per_token": 3e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.5e-06, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "bedrock/us-gov-east-1/meta.llama3-70b-instruct-v1:0": { + "input_cost_per_token": 2.65e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 8000, + "max_output_tokens": 2048, + "max_tokens": 2048, + "mode": "chat", + "output_cost_per_token": 3.5e-06, + "supports_pdf_input": true + }, + "bedrock/us-gov-east-1/meta.llama3-8b-instruct-v1:0": { + "input_cost_per_token": 3e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 8000, + "max_output_tokens": 2048, + "max_tokens": 2048, + "mode": "chat", + "output_cost_per_token": 2.65e-06, + "supports_pdf_input": true + }, + "bedrock/us-gov-west-1/amazon.nova-pro-v1:0": { + "input_cost_per_token": 9.6e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 300000, + "max_output_tokens": 10000, + "max_tokens": 10000, + "mode": "chat", + "output_cost_per_token": 3.84e-06, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_vision": true + }, + "bedrock/us-gov-west-1/amazon.titan-embed-text-v1": { + "input_cost_per_token": 1e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 8192, + "max_tokens": 8192, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 1536 + }, + "bedrock/us-gov-west-1/amazon.titan-embed-text-v2:0": { + "input_cost_per_token": 2e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 8192, + "max_tokens": 8192, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 1024 + }, + "bedrock/us-gov-west-1/amazon.titan-text-express-v1": { + "input_cost_per_token": 1.3e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 42000, + "max_output_tokens": 8000, + "max_tokens": 8000, + "mode": "chat", + "output_cost_per_token": 1.7e-06 + }, + "bedrock/us-gov-west-1/amazon.titan-text-lite-v1": { + "input_cost_per_token": 3e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 42000, + "max_output_tokens": 4000, + "max_tokens": 4000, + "mode": "chat", + "output_cost_per_token": 4e-07 + }, + "bedrock/us-gov-west-1/amazon.titan-text-premier-v1:0": { + "input_cost_per_token": 5e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 42000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 1.5e-06 + }, + "bedrock/us-gov-west-1/anthropic.claude-3-5-sonnet-20240620-v1:0": { + "input_cost_per_token": 3.6e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.8e-05, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "bedrock/us-gov-west-1/anthropic.claude-3-haiku-20240307-v1:0": { + "input_cost_per_token": 3e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.5e-06, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "bedrock/us-gov-west-1/meta.llama3-70b-instruct-v1:0": { + "input_cost_per_token": 2.65e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 8000, + "max_output_tokens": 2048, + "max_tokens": 2048, + "mode": "chat", + "output_cost_per_token": 3.5e-06, + "supports_pdf_input": true + }, + "bedrock/us-gov-west-1/meta.llama3-8b-instruct-v1:0": { + "input_cost_per_token": 3e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 8000, + "max_output_tokens": 2048, + "max_tokens": 2048, + "mode": "chat", + "output_cost_per_token": 2.65e-06, + "supports_pdf_input": true + }, + "bedrock/us-west-1/meta.llama3-70b-instruct-v1:0": { + "input_cost_per_token": 2.65e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 3.5e-06 + }, + "bedrock/us-west-1/meta.llama3-8b-instruct-v1:0": { + "input_cost_per_token": 3e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 6e-07 + }, + "bedrock/us-west-2/1-month-commitment/anthropic.claude-instant-v1": { + "input_cost_per_second": 0.011, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.011, + "supports_tool_choice": true + }, + "bedrock/us-west-2/1-month-commitment/anthropic.claude-v1": { + "input_cost_per_second": 0.0175, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.0175 + }, + "bedrock/us-west-2/1-month-commitment/anthropic.claude-v2:1": { + "input_cost_per_second": 0.0175, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.0175, + "supports_tool_choice": true + }, + "bedrock/us-west-2/6-month-commitment/anthropic.claude-instant-v1": { + "input_cost_per_second": 0.00611, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.00611, + "supports_tool_choice": true + }, + "bedrock/us-west-2/6-month-commitment/anthropic.claude-v1": { + "input_cost_per_second": 0.00972, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.00972 + }, + "bedrock/us-west-2/6-month-commitment/anthropic.claude-v2:1": { + "input_cost_per_second": 0.00972, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.00972, + "supports_tool_choice": true + }, + "bedrock/us-west-2/anthropic.claude-instant-v1": { + "input_cost_per_token": 8e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 2.4e-06, + "supports_tool_choice": true + }, + "bedrock/us-west-2/anthropic.claude-v1": { + "input_cost_per_token": 8e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 2.4e-05, + "supports_tool_choice": true + }, + "bedrock/us-west-2/anthropic.claude-v2:1": { + "input_cost_per_token": 8e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 2.4e-05, + "supports_tool_choice": true + }, + "bedrock/us-west-2/mistral.mistral-7b-instruct-v0:2": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 2e-07, + "supports_tool_choice": true + }, + "bedrock/us-west-2/mistral.mistral-large-2402-v1:0": { + "input_cost_per_token": 8e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 2.4e-05, + "supports_function_calling": true + }, + "bedrock/us-west-2/mistral.mixtral-8x7b-instruct-v0:1": { + "input_cost_per_token": 4.5e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 7e-07, + "supports_tool_choice": true + }, + "bedrock/us.anthropic.claude-3-5-haiku-20241022-v1:0": { + "cache_creation_input_token_cost": 1e-06, + "cache_read_input_token_cost": 8e-08, + "input_cost_per_token": 8e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 4e-06, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "cerebras/llama-3.3-70b": { + "input_cost_per_token": 8.5e-07, + "litellm_provider": "cerebras", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "supports_function_calling": true, + "supports_tool_choice": true + }, + "cerebras/llama3.1-70b": { + "input_cost_per_token": 6e-07, + "litellm_provider": "cerebras", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-07, + "supports_function_calling": true, + "supports_tool_choice": true + }, + "cerebras/llama3.1-8b": { + "input_cost_per_token": 1e-07, + "litellm_provider": "cerebras", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-07, + "supports_function_calling": true, + "supports_tool_choice": true + }, + "cerebras/openai/gpt-oss-120b": { + "input_cost_per_token": 2.5e-07, + "litellm_provider": "cerebras", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 6.9e-07, + "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 + }, + "cerebras/qwen-3-32b": { + "input_cost_per_token": 4e-07, + "litellm_provider": "cerebras", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 8e-07, + "source": "https://inference-docs.cerebras.ai/support/pricing", + "supports_function_calling": true, + "supports_tool_choice": true + }, + "chat-bison": { + "input_cost_per_character": 2.5e-07, + "input_cost_per_token": 1.25e-07, + "litellm_provider": "vertex_ai-chat-models", + "max_input_tokens": 8192, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_character": 5e-07, + "output_cost_per_token": 1.25e-07, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "supports_tool_choice": true + }, + "chat-bison-32k": { + "input_cost_per_character": 2.5e-07, + "input_cost_per_token": 1.25e-07, + "litellm_provider": "vertex_ai-chat-models", + "max_input_tokens": 32000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_character": 5e-07, + "output_cost_per_token": 1.25e-07, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "supports_tool_choice": true + }, + "chat-bison-32k@002": { + "input_cost_per_character": 2.5e-07, + "input_cost_per_token": 1.25e-07, + "litellm_provider": "vertex_ai-chat-models", + "max_input_tokens": 32000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_character": 5e-07, + "output_cost_per_token": 1.25e-07, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "supports_tool_choice": true + }, + "chat-bison@001": { + "input_cost_per_character": 2.5e-07, + "input_cost_per_token": 1.25e-07, + "litellm_provider": "vertex_ai-chat-models", + "max_input_tokens": 8192, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_character": 5e-07, + "output_cost_per_token": 1.25e-07, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "supports_tool_choice": true + }, + "chat-bison@002": { + "deprecation_date": "2025-04-09", + "input_cost_per_character": 2.5e-07, + "input_cost_per_token": 1.25e-07, + "litellm_provider": "vertex_ai-chat-models", + "max_input_tokens": 8192, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_character": 5e-07, + "output_cost_per_token": 1.25e-07, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "supports_tool_choice": true + }, + "chatdolphin": { + "input_cost_per_token": 5e-07, + "litellm_provider": "nlp_cloud", + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 5e-07 + }, + "chatgpt-4o-latest": { + "input_cost_per_token": 5e-06, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "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 + }, + "claude-3-5-haiku-20241022": { + "cache_creation_input_token_cost": 1e-06, + "cache_creation_input_token_cost_above_1hr": 6e-06, + "cache_read_input_token_cost": 8e-08, + "deprecation_date": "2025-10-01", + "input_cost_per_token": 8e-07, + "litellm_provider": "anthropic", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 4e-06, + "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 + }, + "claude-3-5-haiku-latest": { + "cache_creation_input_token_cost": 1.25e-06, + "cache_creation_input_token_cost_above_1hr": 6e-06, + "cache_read_input_token_cost": 1e-07, + "deprecation_date": "2025-10-01", + "input_cost_per_token": 1e-06, + "litellm_provider": "anthropic", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 5e-06, + "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 + }, + "claude-3-5-sonnet-20240620": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_creation_input_token_cost_above_1hr": 6e-06, + "cache_read_input_token_cost": 3e-07, + "deprecation_date": "2025-06-01", + "input_cost_per_token": 3e-06, + "litellm_provider": "anthropic", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "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 + }, + "claude-3-5-sonnet-20241022": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_creation_input_token_cost_above_1hr": 6e-06, + "cache_read_input_token_cost": 3e-07, + "deprecation_date": "2025-10-01", + "input_cost_per_token": 3e-06, + "litellm_provider": "anthropic", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "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 + }, + "claude-3-5-sonnet-latest": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_creation_input_token_cost_above_1hr": 6e-06, + "cache_read_input_token_cost": 3e-07, + "deprecation_date": "2025-06-01", + "input_cost_per_token": 3e-06, + "litellm_provider": "anthropic", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "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 + }, + "claude-3-7-sonnet-20250219": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_creation_input_token_cost_above_1hr": 6e-06, + "cache_read_input_token_cost": 3e-07, + "deprecation_date": "2026-02-01", + "input_cost_per_token": 3e-06, + "litellm_provider": "anthropic", + "max_input_tokens": 200000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "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 + }, + "claude-3-7-sonnet-latest": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_creation_input_token_cost_above_1hr": 6e-06, + "cache_read_input_token_cost": 3e-07, + "deprecation_date": "2025-06-01", + "input_cost_per_token": 3e-06, + "litellm_provider": "anthropic", + "max_input_tokens": 200000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "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 + }, + "claude-3-haiku-20240307": { + "cache_creation_input_token_cost": 3e-07, + "cache_creation_input_token_cost_above_1hr": 6e-06, + "cache_read_input_token_cost": 3e-08, + "deprecation_date": "2025-03-01", + "input_cost_per_token": 2.5e-07, + "litellm_provider": "anthropic", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.25e-06, + "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 + }, + "claude-3-opus-20240229": { + "cache_creation_input_token_cost": 1.875e-05, + "cache_creation_input_token_cost_above_1hr": 6e-06, + "cache_read_input_token_cost": 1.5e-06, + "deprecation_date": "2025-03-01", + "input_cost_per_token": 1.5e-05, + "litellm_provider": "anthropic", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "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 + }, + "claude-3-opus-latest": { + "cache_creation_input_token_cost": 1.875e-05, + "cache_creation_input_token_cost_above_1hr": 6e-06, + "cache_read_input_token_cost": 1.5e-06, + "deprecation_date": "2025-03-01", + "input_cost_per_token": 1.5e-05, + "litellm_provider": "anthropic", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "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 + }, + "claude-4-opus-20250514": { + "cache_creation_input_token_cost": 1.875e-05, + "cache_read_input_token_cost": 1.5e-06, + "input_cost_per_token": 1.5e-05, + "litellm_provider": "anthropic", + "max_input_tokens": 200000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "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 + }, + "claude-4-sonnet-20250514": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, + "cache_read_input_token_cost": 3e-07, + "cache_read_input_token_cost_above_200k_tokens": 6e-07, + "input_cost_per_token": 3e-06, + "input_cost_per_token_above_200k_tokens": 6e-06, + "litellm_provider": "anthropic", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "output_cost_per_token_above_200k_tokens": 2.25e-05, + "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 + }, + "anthropic/claude-sonnet-4-5": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "litellm_provider": "anthropic", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 200000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "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 + }, + "claude-sonnet-4-5-20250929": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "litellm_provider": "anthropic", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 200000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "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 + }, + "claude-opus-4-1": { + "cache_creation_input_token_cost": 1.875e-05, + "cache_creation_input_token_cost_above_1hr": 3e-05, + "cache_read_input_token_cost": 1.5e-06, + "input_cost_per_token": 1.5e-05, + "litellm_provider": "anthropic", + "max_input_tokens": 200000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "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 + }, + "claude-opus-4-1-20250805": { + "cache_creation_input_token_cost": 1.875e-05, + "cache_creation_input_token_cost_above_1hr": 3e-05, + "cache_read_input_token_cost": 1.5e-06, + "input_cost_per_token": 1.5e-05, + "litellm_provider": "anthropic", + "max_input_tokens": 200000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "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 + }, + "claude-opus-4-20250514": { + "cache_creation_input_token_cost": 1.875e-05, + "cache_creation_input_token_cost_above_1hr": 3e-05, + "cache_read_input_token_cost": 1.5e-06, + "input_cost_per_token": 1.5e-05, + "litellm_provider": "anthropic", + "max_input_tokens": 200000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "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 + }, + "claude-sonnet-4-20250514": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_creation_input_token_cost_above_1hr": 6e-06, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "input_cost_per_token_above_200k_tokens": 6e-06, + "output_cost_per_token_above_200k_tokens": 2.25e-05, + "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, + "cache_read_input_token_cost_above_200k_tokens": 6e-07, + "litellm_provider": "anthropic", + "max_input_tokens": 1000000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "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 + }, + "cloudflare/@cf/meta/llama-2-7b-chat-fp16": { + "input_cost_per_token": 1.923e-06, + "litellm_provider": "cloudflare", + "max_input_tokens": 3072, + "max_output_tokens": 3072, + "max_tokens": 3072, + "mode": "chat", + "output_cost_per_token": 1.923e-06 + }, + "cloudflare/@cf/meta/llama-2-7b-chat-int8": { + "input_cost_per_token": 1.923e-06, + "litellm_provider": "cloudflare", + "max_input_tokens": 2048, + "max_output_tokens": 2048, + "max_tokens": 2048, + "mode": "chat", + "output_cost_per_token": 1.923e-06 + }, + "cloudflare/@cf/mistral/mistral-7b-instruct-v0.1": { + "input_cost_per_token": 1.923e-06, + "litellm_provider": "cloudflare", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.923e-06 + }, + "cloudflare/@hf/thebloke/codellama-7b-instruct-awq": { + "input_cost_per_token": 1.923e-06, + "litellm_provider": "cloudflare", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.923e-06 + }, + "code-bison": { + "input_cost_per_character": 2.5e-07, + "input_cost_per_token": 1.25e-07, + "litellm_provider": "vertex_ai-code-text-models", + "max_input_tokens": 6144, + "max_output_tokens": 1024, + "max_tokens": 1024, + "mode": "chat", + "output_cost_per_character": 5e-07, + "output_cost_per_token": 1.25e-07, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "supports_tool_choice": true + }, + "code-bison-32k@002": { + "input_cost_per_character": 2.5e-07, + "input_cost_per_token": 1.25e-07, + "litellm_provider": "vertex_ai-code-text-models", + "max_input_tokens": 6144, + "max_output_tokens": 1024, + "max_tokens": 1024, + "mode": "completion", + "output_cost_per_character": 5e-07, + "output_cost_per_token": 1.25e-07, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" + }, + "code-bison32k": { + "input_cost_per_character": 2.5e-07, + "input_cost_per_token": 1.25e-07, + "litellm_provider": "vertex_ai-code-text-models", + "max_input_tokens": 6144, + "max_output_tokens": 1024, + "max_tokens": 1024, + "mode": "completion", + "output_cost_per_character": 5e-07, + "output_cost_per_token": 1.25e-07, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" + }, + "code-bison@001": { + "input_cost_per_character": 2.5e-07, + "input_cost_per_token": 1.25e-07, + "litellm_provider": "vertex_ai-code-text-models", + "max_input_tokens": 6144, + "max_output_tokens": 1024, + "max_tokens": 1024, + "mode": "completion", + "output_cost_per_character": 5e-07, + "output_cost_per_token": 1.25e-07, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" + }, + "code-bison@002": { + "input_cost_per_character": 2.5e-07, + "input_cost_per_token": 1.25e-07, + "litellm_provider": "vertex_ai-code-text-models", + "max_input_tokens": 6144, + "max_output_tokens": 1024, + "max_tokens": 1024, + "mode": "completion", + "output_cost_per_character": 5e-07, + "output_cost_per_token": 1.25e-07, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" + }, + "code-gecko": { + "input_cost_per_token": 1.25e-07, + "litellm_provider": "vertex_ai-code-text-models", + "max_input_tokens": 2048, + "max_output_tokens": 64, + "max_tokens": 64, + "mode": "completion", + "output_cost_per_token": 1.25e-07, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" + }, + "code-gecko-latest": { + "input_cost_per_token": 1.25e-07, + "litellm_provider": "vertex_ai-code-text-models", + "max_input_tokens": 2048, + "max_output_tokens": 64, + "max_tokens": 64, + "mode": "completion", + "output_cost_per_token": 1.25e-07, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" + }, + "code-gecko@001": { + "input_cost_per_token": 1.25e-07, + "litellm_provider": "vertex_ai-code-text-models", + "max_input_tokens": 2048, + "max_output_tokens": 64, + "max_tokens": 64, + "mode": "completion", + "output_cost_per_token": 1.25e-07, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" + }, + "code-gecko@002": { + "input_cost_per_token": 1.25e-07, + "litellm_provider": "vertex_ai-code-text-models", + "max_input_tokens": 2048, + "max_output_tokens": 64, + "max_tokens": 64, + "mode": "completion", + "output_cost_per_token": 1.25e-07, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" + }, + "codechat-bison": { + "input_cost_per_character": 2.5e-07, + "input_cost_per_token": 1.25e-07, + "litellm_provider": "vertex_ai-code-chat-models", + "max_input_tokens": 6144, + "max_output_tokens": 1024, + "max_tokens": 1024, + "mode": "chat", + "output_cost_per_character": 5e-07, + "output_cost_per_token": 1.25e-07, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "supports_tool_choice": true + }, + "codechat-bison-32k": { + "input_cost_per_character": 2.5e-07, + "input_cost_per_token": 1.25e-07, + "litellm_provider": "vertex_ai-code-chat-models", + "max_input_tokens": 32000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_character": 5e-07, + "output_cost_per_token": 1.25e-07, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "supports_tool_choice": true + }, + "codechat-bison-32k@002": { + "input_cost_per_character": 2.5e-07, + "input_cost_per_token": 1.25e-07, + "litellm_provider": "vertex_ai-code-chat-models", + "max_input_tokens": 32000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_character": 5e-07, + "output_cost_per_token": 1.25e-07, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "supports_tool_choice": true + }, + "codechat-bison@001": { + "input_cost_per_character": 2.5e-07, + "input_cost_per_token": 1.25e-07, + "litellm_provider": "vertex_ai-code-chat-models", + "max_input_tokens": 6144, + "max_output_tokens": 1024, + "max_tokens": 1024, + "mode": "chat", + "output_cost_per_character": 5e-07, + "output_cost_per_token": 1.25e-07, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "supports_tool_choice": true + }, + "codechat-bison@002": { + "input_cost_per_character": 2.5e-07, + "input_cost_per_token": 1.25e-07, + "litellm_provider": "vertex_ai-code-chat-models", + "max_input_tokens": 6144, + "max_output_tokens": 1024, + "max_tokens": 1024, + "mode": "chat", + "output_cost_per_character": 5e-07, + "output_cost_per_token": 1.25e-07, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "supports_tool_choice": true + }, + "codechat-bison@latest": { + "input_cost_per_character": 2.5e-07, + "input_cost_per_token": 1.25e-07, + "litellm_provider": "vertex_ai-code-chat-models", + "max_input_tokens": 6144, + "max_output_tokens": 1024, + "max_tokens": 1024, + "mode": "chat", + "output_cost_per_character": 5e-07, + "output_cost_per_token": 1.25e-07, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "supports_tool_choice": true + }, + "codestral/codestral-2405": { + "input_cost_per_token": 0.0, + "litellm_provider": "codestral", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 0.0, + "source": "https://docs.mistral.ai/capabilities/code_generation/", + "supports_assistant_prefill": true, + "supports_tool_choice": true + }, + "codestral/codestral-latest": { + "input_cost_per_token": 0.0, + "litellm_provider": "codestral", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 0.0, + "source": "https://docs.mistral.ai/capabilities/code_generation/", + "supports_assistant_prefill": true, + "supports_tool_choice": true + }, + "codex-mini-latest": { + "cache_read_input_token_cost": 3.75e-07, + "input_cost_per_token": 1.5e-06, + "litellm_provider": "openai", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "responses", + "output_cost_per_token": 6e-06, + "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 + }, + "cohere.command-light-text-v14": { + "input_cost_per_token": 3e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 6e-07, + "supports_tool_choice": true + }, + "cohere.command-r-plus-v1:0": { + "input_cost_per_token": 3e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_tool_choice": true + }, + "cohere.command-r-v1:0": { + "input_cost_per_token": 5e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.5e-06, + "supports_tool_choice": true + }, + "cohere.command-text-v14": { + "input_cost_per_token": 1.5e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2e-06, + "supports_tool_choice": true + }, + "cohere.embed-english-v3": { + "input_cost_per_token": 1e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 512, + "max_tokens": 512, + "mode": "embedding", + "output_cost_per_token": 0.0, + "supports_embedding_image_input": true + }, + "cohere.embed-multilingual-v3": { + "input_cost_per_token": 1e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 512, + "max_tokens": 512, + "mode": "embedding", + "output_cost_per_token": 0.0, + "supports_embedding_image_input": true + }, + "cohere.rerank-v3-5:0": { + "input_cost_per_query": 0.002, + "input_cost_per_token": 0.0, + "litellm_provider": "bedrock", + "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": 0.0 + }, + "command": { + "input_cost_per_token": 1e-06, + "litellm_provider": "cohere", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "completion", + "output_cost_per_token": 2e-06 + }, + "command-a-03-2025": { + "input_cost_per_token": 2.5e-06, + "litellm_provider": "cohere_chat", + "max_input_tokens": 256000, + "max_output_tokens": 8000, + "max_tokens": 8000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "supports_function_calling": true, + "supports_tool_choice": true + }, + "command-light": { + "input_cost_per_token": 3e-07, + "litellm_provider": "cohere_chat", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 6e-07, + "supports_tool_choice": true + }, + "command-nightly": { + "input_cost_per_token": 1e-06, + "litellm_provider": "cohere", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "completion", + "output_cost_per_token": 2e-06 + }, + "command-r": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "cohere_chat", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 6e-07, + "supports_function_calling": true, + "supports_tool_choice": true + }, + "command-r-08-2024": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "cohere_chat", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 6e-07, + "supports_function_calling": true, + "supports_tool_choice": true + }, + "command-r-plus": { + "input_cost_per_token": 2.5e-06, + "litellm_provider": "cohere_chat", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1e-05, + "supports_function_calling": true, + "supports_tool_choice": true + }, + "command-r-plus-08-2024": { + "input_cost_per_token": 2.5e-06, + "litellm_provider": "cohere_chat", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1e-05, + "supports_function_calling": true, + "supports_tool_choice": true + }, + "command-r7b-12-2024": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "cohere_chat", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 3.75e-08, + "source": "https://docs.cohere.com/v2/docs/command-r7b", + "supports_function_calling": true, + "supports_tool_choice": true + }, + "computer-use-preview": { + "input_cost_per_token": 3e-06, + "litellm_provider": "azure", + "max_input_tokens": 8192, + "max_output_tokens": 1024, + "max_tokens": 1024, + "mode": "chat", + "output_cost_per_token": 1.2e-05, + "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 + }, + "deepseek-chat": { + "cache_read_input_token_cost": 6e-08, + "input_cost_per_token": 6e-07, + "litellm_provider": "deepseek", + "max_input_tokens": 131072, + "max_output_tokens": 8192, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.7e-06, + "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 + }, + "deepseek-reasoner": { + "cache_read_input_token_cost": 6e-08, + "input_cost_per_token": 6e-07, + "litellm_provider": "deepseek", + "max_input_tokens": 131072, + "max_output_tokens": 65536, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.7e-06, + "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 + }, + "dashscope/qwen-coder": { + "input_cost_per_token": 3e-07, + "litellm_provider": "dashscope", + "max_input_tokens": 1000000, + "max_output_tokens": 16384, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 1.5e-06, + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "dashscope/qwen-flash": { + "litellm_provider": "dashscope", + "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-08, + "output_cost_per_token": 4e-07, + "range": [ + 0, + 256000.0 + ] + }, + { + "input_cost_per_token": 2.5e-07, + "output_cost_per_token": 2e-06, + "range": [ + 256000.0, + 1000000.0 + ] + } + ] + }, + "dashscope/qwen-flash-2025-07-28": { + "litellm_provider": "dashscope", + "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-08, + "output_cost_per_token": 4e-07, + "range": [ + 0, + 256000.0 + ] + }, + { + "input_cost_per_token": 2.5e-07, + "output_cost_per_token": 2e-06, + "range": [ + 256000.0, + 1000000.0 + ] + } + ] + }, + "dashscope/qwen-max": { + "input_cost_per_token": 1.6e-06, + "litellm_provider": "dashscope", + "max_input_tokens": 30720, + "max_output_tokens": 8192, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 6.4e-06, + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "dashscope/qwen-plus": { + "input_cost_per_token": 4e-07, + "litellm_provider": "dashscope", + "max_input_tokens": 129024, + "max_output_tokens": 16384, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "dashscope/qwen-plus-2025-01-25": { + "input_cost_per_token": 4e-07, + "litellm_provider": "dashscope", + "max_input_tokens": 129024, + "max_output_tokens": 8192, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "dashscope/qwen-plus-2025-04-28": { + "input_cost_per_token": 4e-07, + "litellm_provider": "dashscope", + "max_input_tokens": 129024, + "max_output_tokens": 16384, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_reasoning_token": 4e-06, + "output_cost_per_token": 1.2e-06, + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "dashscope/qwen-plus-2025-07-14": { + "input_cost_per_token": 4e-07, + "litellm_provider": "dashscope", + "max_input_tokens": 129024, + "max_output_tokens": 16384, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_reasoning_token": 4e-06, + "output_cost_per_token": 1.2e-06, + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "dashscope/qwen-plus-2025-07-28": { + "litellm_provider": "dashscope", + "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-07, + "output_cost_per_reasoning_token": 4e-06, + "output_cost_per_token": 1.2e-06, + "range": [ + 0, + 256000.0 + ] + }, + { + "input_cost_per_token": 1.2e-06, + "output_cost_per_reasoning_token": 1.2e-05, + "output_cost_per_token": 3.6e-06, + "range": [ + 256000.0, + 1000000.0 + ] + } + ] + }, + "dashscope/qwen-plus-2025-09-11": { + "litellm_provider": "dashscope", + "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-07, + "output_cost_per_reasoning_token": 4e-06, + "output_cost_per_token": 1.2e-06, + "range": [ + 0, + 256000.0 + ] + }, + { + "input_cost_per_token": 1.2e-06, + "output_cost_per_reasoning_token": 1.2e-05, + "output_cost_per_token": 3.6e-06, + "range": [ + 256000.0, + 1000000.0 + ] + } + ] + }, + "dashscope/qwen-plus-latest": { + "litellm_provider": "dashscope", + "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-07, + "output_cost_per_reasoning_token": 4e-06, + "output_cost_per_token": 1.2e-06, + "range": [ + 0, + 256000.0 + ] + }, + { + "input_cost_per_token": 1.2e-06, + "output_cost_per_reasoning_token": 1.2e-05, + "output_cost_per_token": 3.6e-06, + "range": [ + 256000.0, + 1000000.0 + ] + } + ] + }, + "dashscope/qwen-turbo": { + "input_cost_per_token": 5e-08, + "litellm_provider": "dashscope", + "max_input_tokens": 129024, + "max_output_tokens": 16384, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_reasoning_token": 5e-07, + "output_cost_per_token": 2e-07, + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "dashscope/qwen-turbo-2024-11-01": { + "input_cost_per_token": 5e-08, + "litellm_provider": "dashscope", + "max_input_tokens": 1000000, + "max_output_tokens": 8192, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 2e-07, + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "dashscope/qwen-turbo-2025-04-28": { + "input_cost_per_token": 5e-08, + "litellm_provider": "dashscope", + "max_input_tokens": 1000000, + "max_output_tokens": 16384, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_reasoning_token": 5e-07, + "output_cost_per_token": 2e-07, + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "dashscope/qwen-turbo-latest": { + "input_cost_per_token": 5e-08, + "litellm_provider": "dashscope", + "max_input_tokens": 1000000, + "max_output_tokens": 16384, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_reasoning_token": 5e-07, + "output_cost_per_token": 2e-07, + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "dashscope/qwen3-30b-a3b": { + "litellm_provider": "dashscope", + "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 + }, + "dashscope/qwen3-coder-flash": { + "litellm_provider": "dashscope", + "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-08, + "input_cost_per_token": 3e-07, + "output_cost_per_token": 1.5e-06, + "range": [ + 0, + 32000.0 + ] + }, + { + "cache_read_input_token_cost": 1.2e-07, + "input_cost_per_token": 5e-07, + "output_cost_per_token": 2.5e-06, + "range": [ + 32000.0, + 128000.0 + ] + }, + { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 8e-07, + "output_cost_per_token": 4e-06, + "range": [ + 128000.0, + 256000.0 + ] + }, + { + "cache_read_input_token_cost": 4e-07, + "input_cost_per_token": 1.6e-06, + "output_cost_per_token": 9.6e-06, + "range": [ + 256000.0, + 1000000.0 + ] + } + ] + }, + "dashscope/qwen3-coder-flash-2025-07-28": { + "litellm_provider": "dashscope", + "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-07, + "output_cost_per_token": 1.5e-06, + "range": [ + 0, + 32000.0 + ] + }, + { + "input_cost_per_token": 5e-07, + "output_cost_per_token": 2.5e-06, + "range": [ + 32000.0, + 128000.0 + ] + }, + { + "input_cost_per_token": 8e-07, + "output_cost_per_token": 4e-06, + "range": [ + 128000.0, + 256000.0 + ] + }, + { + "input_cost_per_token": 1.6e-06, + "output_cost_per_token": 9.6e-06, + "range": [ + 256000.0, + 1000000.0 + ] + } + ] + }, + "dashscope/qwen3-coder-plus": { + "litellm_provider": "dashscope", + "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-07, + "input_cost_per_token": 1e-06, + "output_cost_per_token": 5e-06, + "range": [ + 0, + 32000.0 + ] + }, + { + "cache_read_input_token_cost": 1.8e-07, + "input_cost_per_token": 1.8e-06, + "output_cost_per_token": 9e-06, + "range": [ + 32000.0, + 128000.0 + ] + }, + { + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "output_cost_per_token": 1.5e-05, + "range": [ + 128000.0, + 256000.0 + ] + }, + { + "cache_read_input_token_cost": 6e-07, + "input_cost_per_token": 6e-06, + "output_cost_per_token": 6e-05, + "range": [ + 256000.0, + 1000000.0 + ] + } + ] + }, + "dashscope/qwen3-coder-plus-2025-07-22": { + "litellm_provider": "dashscope", + "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": 1e-06, + "output_cost_per_token": 5e-06, + "range": [ + 0, + 32000.0 + ] + }, + { + "input_cost_per_token": 1.8e-06, + "output_cost_per_token": 9e-06, + "range": [ + 32000.0, + 128000.0 + ] + }, + { + "input_cost_per_token": 3e-06, + "output_cost_per_token": 1.5e-05, + "range": [ + 128000.0, + 256000.0 + ] + }, + { + "input_cost_per_token": 6e-06, + "output_cost_per_token": 6e-05, + "range": [ + 256000.0, + 1000000.0 + ] + } + ] + }, + "dashscope/qwen3-max-preview": { + "litellm_provider": "dashscope", + "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": 1.2e-06, + "output_cost_per_token": 6e-06, + "range": [ + 0, + 32000.0 + ] + }, + { + "input_cost_per_token": 2.4e-06, + "output_cost_per_token": 1.2e-05, + "range": [ + 32000.0, + 128000.0 + ] + }, + { + "input_cost_per_token": 3e-06, + "output_cost_per_token": 1.5e-05, + "range": [ + 128000.0, + 252000.0 + ] + } + ] + }, + "dashscope/qwq-plus": { + "input_cost_per_token": 8e-07, + "litellm_provider": "dashscope", + "max_input_tokens": 98304, + "max_output_tokens": 8192, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.4e-06, + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "databricks/databricks-bge-large-en": { + "input_cost_per_token": 1.0003e-07, + "input_dbu_cost_per_token": 1.429e-06, + "litellm_provider": "databricks", + "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": 0.0, + "output_dbu_cost_per_token": 0.0, + "output_vector_size": 1024, + "source": "https://www.databricks.com/product/pricing/foundation-model-serving" + }, + "databricks/databricks-claude-3-7-sonnet": { + "input_cost_per_token": 2.5e-06, + "input_dbu_cost_per_token": 3.571e-05, + "litellm_provider": "databricks", + "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": 1.7857e-05, + "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 + }, + "databricks/databricks-gte-large-en": { + "input_cost_per_token": 1.2999e-07, + "input_dbu_cost_per_token": 1.857e-06, + "litellm_provider": "databricks", + "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": 0.0, + "output_dbu_cost_per_token": 0.0, + "output_vector_size": 1024, + "source": "https://www.databricks.com/product/pricing/foundation-model-serving" + }, + "databricks/databricks-llama-2-70b-chat": { + "input_cost_per_token": 5.0001e-07, + "input_dbu_cost_per_token": 7.143e-06, + "litellm_provider": "databricks", + "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": 1.5e-06, + "output_dbu_cost_per_token": 2.1429e-05, + "source": "https://www.databricks.com/product/pricing/foundation-model-serving", + "supports_tool_choice": true + }, + "databricks/databricks-llama-4-maverick": { + "input_cost_per_token": 5e-06, + "input_dbu_cost_per_token": 7.143e-05, + "litellm_provider": "databricks", + "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": 1.5e-05, + "output_dbu_cost_per_token": 0.00021429, + "source": "https://www.databricks.com/product/pricing/foundation-model-serving", + "supports_tool_choice": true + }, + "databricks/databricks-meta-llama-3-1-405b-instruct": { + "input_cost_per_token": 5e-06, + "input_dbu_cost_per_token": 7.1429e-05, + "litellm_provider": "databricks", + "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": 1.500002e-05, + "output_db_cost_per_token": 0.000214286, + "source": "https://www.databricks.com/product/pricing/foundation-model-serving", + "supports_tool_choice": true + }, + "databricks/databricks-meta-llama-3-3-70b-instruct": { + "input_cost_per_token": 1.00002e-06, + "input_dbu_cost_per_token": 1.4286e-05, + "litellm_provider": "databricks", + "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": 2.99999e-06, + "output_dbu_cost_per_token": 4.2857e-05, + "source": "https://www.databricks.com/product/pricing/foundation-model-serving", + "supports_tool_choice": true + }, + "databricks/databricks-meta-llama-3-70b-instruct": { + "input_cost_per_token": 1.00002e-06, + "input_dbu_cost_per_token": 1.4286e-05, + "litellm_provider": "databricks", + "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": 2.99999e-06, + "output_dbu_cost_per_token": 4.2857e-05, + "source": "https://www.databricks.com/product/pricing/foundation-model-serving", + "supports_tool_choice": true + }, + "databricks/databricks-mixtral-8x7b-instruct": { + "input_cost_per_token": 5.0001e-07, + "input_dbu_cost_per_token": 7.143e-06, + "litellm_provider": "databricks", + "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-07, + "output_dbu_cost_per_token": 1.4286e-05, + "source": "https://www.databricks.com/product/pricing/foundation-model-serving", + "supports_tool_choice": true + }, + "databricks/databricks-mpt-30b-instruct": { + "input_cost_per_token": 9.9902e-07, + "input_dbu_cost_per_token": 1.4286e-05, + "litellm_provider": "databricks", + "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-07, + "output_dbu_cost_per_token": 1.4286e-05, + "source": "https://www.databricks.com/product/pricing/foundation-model-serving", + "supports_tool_choice": true + }, + "databricks/databricks-mpt-7b-instruct": { + "input_cost_per_token": 5.0001e-07, + "input_dbu_cost_per_token": 7.143e-06, + "litellm_provider": "databricks", + "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": 0.0, + "output_dbu_cost_per_token": 0.0, + "source": "https://www.databricks.com/product/pricing/foundation-model-serving", + "supports_tool_choice": true + }, + "davinci-002": { + "input_cost_per_token": 2e-06, + "litellm_provider": "text-completion-openai", + "max_input_tokens": 16384, + "max_output_tokens": 4096, + "max_tokens": 16384, + "mode": "completion", + "output_cost_per_token": 2e-06 + }, + "deepgram/base": { + "input_cost_per_second": 0.00020833, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0125/60 seconds = $0.00020833 per second", + "original_pricing_per_minute": 0.0125 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/base-conversationalai": { + "input_cost_per_second": 0.00020833, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0125/60 seconds = $0.00020833 per second", + "original_pricing_per_minute": 0.0125 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/base-finance": { + "input_cost_per_second": 0.00020833, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0125/60 seconds = $0.00020833 per second", + "original_pricing_per_minute": 0.0125 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/base-general": { + "input_cost_per_second": 0.00020833, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0125/60 seconds = $0.00020833 per second", + "original_pricing_per_minute": 0.0125 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/base-meeting": { + "input_cost_per_second": 0.00020833, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0125/60 seconds = $0.00020833 per second", + "original_pricing_per_minute": 0.0125 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/base-phonecall": { + "input_cost_per_second": 0.00020833, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0125/60 seconds = $0.00020833 per second", + "original_pricing_per_minute": 0.0125 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/base-video": { + "input_cost_per_second": 0.00020833, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0125/60 seconds = $0.00020833 per second", + "original_pricing_per_minute": 0.0125 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/base-voicemail": { + "input_cost_per_second": 0.00020833, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0125/60 seconds = $0.00020833 per second", + "original_pricing_per_minute": 0.0125 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/enhanced": { + "input_cost_per_second": 0.00024167, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0145/60 seconds = $0.00024167 per second", + "original_pricing_per_minute": 0.0145 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/enhanced-finance": { + "input_cost_per_second": 0.00024167, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0145/60 seconds = $0.00024167 per second", + "original_pricing_per_minute": 0.0145 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/enhanced-general": { + "input_cost_per_second": 0.00024167, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0145/60 seconds = $0.00024167 per second", + "original_pricing_per_minute": 0.0145 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/enhanced-meeting": { + "input_cost_per_second": 0.00024167, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0145/60 seconds = $0.00024167 per second", + "original_pricing_per_minute": 0.0145 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/enhanced-phonecall": { + "input_cost_per_second": 0.00024167, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0145/60 seconds = $0.00024167 per second", + "original_pricing_per_minute": 0.0145 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/nova": { + "input_cost_per_second": 7.167e-05, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0043/60 seconds = $0.00007167 per second", + "original_pricing_per_minute": 0.0043 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/nova-2": { + "input_cost_per_second": 7.167e-05, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0043/60 seconds = $0.00007167 per second", + "original_pricing_per_minute": 0.0043 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/nova-2-atc": { + "input_cost_per_second": 7.167e-05, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0043/60 seconds = $0.00007167 per second", + "original_pricing_per_minute": 0.0043 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/nova-2-automotive": { + "input_cost_per_second": 7.167e-05, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0043/60 seconds = $0.00007167 per second", + "original_pricing_per_minute": 0.0043 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/nova-2-conversationalai": { + "input_cost_per_second": 7.167e-05, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0043/60 seconds = $0.00007167 per second", + "original_pricing_per_minute": 0.0043 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/nova-2-drivethru": { + "input_cost_per_second": 7.167e-05, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0043/60 seconds = $0.00007167 per second", + "original_pricing_per_minute": 0.0043 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/nova-2-finance": { + "input_cost_per_second": 7.167e-05, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0043/60 seconds = $0.00007167 per second", + "original_pricing_per_minute": 0.0043 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/nova-2-general": { + "input_cost_per_second": 7.167e-05, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0043/60 seconds = $0.00007167 per second", + "original_pricing_per_minute": 0.0043 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/nova-2-meeting": { + "input_cost_per_second": 7.167e-05, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0043/60 seconds = $0.00007167 per second", + "original_pricing_per_minute": 0.0043 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/nova-2-phonecall": { + "input_cost_per_second": 7.167e-05, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0043/60 seconds = $0.00007167 per second", + "original_pricing_per_minute": 0.0043 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/nova-2-video": { + "input_cost_per_second": 7.167e-05, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0043/60 seconds = $0.00007167 per second", + "original_pricing_per_minute": 0.0043 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/nova-2-voicemail": { + "input_cost_per_second": 7.167e-05, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0043/60 seconds = $0.00007167 per second", + "original_pricing_per_minute": 0.0043 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/nova-3": { + "input_cost_per_second": 7.167e-05, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0043/60 seconds = $0.00007167 per second", + "original_pricing_per_minute": 0.0043 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/nova-3-general": { + "input_cost_per_second": 7.167e-05, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0043/60 seconds = $0.00007167 per second", + "original_pricing_per_minute": 0.0043 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/nova-3-medical": { + "input_cost_per_second": 8.667e-05, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0052/60 seconds = $0.00008667 per second (multilingual)", + "original_pricing_per_minute": 0.0052 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/nova-general": { + "input_cost_per_second": 7.167e-05, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0043/60 seconds = $0.00007167 per second", + "original_pricing_per_minute": 0.0043 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/nova-phonecall": { + "input_cost_per_second": 7.167e-05, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0043/60 seconds = $0.00007167 per second", + "original_pricing_per_minute": 0.0043 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/whisper": { + "input_cost_per_second": 0.0001, + "litellm_provider": "deepgram", + "metadata": { + "notes": "Deepgram's hosted OpenAI Whisper models - pricing may differ from native Deepgram models" + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/whisper-base": { + "input_cost_per_second": 0.0001, + "litellm_provider": "deepgram", + "metadata": { + "notes": "Deepgram's hosted OpenAI Whisper models - pricing may differ from native Deepgram models" + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/whisper-large": { + "input_cost_per_second": 0.0001, + "litellm_provider": "deepgram", + "metadata": { + "notes": "Deepgram's hosted OpenAI Whisper models - pricing may differ from native Deepgram models" + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/whisper-medium": { + "input_cost_per_second": 0.0001, + "litellm_provider": "deepgram", + "metadata": { + "notes": "Deepgram's hosted OpenAI Whisper models - pricing may differ from native Deepgram models" + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/whisper-small": { + "input_cost_per_second": 0.0001, + "litellm_provider": "deepgram", + "metadata": { + "notes": "Deepgram's hosted OpenAI Whisper models - pricing may differ from native Deepgram models" + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/whisper-tiny": { + "input_cost_per_second": 0.0001, + "litellm_provider": "deepgram", + "metadata": { + "notes": "Deepgram's hosted OpenAI Whisper models - pricing may differ from native Deepgram models" + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepinfra/Gryphe/MythoMax-L2-13b": { + "input_cost_per_token": 7.2e-08, + "litellm_provider": "deepinfra", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 7.2e-08, + "supports_tool_choice": true + }, + "deepinfra/NousResearch/Hermes-3-Llama-3.1-405B": { + "input_cost_per_token": 7e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 8e-07, + "supports_tool_choice": true + }, + "deepinfra/NousResearch/Hermes-3-Llama-3.1-70B": { + "input_cost_per_token": 1e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.8e-07, + "supports_tool_choice": false + }, + "deepinfra/Qwen/QwQ-32B": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4e-07, + "supports_tool_choice": true + }, + "deepinfra/Qwen/Qwen2.5-72B-Instruct": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 3.9e-07, + "supports_tool_choice": true + }, + "deepinfra/Qwen/Qwen2.5-7B-Instruct": { + "input_cost_per_token": 4e-08, + "litellm_provider": "deepinfra", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 1e-07, + "supports_tool_choice": false + }, + "deepinfra/Qwen/Qwen2.5-VL-32B-Instruct": { + "input_cost_per_token": 2e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-07, + "supports_tool_choice": true + }, + "deepinfra/Qwen/Qwen3-14B": { + "input_cost_per_token": 6e-08, + "litellm_provider": "deepinfra", + "max_input_tokens": 40960, + "max_output_tokens": 40960, + "max_tokens": 40960, + "mode": "chat", + "output_cost_per_token": 2.4e-07, + "supports_tool_choice": true + }, + "deepinfra/Qwen/Qwen3-235B-A22B": { + "input_cost_per_token": 1.3e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 40960, + "max_output_tokens": 40960, + "max_tokens": 40960, + "mode": "chat", + "output_cost_per_token": 6e-07, + "supports_tool_choice": true + }, + "deepinfra/Qwen/Qwen3-235B-A22B-Instruct-2507": { + "input_cost_per_token": 1.3e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 6e-07, + "supports_tool_choice": true + }, + "deepinfra/Qwen/Qwen3-235B-A22B-Thinking-2507": { + "input_cost_per_token": 1.3e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 6e-07, + "supports_tool_choice": true + }, + "deepinfra/Qwen/Qwen3-30B-A3B": { + "input_cost_per_token": 8e-08, + "litellm_provider": "deepinfra", + "max_input_tokens": 40960, + "max_output_tokens": 40960, + "max_tokens": 40960, + "mode": "chat", + "output_cost_per_token": 2.9e-07, + "supports_tool_choice": true + }, + "deepinfra/Qwen/Qwen3-32B": { + "input_cost_per_token": 1e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 40960, + "max_output_tokens": 40960, + "max_tokens": 40960, + "mode": "chat", + "output_cost_per_token": 3e-07, + "supports_tool_choice": true + }, + "deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct": { + "input_cost_per_token": 4e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 1.6e-06, + "supports_tool_choice": true + }, + "deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo": { + "cache_read_input_token_cost": 2.4e-07, + "input_cost_per_token": 3e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "supports_tool_choice": true + }, + "deepinfra/Sao10K/L3-8B-Lunaris-v1-Turbo": { + "input_cost_per_token": 2e-08, + "litellm_provider": "deepinfra", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 5e-08, + "supports_tool_choice": false + }, + "deepinfra/Sao10K/L3.1-70B-Euryale-v2.2": { + "input_cost_per_token": 6.5e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 7.5e-07, + "supports_tool_choice": false + }, + "deepinfra/Sao10K/L3.3-70B-Euryale-v2.3": { + "input_cost_per_token": 6.5e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 7.5e-07, + "supports_tool_choice": false + }, + "deepinfra/allenai/olmOCR-7B-0725-FP8": { + "input_cost_per_token": 2.7e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.5e-06, + "supports_tool_choice": false + }, + "deepinfra/anthropic/claude-3-7-sonnet-latest": { + "cache_read_input_token_cost": 3.3e-07, + "input_cost_per_token": 3.3e-06, + "litellm_provider": "deepinfra", + "max_input_tokens": 200000, + "max_output_tokens": 200000, + "max_tokens": 200000, + "mode": "chat", + "output_cost_per_token": 1.65e-05, + "supports_tool_choice": true + }, + "deepinfra/anthropic/claude-4-opus": { + "input_cost_per_token": 1.65e-05, + "litellm_provider": "deepinfra", + "max_input_tokens": 200000, + "max_output_tokens": 200000, + "max_tokens": 200000, + "mode": "chat", + "output_cost_per_token": 8.25e-05, + "supports_tool_choice": true + }, + "deepinfra/anthropic/claude-4-sonnet": { + "input_cost_per_token": 3.3e-06, + "litellm_provider": "deepinfra", + "max_input_tokens": 200000, + "max_output_tokens": 200000, + "max_tokens": 200000, + "mode": "chat", + "output_cost_per_token": 1.65e-05, + "supports_tool_choice": true + }, + "deepinfra/deepseek-ai/DeepSeek-R1": { + "input_cost_per_token": 7e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 163840, + "max_output_tokens": 163840, + "max_tokens": 163840, + "mode": "chat", + "output_cost_per_token": 2.4e-06, + "supports_tool_choice": true + }, + "deepinfra/deepseek-ai/DeepSeek-R1-0528": { + "cache_read_input_token_cost": 4e-07, + "input_cost_per_token": 5e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 163840, + "max_output_tokens": 163840, + "max_tokens": 163840, + "mode": "chat", + "output_cost_per_token": 2.15e-06, + "supports_tool_choice": true + }, + "deepinfra/deepseek-ai/DeepSeek-R1-0528-Turbo": { + "input_cost_per_token": 1e-06, + "litellm_provider": "deepinfra", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 3e-06, + "supports_tool_choice": true + }, + "deepinfra/deepseek-ai/DeepSeek-R1-Distill-Llama-70B": { + "input_cost_per_token": 1e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4e-07, + "supports_tool_choice": false + }, + "deepinfra/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B": { + "input_cost_per_token": 7.5e-08, + "litellm_provider": "deepinfra", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.5e-07, + "supports_tool_choice": true + }, + "deepinfra/deepseek-ai/DeepSeek-R1-Turbo": { + "input_cost_per_token": 1e-06, + "litellm_provider": "deepinfra", + "max_input_tokens": 40960, + "max_output_tokens": 40960, + "max_tokens": 40960, + "mode": "chat", + "output_cost_per_token": 3e-06, + "supports_tool_choice": true + }, + "deepinfra/deepseek-ai/DeepSeek-V3": { + "input_cost_per_token": 3.8e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 163840, + "max_output_tokens": 163840, + "max_tokens": 163840, + "mode": "chat", + "output_cost_per_token": 8.9e-07, + "supports_tool_choice": true + }, + "deepinfra/deepseek-ai/DeepSeek-V3-0324": { + "cache_read_input_token_cost": 2.24e-07, + "input_cost_per_token": 2.8e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 163840, + "max_output_tokens": 163840, + "max_tokens": 163840, + "mode": "chat", + "output_cost_per_token": 8.8e-07, + "supports_tool_choice": true + }, + "deepinfra/deepseek-ai/DeepSeek-V3.1": { + "cache_read_input_token_cost": 2.16e-07, + "input_cost_per_token": 2.7e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 163840, + "max_output_tokens": 163840, + "max_tokens": 163840, + "mode": "chat", + "output_cost_per_token": 1e-06, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "deepinfra/google/gemini-2.0-flash-001": { + "input_cost_per_token": 1e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 4e-07, + "supports_tool_choice": true + }, + "deepinfra/google/gemini-2.5-flash": { + "input_cost_per_token": 2.1e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 1.75e-06, + "supports_tool_choice": true + }, + "deepinfra/google/gemini-2.5-pro": { + "input_cost_per_token": 8.75e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 7e-06, + "supports_tool_choice": true + }, + "deepinfra/google/gemma-3-12b-it": { + "input_cost_per_token": 5e-08, + "litellm_provider": "deepinfra", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1e-07, + "supports_tool_choice": true + }, + "deepinfra/google/gemma-3-27b-it": { + "input_cost_per_token": 9e-08, + "litellm_provider": "deepinfra", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.7e-07, + "supports_tool_choice": true + }, + "deepinfra/google/gemma-3-4b-it": { + "input_cost_per_token": 4e-08, + "litellm_provider": "deepinfra", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 8e-08, + "supports_tool_choice": true + }, + "deepinfra/meta-llama/Llama-3.2-11B-Vision-Instruct": { + "input_cost_per_token": 4.9e-08, + "litellm_provider": "deepinfra", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4.9e-08, + "supports_tool_choice": false + }, + "deepinfra/meta-llama/Llama-3.2-3B-Instruct": { + "input_cost_per_token": 1.2e-08, + "litellm_provider": "deepinfra", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.4e-08, + "supports_tool_choice": true + }, + "deepinfra/meta-llama/Llama-3.3-70B-Instruct": { + "input_cost_per_token": 2.3e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4e-07, + "supports_tool_choice": true + }, + "deepinfra/meta-llama/Llama-3.3-70B-Instruct-Turbo": { + "input_cost_per_token": 3.8e-08, + "litellm_provider": "deepinfra", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.2e-07, + "supports_tool_choice": true + }, + "deepinfra/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 6e-07, + "supports_tool_choice": true + }, + "deepinfra/meta-llama/Llama-4-Scout-17B-16E-Instruct": { + "input_cost_per_token": 8e-08, + "litellm_provider": "deepinfra", + "max_input_tokens": 327680, + "max_output_tokens": 327680, + "max_tokens": 327680, + "mode": "chat", + "output_cost_per_token": 3e-07, + "supports_tool_choice": true + }, + "deepinfra/meta-llama/Llama-Guard-3-8B": { + "input_cost_per_token": 5.5e-08, + "litellm_provider": "deepinfra", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 5.5e-08, + "supports_tool_choice": false + }, + "deepinfra/meta-llama/Llama-Guard-4-12B": { + "input_cost_per_token": 1.8e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 163840, + "max_output_tokens": 163840, + "max_tokens": 163840, + "mode": "chat", + "output_cost_per_token": 1.8e-07, + "supports_tool_choice": false + }, + "deepinfra/meta-llama/Meta-Llama-3-8B-Instruct": { + "input_cost_per_token": 3e-08, + "litellm_provider": "deepinfra", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 6e-08, + "supports_tool_choice": true + }, + "deepinfra/meta-llama/Meta-Llama-3.1-70B-Instruct": { + "input_cost_per_token": 2.3e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4e-07, + "supports_tool_choice": true + }, + "deepinfra/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo": { + "input_cost_per_token": 1e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.8e-07, + "supports_tool_choice": true + }, + "deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct": { + "input_cost_per_token": 3e-08, + "litellm_provider": "deepinfra", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 5e-08, + "supports_tool_choice": true + }, + "deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo": { + "input_cost_per_token": 1.5e-08, + "litellm_provider": "deepinfra", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2e-08, + "supports_tool_choice": true + }, + "deepinfra/microsoft/WizardLM-2-8x22B": { + "input_cost_per_token": 4.8e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 65536, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 4.8e-07, + "supports_tool_choice": false + }, + "deepinfra/microsoft/phi-4": { + "input_cost_per_token": 7e-08, + "litellm_provider": "deepinfra", + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.4e-07, + "supports_tool_choice": true + }, + "deepinfra/mistralai/Mistral-Nemo-Instruct-2407": { + "input_cost_per_token": 2e-08, + "litellm_provider": "deepinfra", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4e-08, + "supports_tool_choice": true + }, + "deepinfra/mistralai/Mistral-Small-24B-Instruct-2501": { + "input_cost_per_token": 5e-08, + "litellm_provider": "deepinfra", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 8e-08, + "supports_tool_choice": true + }, + "deepinfra/mistralai/Mistral-Small-3.2-24B-Instruct-2506": { + "input_cost_per_token": 5e-08, + "litellm_provider": "deepinfra", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-07, + "supports_tool_choice": true + }, + "deepinfra/mistralai/Mixtral-8x7B-Instruct-v0.1": { + "input_cost_per_token": 8e-08, + "litellm_provider": "deepinfra", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 2.4e-07, + "supports_tool_choice": true + }, + "deepinfra/moonshotai/Kimi-K2-Instruct": { + "input_cost_per_token": 5e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2e-06, + "supports_tool_choice": true + }, + "deepinfra/nvidia/Llama-3.1-Nemotron-70B-Instruct": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 3e-07, + "supports_tool_choice": true + }, + "deepinfra/openai/gpt-oss-120b": { + "input_cost_per_token": 9e-08, + "litellm_provider": "deepinfra", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4.5e-07, + "supports_tool_choice": true + }, + "deepinfra/openai/gpt-oss-20b": { + "input_cost_per_token": 4e-08, + "litellm_provider": "deepinfra", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.6e-07, + "supports_tool_choice": true + }, + "deepinfra/zai-org/GLM-4.5": { + "input_cost_per_token": 5.5e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2e-06, + "supports_tool_choice": true + }, + "deepinfra/zai-org/GLM-4.5-Air": { + "input_cost_per_token": 2e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.1e-06, + "supports_tool_choice": true + }, + "deepseek/deepseek-chat": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 7e-08, + "input_cost_per_token": 2.7e-07, + "input_cost_per_token_cache_hit": 7e-08, + "litellm_provider": "deepseek", + "max_input_tokens": 65536, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.1e-06, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_tool_choice": true + }, + "deepseek/deepseek-coder": { + "input_cost_per_token": 1.4e-07, + "input_cost_per_token_cache_hit": 1.4e-08, + "litellm_provider": "deepseek", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2.8e-07, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_tool_choice": true + }, + "deepseek/deepseek-r1": { + "input_cost_per_token": 5.5e-07, + "input_cost_per_token_cache_hit": 1.4e-07, + "litellm_provider": "deepseek", + "max_input_tokens": 65536, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2.19e-06, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "deepseek/deepseek-reasoner": { + "input_cost_per_token": 5.5e-07, + "input_cost_per_token_cache_hit": 1.4e-07, + "litellm_provider": "deepseek", + "max_input_tokens": 65536, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2.19e-06, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "deepseek/deepseek-v3": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 7e-08, + "input_cost_per_token": 2.7e-07, + "input_cost_per_token_cache_hit": 7e-08, + "litellm_provider": "deepseek", + "max_input_tokens": 65536, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.1e-06, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_tool_choice": true + }, + "deepseek.v3-v1:0": { + "input_cost_per_token": 5.8e-07, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 163840, + "max_output_tokens": 81920, + "max_tokens": 163840, + "mode": "chat", + "output_cost_per_token": 1.68e-06, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "dolphin": { + "input_cost_per_token": 5e-07, + "litellm_provider": "nlp_cloud", + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "completion", + "output_cost_per_token": 5e-07 + }, + "doubao-embedding": { + "input_cost_per_token": 0.0, + "litellm_provider": "volcengine", + "max_input_tokens": 4096, + "max_tokens": 4096, + "metadata": { + "notes": "Volcengine Doubao embedding model - standard version with 2560 dimensions" + }, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 2560 + }, + "doubao-embedding-large": { + "input_cost_per_token": 0.0, + "litellm_provider": "volcengine", + "max_input_tokens": 4096, + "max_tokens": 4096, + "metadata": { + "notes": "Volcengine Doubao embedding model - large version with 2048 dimensions" + }, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 2048 + }, + "doubao-embedding-large-text-240915": { + "input_cost_per_token": 0.0, + "litellm_provider": "volcengine", + "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": 0.0, + "output_vector_size": 4096 + }, + "doubao-embedding-large-text-250515": { + "input_cost_per_token": 0.0, + "litellm_provider": "volcengine", + "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": 0.0, + "output_vector_size": 2048 + }, + "doubao-embedding-text-240715": { + "input_cost_per_token": 0.0, + "litellm_provider": "volcengine", + "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": 0.0, + "output_vector_size": 2560 + }, + "elevenlabs/scribe_v1": { + "input_cost_per_second": 6.11e-05, + "litellm_provider": "elevenlabs", + "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": 0.0, + "source": "https://elevenlabs.io/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "elevenlabs/scribe_v1_experimental": { + "input_cost_per_second": 6.11e-05, + "litellm_provider": "elevenlabs", + "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": 0.0, + "source": "https://elevenlabs.io/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "embed-english-light-v2.0": { + "input_cost_per_token": 1e-07, + "litellm_provider": "cohere", + "max_input_tokens": 1024, + "max_tokens": 1024, + "mode": "embedding", + "output_cost_per_token": 0.0 + }, + "embed-english-light-v3.0": { + "input_cost_per_token": 1e-07, + "litellm_provider": "cohere", + "max_input_tokens": 1024, + "max_tokens": 1024, + "mode": "embedding", + "output_cost_per_token": 0.0 + }, + "embed-english-v2.0": { + "input_cost_per_token": 1e-07, + "litellm_provider": "cohere", + "max_input_tokens": 4096, + "max_tokens": 4096, + "mode": "embedding", + "output_cost_per_token": 0.0 + }, + "embed-english-v3.0": { + "input_cost_per_image": 0.0001, + "input_cost_per_token": 1e-07, + "litellm_provider": "cohere", + "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": 0.0, + "supports_embedding_image_input": true, + "supports_image_input": true + }, + "embed-multilingual-v2.0": { + "input_cost_per_token": 1e-07, + "litellm_provider": "cohere", + "max_input_tokens": 768, + "max_tokens": 768, + "mode": "embedding", + "output_cost_per_token": 0.0 + }, + "embed-multilingual-v3.0": { + "input_cost_per_token": 1e-07, + "litellm_provider": "cohere", + "max_input_tokens": 1024, + "max_tokens": 1024, + "mode": "embedding", + "output_cost_per_token": 0.0, + "supports_embedding_image_input": true + }, + "eu.amazon.nova-lite-v1:0": { + "input_cost_per_token": 7.8e-08, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 300000, + "max_output_tokens": 10000, + "max_tokens": 10000, + "mode": "chat", + "output_cost_per_token": 3.12e-07, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_vision": true + }, + "eu.amazon.nova-micro-v1:0": { + "input_cost_per_token": 4.6e-08, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 128000, + "max_output_tokens": 10000, + "max_tokens": 10000, + "mode": "chat", + "output_cost_per_token": 1.84e-07, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true + }, + "eu.amazon.nova-pro-v1:0": { + "input_cost_per_token": 1.05e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 300000, + "max_output_tokens": 10000, + "max_tokens": 10000, + "mode": "chat", + "output_cost_per_token": 4.2e-06, + "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 + }, + "eu.anthropic.claude-3-5-haiku-20241022-v1:0": { + "input_cost_per_token": 2.5e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.25e-06, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "eu.anthropic.claude-3-5-sonnet-20240620-v1:0": { + "input_cost_per_token": 3e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "eu.anthropic.claude-3-5-sonnet-20241022-v2:0": { + "input_cost_per_token": 3e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "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 + }, + "eu.anthropic.claude-3-7-sonnet-20250219-v1:0": { + "input_cost_per_token": 3e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "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 + }, + "eu.anthropic.claude-3-haiku-20240307-v1:0": { + "input_cost_per_token": 2.5e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.25e-06, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "eu.anthropic.claude-3-opus-20240229-v1:0": { + "input_cost_per_token": 1.5e-05, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "eu.anthropic.claude-3-sonnet-20240229-v1:0": { + "input_cost_per_token": 3e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "eu.anthropic.claude-opus-4-1-20250805-v1:0": { + "cache_creation_input_token_cost": 1.875e-05, + "cache_read_input_token_cost": 1.5e-06, + "input_cost_per_token": 1.5e-05, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 200000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "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 + }, + "eu.anthropic.claude-opus-4-20250514-v1:0": { + "cache_creation_input_token_cost": 1.875e-05, + "cache_read_input_token_cost": 1.5e-06, + "input_cost_per_token": 1.5e-05, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 200000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "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 + }, + "eu.anthropic.claude-sonnet-4-20250514-v1:0": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "input_cost_per_token_above_200k_tokens": 6e-06, + "output_cost_per_token_above_200k_tokens": 2.25e-05, + "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, + "cache_read_input_token_cost_above_200k_tokens": 6e-07, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "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 + }, + "eu.meta.llama3-2-1b-instruct-v1:0": { + "input_cost_per_token": 1.3e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.3e-07, + "supports_function_calling": true, + "supports_tool_choice": false + }, + "eu.meta.llama3-2-3b-instruct-v1:0": { + "input_cost_per_token": 1.9e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.9e-07, + "supports_function_calling": true, + "supports_tool_choice": false + }, + "eu.mistral.pixtral-large-2502-v1:0": { + "input_cost_per_token": 2e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-06, + "supports_function_calling": true, + "supports_tool_choice": false + }, + "featherless_ai/featherless-ai/Qwerky-72B": { + "litellm_provider": "featherless_ai", + "max_input_tokens": 32768, + "max_output_tokens": 4096, + "max_tokens": 32768, + "mode": "chat" + }, + "featherless_ai/featherless-ai/Qwerky-QwQ-32B": { + "litellm_provider": "featherless_ai", + "max_input_tokens": 32768, + "max_output_tokens": 4096, + "max_tokens": 32768, + "mode": "chat" + }, + "fireworks-ai-4.1b-to-16b": { + "input_cost_per_token": 2e-07, + "litellm_provider": "fireworks_ai", + "output_cost_per_token": 2e-07 + }, + "fireworks-ai-56b-to-176b": { + "input_cost_per_token": 1.2e-06, + "litellm_provider": "fireworks_ai", + "output_cost_per_token": 1.2e-06 + }, + "fireworks-ai-above-16b": { + "input_cost_per_token": 9e-07, + "litellm_provider": "fireworks_ai", + "output_cost_per_token": 9e-07 + }, + "fireworks-ai-default": { + "input_cost_per_token": 0.0, + "litellm_provider": "fireworks_ai", + "output_cost_per_token": 0.0 + }, + "fireworks-ai-embedding-150m-to-350m": { + "input_cost_per_token": 1.6e-08, + "litellm_provider": "fireworks_ai-embedding-models", + "output_cost_per_token": 0.0 + }, + "fireworks-ai-embedding-up-to-150m": { + "input_cost_per_token": 8e-09, + "litellm_provider": "fireworks_ai-embedding-models", + "output_cost_per_token": 0.0 + }, + "fireworks-ai-moe-up-to-56b": { + "input_cost_per_token": 5e-07, + "litellm_provider": "fireworks_ai", + "output_cost_per_token": 5e-07 + }, + "fireworks-ai-up-to-4b": { + "input_cost_per_token": 2e-07, + "litellm_provider": "fireworks_ai", + "output_cost_per_token": 2e-07 + }, + "fireworks_ai/WhereIsAI/UAE-Large-V1": { + "input_cost_per_token": 1.6e-08, + "litellm_provider": "fireworks_ai-embedding-models", + "max_input_tokens": 512, + "max_tokens": 512, + "mode": "embedding", + "output_cost_per_token": 0.0, + "source": "https://fireworks.ai/pricing" + }, + "fireworks_ai/accounts/fireworks/models/deepseek-coder-v2-instruct": { + "input_cost_per_token": 1.2e-06, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 65536, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://fireworks.ai/pricing", + "supports_function_calling": false, + "supports_response_schema": true, + "supports_tool_choice": false + }, + "fireworks_ai/accounts/fireworks/models/deepseek-r1": { + "input_cost_per_token": 3e-06, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 128000, + "max_output_tokens": 20480, + "max_tokens": 20480, + "mode": "chat", + "output_cost_per_token": 8e-06, + "source": "https://fireworks.ai/pricing", + "supports_response_schema": true, + "supports_tool_choice": false + }, + "fireworks_ai/accounts/fireworks/models/deepseek-r1-0528": { + "input_cost_per_token": 3e-06, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 160000, + "max_output_tokens": 160000, + "max_tokens": 160000, + "mode": "chat", + "output_cost_per_token": 8e-06, + "source": "https://fireworks.ai/pricing", + "supports_response_schema": true, + "supports_tool_choice": false + }, + "fireworks_ai/accounts/fireworks/models/deepseek-r1-basic": { + "input_cost_per_token": 5.5e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 128000, + "max_output_tokens": 20480, + "max_tokens": 20480, + "mode": "chat", + "output_cost_per_token": 2.19e-06, + "source": "https://fireworks.ai/pricing", + "supports_response_schema": true, + "supports_tool_choice": false + }, + "fireworks_ai/accounts/fireworks/models/deepseek-v3": { + "input_cost_per_token": 9e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 9e-07, + "source": "https://fireworks.ai/pricing", + "supports_response_schema": true, + "supports_tool_choice": false + }, + "fireworks_ai/accounts/fireworks/models/deepseek-v3-0324": { + "input_cost_per_token": 9e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 163840, + "max_output_tokens": 163840, + "max_tokens": 163840, + "mode": "chat", + "output_cost_per_token": 9e-07, + "source": "https://fireworks.ai/models/fireworks/deepseek-v3-0324", + "supports_response_schema": true, + "supports_tool_choice": false + }, + "fireworks_ai/accounts/fireworks/models/deepseek-v3p1": { + "input_cost_per_token": 5.6e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.68e-06, + "source": "https://fireworks.ai/pricing", + "supports_response_schema": true, + "supports_tool_choice": true + }, + "fireworks_ai/accounts/fireworks/models/firefunction-v2": { + "input_cost_per_token": 9e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 9e-07, + "source": "https://fireworks.ai/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "fireworks_ai/accounts/fireworks/models/glm-4p5": { + "input_cost_per_token": 5.5e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 128000, + "max_output_tokens": 96000, + "max_tokens": 96000, + "mode": "chat", + "output_cost_per_token": 2.19e-06, + "source": "https://fireworks.ai/models/fireworks/glm-4p5", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "fireworks_ai/accounts/fireworks/models/glm-4p5-air": { + "input_cost_per_token": 2.2e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 128000, + "max_output_tokens": 96000, + "max_tokens": 96000, + "mode": "chat", + "output_cost_per_token": 8.8e-07, + "source": "https://artificialanalysis.ai/models/glm-4-5-air", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "fireworks_ai/accounts/fireworks/models/gpt-oss-120b": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 6e-07, + "source": "https://fireworks.ai/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "fireworks_ai/accounts/fireworks/models/gpt-oss-20b": { + "input_cost_per_token": 5e-08, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2e-07, + "source": "https://fireworks.ai/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "fireworks_ai/accounts/fireworks/models/kimi-k2-instruct": { + "input_cost_per_token": 6e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 131072, + "max_output_tokens": 16384, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.5e-06, + "source": "https://fireworks.ai/models/fireworks/kimi-k2-instruct", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "fireworks_ai/accounts/fireworks/models/llama-v3p1-405b-instruct": { + "input_cost_per_token": 3e-06, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 3e-06, + "source": "https://fireworks.ai/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "fireworks_ai/accounts/fireworks/models/llama-v3p1-8b-instruct": { + "input_cost_per_token": 1e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1e-07, + "source": "https://fireworks.ai/pricing", + "supports_function_calling": false, + "supports_response_schema": true, + "supports_tool_choice": false + }, + "fireworks_ai/accounts/fireworks/models/llama-v3p2-11b-vision-instruct": { + "input_cost_per_token": 2e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 2e-07, + "source": "https://fireworks.ai/pricing", + "supports_function_calling": false, + "supports_response_schema": true, + "supports_tool_choice": false, + "supports_vision": true + }, + "fireworks_ai/accounts/fireworks/models/llama-v3p2-1b-instruct": { + "input_cost_per_token": 1e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1e-07, + "source": "https://fireworks.ai/pricing", + "supports_function_calling": false, + "supports_response_schema": true, + "supports_tool_choice": false + }, + "fireworks_ai/accounts/fireworks/models/llama-v3p2-3b-instruct": { + "input_cost_per_token": 1e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1e-07, + "source": "https://fireworks.ai/pricing", + "supports_function_calling": false, + "supports_response_schema": true, + "supports_tool_choice": false + }, + "fireworks_ai/accounts/fireworks/models/llama-v3p2-90b-vision-instruct": { + "input_cost_per_token": 9e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 9e-07, + "source": "https://fireworks.ai/pricing", + "supports_response_schema": true, + "supports_tool_choice": false, + "supports_vision": true + }, + "fireworks_ai/accounts/fireworks/models/llama4-maverick-instruct-basic": { + "input_cost_per_token": 2.2e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 8.8e-07, + "source": "https://fireworks.ai/pricing", + "supports_response_schema": true, + "supports_tool_choice": false + }, + "fireworks_ai/accounts/fireworks/models/llama4-scout-instruct-basic": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 6e-07, + "source": "https://fireworks.ai/pricing", + "supports_response_schema": true, + "supports_tool_choice": false + }, + "fireworks_ai/accounts/fireworks/models/mixtral-8x22b-instruct-hf": { + "input_cost_per_token": 1.2e-06, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 65536, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://fireworks.ai/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "fireworks_ai/accounts/fireworks/models/qwen2-72b-instruct": { + "input_cost_per_token": 9e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 9e-07, + "source": "https://fireworks.ai/pricing", + "supports_function_calling": false, + "supports_response_schema": true, + "supports_tool_choice": false + }, + "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b-instruct": { + "input_cost_per_token": 9e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 9e-07, + "source": "https://fireworks.ai/pricing", + "supports_function_calling": false, + "supports_response_schema": true, + "supports_tool_choice": false + }, + "fireworks_ai/accounts/fireworks/models/yi-large": { + "input_cost_per_token": 3e-06, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 3e-06, + "source": "https://fireworks.ai/pricing", + "supports_function_calling": false, + "supports_response_schema": true, + "supports_tool_choice": false + }, + "fireworks_ai/nomic-ai/nomic-embed-text-v1": { + "input_cost_per_token": 8e-09, + "litellm_provider": "fireworks_ai-embedding-models", + "max_input_tokens": 8192, + "max_tokens": 8192, + "mode": "embedding", + "output_cost_per_token": 0.0, + "source": "https://fireworks.ai/pricing" + }, + "fireworks_ai/nomic-ai/nomic-embed-text-v1.5": { + "input_cost_per_token": 8e-09, + "litellm_provider": "fireworks_ai-embedding-models", + "max_input_tokens": 8192, + "max_tokens": 8192, + "mode": "embedding", + "output_cost_per_token": 0.0, + "source": "https://fireworks.ai/pricing" + }, + "fireworks_ai/thenlper/gte-base": { + "input_cost_per_token": 8e-09, + "litellm_provider": "fireworks_ai-embedding-models", + "max_input_tokens": 512, + "max_tokens": 512, + "mode": "embedding", + "output_cost_per_token": 0.0, + "source": "https://fireworks.ai/pricing" + }, + "fireworks_ai/thenlper/gte-large": { + "input_cost_per_token": 1.6e-08, + "litellm_provider": "fireworks_ai-embedding-models", + "max_input_tokens": 512, + "max_tokens": 512, + "mode": "embedding", + "output_cost_per_token": 0.0, + "source": "https://fireworks.ai/pricing" + }, + "friendliai/meta-llama-3.1-70b-instruct": { + "input_cost_per_token": 6e-07, + "litellm_provider": "friendliai", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 6e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "friendliai/meta-llama-3.1-8b-instruct": { + "input_cost_per_token": 1e-07, + "litellm_provider": "friendliai", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "ft:babbage-002": { + "input_cost_per_token": 4e-07, + "input_cost_per_token_batches": 2e-07, + "litellm_provider": "text-completion-openai", + "max_input_tokens": 16384, + "max_output_tokens": 4096, + "max_tokens": 16384, + "mode": "completion", + "output_cost_per_token": 4e-07, + "output_cost_per_token_batches": 2e-07 + }, + "ft:davinci-002": { + "input_cost_per_token": 2e-06, + "input_cost_per_token_batches": 1e-06, + "litellm_provider": "text-completion-openai", + "max_input_tokens": 16384, + "max_output_tokens": 4096, + "max_tokens": 16384, + "mode": "completion", + "output_cost_per_token": 2e-06, + "output_cost_per_token_batches": 1e-06 + }, + "ft:gpt-3.5-turbo": { + "input_cost_per_token": 3e-06, + "input_cost_per_token_batches": 1.5e-06, + "litellm_provider": "openai", + "max_input_tokens": 16385, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 6e-06, + "output_cost_per_token_batches": 3e-06, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "ft:gpt-3.5-turbo-0125": { + "input_cost_per_token": 3e-06, + "litellm_provider": "openai", + "max_input_tokens": 16385, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 6e-06, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "ft:gpt-3.5-turbo-0613": { + "input_cost_per_token": 3e-06, + "litellm_provider": "openai", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 6e-06, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "ft:gpt-3.5-turbo-1106": { + "input_cost_per_token": 3e-06, + "litellm_provider": "openai", + "max_input_tokens": 16385, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 6e-06, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "ft:gpt-4-0613": { + "input_cost_per_token": 3e-05, + "litellm_provider": "openai", + "max_input_tokens": 8192, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 6e-05, + "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 + }, + "ft:gpt-4o-2024-08-06": { + "input_cost_per_token": 3.75e-06, + "input_cost_per_token_batches": 1.875e-06, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "output_cost_per_token_batches": 7.5e-06, + "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 + }, + "ft:gpt-4o-2024-11-20": { + "cache_creation_input_token_cost": 1.875e-06, + "input_cost_per_token": 3.75e-06, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "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 + }, + "ft:gpt-4o-mini-2024-07-18": { + "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token": 3e-07, + "input_cost_per_token_batches": 1.5e-07, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "output_cost_per_token_batches": 6e-07, + "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 + }, + "gemini-1.0-pro": { + "input_cost_per_character": 1.25e-07, + "input_cost_per_image": 0.0025, + "input_cost_per_token": 5e-07, + "input_cost_per_video_per_second": 0.002, + "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 32760, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_character": 3.75e-07, + "output_cost_per_token": 1.5e-06, + "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 + }, + "gemini-1.0-pro-001": { + "deprecation_date": "2025-04-09", + "input_cost_per_character": 1.25e-07, + "input_cost_per_image": 0.0025, + "input_cost_per_token": 5e-07, + "input_cost_per_video_per_second": 0.002, + "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 32760, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_character": 3.75e-07, + "output_cost_per_token": 1.5e-06, + "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 + }, + "gemini-1.0-pro-002": { + "deprecation_date": "2025-04-09", + "input_cost_per_character": 1.25e-07, + "input_cost_per_image": 0.0025, + "input_cost_per_token": 5e-07, + "input_cost_per_video_per_second": 0.002, + "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 32760, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_character": 3.75e-07, + "output_cost_per_token": 1.5e-06, + "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 + }, + "gemini-1.0-pro-vision": { + "input_cost_per_image": 0.0025, + "input_cost_per_token": 5e-07, + "litellm_provider": "vertex_ai-vision-models", + "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": 1.5e-06, + "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 + }, + "gemini-1.0-pro-vision-001": { + "deprecation_date": "2025-04-09", + "input_cost_per_image": 0.0025, + "input_cost_per_token": 5e-07, + "litellm_provider": "vertex_ai-vision-models", + "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": 1.5e-06, + "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 + }, + "gemini-1.0-ultra": { + "input_cost_per_character": 1.25e-07, + "input_cost_per_image": 0.0025, + "input_cost_per_token": 5e-07, + "input_cost_per_video_per_second": 0.002, + "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 8192, + "max_output_tokens": 2048, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_character": 3.75e-07, + "output_cost_per_token": 1.5e-06, + "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 + }, + "gemini-1.0-ultra-001": { + "input_cost_per_character": 1.25e-07, + "input_cost_per_image": 0.0025, + "input_cost_per_token": 5e-07, + "input_cost_per_video_per_second": 0.002, + "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 8192, + "max_output_tokens": 2048, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_character": 3.75e-07, + "output_cost_per_token": 1.5e-06, + "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 + }, + "gemini-1.5-flash": { + "input_cost_per_audio_per_second": 2e-06, + "input_cost_per_audio_per_second_above_128k_tokens": 4e-06, + "input_cost_per_character": 1.875e-08, + "input_cost_per_character_above_128k_tokens": 2.5e-07, + "input_cost_per_image": 2e-05, + "input_cost_per_image_above_128k_tokens": 4e-05, + "input_cost_per_token": 7.5e-08, + "input_cost_per_token_above_128k_tokens": 1e-06, + "input_cost_per_video_per_second": 2e-05, + "input_cost_per_video_per_second_above_128k_tokens": 4e-05, + "litellm_provider": "vertex_ai-language-models", + "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-08, + "output_cost_per_character_above_128k_tokens": 1.5e-07, + "output_cost_per_token": 3e-07, + "output_cost_per_token_above_128k_tokens": 6e-07, + "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 + }, + "gemini-1.5-flash-001": { + "deprecation_date": "2025-05-24", + "input_cost_per_audio_per_second": 2e-06, + "input_cost_per_audio_per_second_above_128k_tokens": 4e-06, + "input_cost_per_character": 1.875e-08, + "input_cost_per_character_above_128k_tokens": 2.5e-07, + "input_cost_per_image": 2e-05, + "input_cost_per_image_above_128k_tokens": 4e-05, + "input_cost_per_token": 7.5e-08, + "input_cost_per_token_above_128k_tokens": 1e-06, + "input_cost_per_video_per_second": 2e-05, + "input_cost_per_video_per_second_above_128k_tokens": 4e-05, + "litellm_provider": "vertex_ai-language-models", + "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-08, + "output_cost_per_character_above_128k_tokens": 1.5e-07, + "output_cost_per_token": 3e-07, + "output_cost_per_token_above_128k_tokens": 6e-07, + "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 + }, + "gemini-1.5-flash-002": { + "deprecation_date": "2025-09-24", + "input_cost_per_audio_per_second": 2e-06, + "input_cost_per_audio_per_second_above_128k_tokens": 4e-06, + "input_cost_per_character": 1.875e-08, + "input_cost_per_character_above_128k_tokens": 2.5e-07, + "input_cost_per_image": 2e-05, + "input_cost_per_image_above_128k_tokens": 4e-05, + "input_cost_per_token": 7.5e-08, + "input_cost_per_token_above_128k_tokens": 1e-06, + "input_cost_per_video_per_second": 2e-05, + "input_cost_per_video_per_second_above_128k_tokens": 4e-05, + "litellm_provider": "vertex_ai-language-models", + "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-08, + "output_cost_per_character_above_128k_tokens": 1.5e-07, + "output_cost_per_token": 3e-07, + "output_cost_per_token_above_128k_tokens": 6e-07, + "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 + }, + "gemini-1.5-flash-exp-0827": { + "input_cost_per_audio_per_second": 2e-06, + "input_cost_per_audio_per_second_above_128k_tokens": 4e-06, + "input_cost_per_character": 1.875e-08, + "input_cost_per_character_above_128k_tokens": 2.5e-07, + "input_cost_per_image": 2e-05, + "input_cost_per_image_above_128k_tokens": 4e-05, + "input_cost_per_token": 4.688e-09, + "input_cost_per_token_above_128k_tokens": 1e-06, + "input_cost_per_video_per_second": 2e-05, + "input_cost_per_video_per_second_above_128k_tokens": 4e-05, + "litellm_provider": "vertex_ai-language-models", + "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-08, + "output_cost_per_character_above_128k_tokens": 3.75e-08, + "output_cost_per_token": 4.6875e-09, + "output_cost_per_token_above_128k_tokens": 9.375e-09, + "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 + }, + "gemini-1.5-flash-preview-0514": { + "input_cost_per_audio_per_second": 2e-06, + "input_cost_per_audio_per_second_above_128k_tokens": 4e-06, + "input_cost_per_character": 1.875e-08, + "input_cost_per_character_above_128k_tokens": 2.5e-07, + "input_cost_per_image": 2e-05, + "input_cost_per_image_above_128k_tokens": 4e-05, + "input_cost_per_token": 7.5e-08, + "input_cost_per_token_above_128k_tokens": 1e-06, + "input_cost_per_video_per_second": 2e-05, + "input_cost_per_video_per_second_above_128k_tokens": 4e-05, + "litellm_provider": "vertex_ai-language-models", + "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-08, + "output_cost_per_character_above_128k_tokens": 3.75e-08, + "output_cost_per_token": 4.6875e-09, + "output_cost_per_token_above_128k_tokens": 9.375e-09, + "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 + }, + "gemini-1.5-pro": { + "input_cost_per_audio_per_second": 3.125e-05, + "input_cost_per_audio_per_second_above_128k_tokens": 6.25e-05, + "input_cost_per_character": 3.125e-07, + "input_cost_per_character_above_128k_tokens": 6.25e-07, + "input_cost_per_image": 0.00032875, + "input_cost_per_image_above_128k_tokens": 0.0006575, + "input_cost_per_token": 1.25e-06, + "input_cost_per_token_above_128k_tokens": 2.5e-06, + "input_cost_per_video_per_second": 0.00032875, + "input_cost_per_video_per_second_above_128k_tokens": 0.0006575, + "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 2097152, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_character": 1.25e-06, + "output_cost_per_character_above_128k_tokens": 2.5e-06, + "output_cost_per_token": 5e-06, + "output_cost_per_token_above_128k_tokens": 1e-05, + "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 + }, + "gemini-1.5-pro-001": { + "deprecation_date": "2025-05-24", + "input_cost_per_audio_per_second": 3.125e-05, + "input_cost_per_audio_per_second_above_128k_tokens": 6.25e-05, + "input_cost_per_character": 3.125e-07, + "input_cost_per_character_above_128k_tokens": 6.25e-07, + "input_cost_per_image": 0.00032875, + "input_cost_per_image_above_128k_tokens": 0.0006575, + "input_cost_per_token": 1.25e-06, + "input_cost_per_token_above_128k_tokens": 2.5e-06, + "input_cost_per_video_per_second": 0.00032875, + "input_cost_per_video_per_second_above_128k_tokens": 0.0006575, + "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 1000000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_character": 1.25e-06, + "output_cost_per_character_above_128k_tokens": 2.5e-06, + "output_cost_per_token": 5e-06, + "output_cost_per_token_above_128k_tokens": 1e-05, + "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 + }, + "gemini-1.5-pro-002": { + "deprecation_date": "2025-09-24", + "input_cost_per_audio_per_second": 3.125e-05, + "input_cost_per_audio_per_second_above_128k_tokens": 6.25e-05, + "input_cost_per_character": 3.125e-07, + "input_cost_per_character_above_128k_tokens": 6.25e-07, + "input_cost_per_image": 0.00032875, + "input_cost_per_image_above_128k_tokens": 0.0006575, + "input_cost_per_token": 1.25e-06, + "input_cost_per_token_above_128k_tokens": 2.5e-06, + "input_cost_per_video_per_second": 0.00032875, + "input_cost_per_video_per_second_above_128k_tokens": 0.0006575, + "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 2097152, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_character": 1.25e-06, + "output_cost_per_character_above_128k_tokens": 2.5e-06, + "output_cost_per_token": 5e-06, + "output_cost_per_token_above_128k_tokens": 1e-05, + "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 + }, + "gemini-1.5-pro-preview-0215": { + "input_cost_per_audio_per_second": 3.125e-05, + "input_cost_per_audio_per_second_above_128k_tokens": 6.25e-05, + "input_cost_per_character": 3.125e-07, + "input_cost_per_character_above_128k_tokens": 6.25e-07, + "input_cost_per_image": 0.00032875, + "input_cost_per_image_above_128k_tokens": 0.0006575, + "input_cost_per_token": 7.8125e-08, + "input_cost_per_token_above_128k_tokens": 1.5625e-07, + "input_cost_per_video_per_second": 0.00032875, + "input_cost_per_video_per_second_above_128k_tokens": 0.0006575, + "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 1000000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_character": 1.25e-06, + "output_cost_per_character_above_128k_tokens": 2.5e-06, + "output_cost_per_token": 3.125e-07, + "output_cost_per_token_above_128k_tokens": 6.25e-07, + "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 + }, + "gemini-1.5-pro-preview-0409": { + "input_cost_per_audio_per_second": 3.125e-05, + "input_cost_per_audio_per_second_above_128k_tokens": 6.25e-05, + "input_cost_per_character": 3.125e-07, + "input_cost_per_character_above_128k_tokens": 6.25e-07, + "input_cost_per_image": 0.00032875, + "input_cost_per_image_above_128k_tokens": 0.0006575, + "input_cost_per_token": 7.8125e-08, + "input_cost_per_token_above_128k_tokens": 1.5625e-07, + "input_cost_per_video_per_second": 0.00032875, + "input_cost_per_video_per_second_above_128k_tokens": 0.0006575, + "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 1000000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_character": 1.25e-06, + "output_cost_per_character_above_128k_tokens": 2.5e-06, + "output_cost_per_token": 3.125e-07, + "output_cost_per_token_above_128k_tokens": 6.25e-07, + "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 + }, + "gemini-1.5-pro-preview-0514": { + "input_cost_per_audio_per_second": 3.125e-05, + "input_cost_per_audio_per_second_above_128k_tokens": 6.25e-05, + "input_cost_per_character": 3.125e-07, + "input_cost_per_character_above_128k_tokens": 6.25e-07, + "input_cost_per_image": 0.00032875, + "input_cost_per_image_above_128k_tokens": 0.0006575, + "input_cost_per_token": 7.8125e-08, + "input_cost_per_token_above_128k_tokens": 1.5625e-07, + "input_cost_per_video_per_second": 0.00032875, + "input_cost_per_video_per_second_above_128k_tokens": 0.0006575, + "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 1000000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_character": 1.25e-06, + "output_cost_per_character_above_128k_tokens": 2.5e-06, + "output_cost_per_token": 3.125e-07, + "output_cost_per_token_above_128k_tokens": 6.25e-07, + "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 + }, + "gemini-2.0-flash": { + "cache_read_input_token_cost": 2.5e-08, + "input_cost_per_audio_token": 7e-07, + "input_cost_per_token": 1e-07, + "litellm_provider": "vertex_ai-language-models", + "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-07, + "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 + }, + "gemini-2.0-flash-001": { + "cache_read_input_token_cost": 3.75e-08, + "deprecation_date": "2026-02-05", + "input_cost_per_audio_token": 1e-06, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "vertex_ai-language-models", + "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-07, + "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 + }, + "gemini-2.0-flash-exp": { + "cache_read_input_token_cost": 3.75e-08, + "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-07, + "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, + "litellm_provider": "vertex_ai-language-models", + "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-07, + "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 + }, + "gemini-2.0-flash-lite": { + "cache_read_input_token_cost": 1.875e-08, + "input_cost_per_audio_token": 7.5e-08, + "input_cost_per_token": 7.5e-08, + "litellm_provider": "vertex_ai-language-models", + "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-07, + "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 + }, + "gemini-2.0-flash-lite-001": { + "cache_read_input_token_cost": 1.875e-08, + "deprecation_date": "2026-02-25", + "input_cost_per_audio_token": 7.5e-08, + "input_cost_per_token": 7.5e-08, + "litellm_provider": "vertex_ai-language-models", + "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-07, + "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 + }, + "gemini-2.0-flash-live-preview-04-09": { + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_audio_token": 3e-06, + "input_cost_per_image": 3e-06, + "input_cost_per_token": 5e-07, + "input_cost_per_video_per_second": 3e-06, + "litellm_provider": "vertex_ai-language-models", + "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": 1.2e-05, + "output_cost_per_token": 2e-06, + "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 + }, + "gemini-2.0-flash-preview-image-generation": { + "cache_read_input_token_cost": 2.5e-08, + "input_cost_per_audio_token": 7e-07, + "input_cost_per_token": 1e-07, + "litellm_provider": "vertex_ai-language-models", + "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-07, + "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 + }, + "gemini-2.0-flash-thinking-exp": { + "cache_read_input_token_cost": 0.0, + "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, + "litellm_provider": "vertex_ai-language-models", + "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 + }, + "gemini-2.0-flash-thinking-exp-01-21": { + "cache_read_input_token_cost": 0.0, + "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, + "litellm_provider": "vertex_ai-language-models", + "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_response_schema": false, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "gemini-2.0-pro-exp-02-05": { + "cache_read_input_token_cost": 3.125e-07, + "input_cost_per_token": 1.25e-06, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "litellm_provider": "vertex_ai-language-models", + "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": 1e-05, + "output_cost_per_token_above_200k_tokens": 1.5e-05, + "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 + }, + "gemini-2.5-flash": { + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_audio_token": 1e-06, + "input_cost_per_token": 3e-07, + "litellm_provider": "vertex_ai-language-models", + "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": 2.5e-06, + "output_cost_per_token": 2.5e-06, + "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 + }, + "gemini-2.5-flash-image-preview": { + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_audio_token": 1e-06, + "input_cost_per_token": 3e-07, + "litellm_provider": "vertex_ai-language-models", + "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": 3e-05, + "output_cost_per_token": 3e-05, + "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 + }, + "gemini-2.5-flash-lite": { + "cache_read_input_token_cost": 2.5e-08, + "input_cost_per_audio_token": 5e-07, + "input_cost_per_token": 1e-07, + "litellm_provider": "vertex_ai-language-models", + "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-07, + "output_cost_per_token": 4e-07, + "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 + }, + "gemini-2.5-flash-lite-preview-09-2025": { + "cache_read_input_token_cost": 2.5e-08, + "input_cost_per_audio_token": 3e-07, + "input_cost_per_token": 1e-07, + "litellm_provider": "vertex_ai-language-models", + "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-07, + "output_cost_per_token": 4e-07, + "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 + }, + "gemini-2.5-flash-preview-09-2025": { + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_audio_token": 1e-06, + "input_cost_per_token": 3e-07, + "litellm_provider": "vertex_ai-language-models", + "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": 2.5e-06, + "output_cost_per_token": 2.5e-06, + "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 + }, + "gemini-flash-latest": { + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_audio_token": 1e-06, + "input_cost_per_token": 3e-07, + "litellm_provider": "vertex_ai-language-models", + "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": 2.5e-06, + "output_cost_per_token": 2.5e-06, + "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 + }, + "gemini-flash-lite-latest": { + "cache_read_input_token_cost": 2.5e-08, + "input_cost_per_audio_token": 3e-07, + "input_cost_per_token": 1e-07, + "litellm_provider": "vertex_ai-language-models", + "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-07, + "output_cost_per_token": 4e-07, + "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 + }, + "gemini-2.5-flash-lite-preview-06-17": { + "cache_read_input_token_cost": 2.5e-08, + "input_cost_per_audio_token": 5e-07, + "input_cost_per_token": 1e-07, + "litellm_provider": "vertex_ai-language-models", + "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-07, + "output_cost_per_token": 4e-07, + "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 + }, + "gemini-2.5-flash-preview-04-17": { + "cache_read_input_token_cost": 3.75e-08, + "input_cost_per_audio_token": 1e-06, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "vertex_ai-language-models", + "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": 3.5e-06, + "output_cost_per_token": 6e-07, + "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 + }, + "gemini-2.5-flash-preview-05-20": { + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_audio_token": 1e-06, + "input_cost_per_token": 3e-07, + "litellm_provider": "vertex_ai-language-models", + "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": 2.5e-06, + "output_cost_per_token": 2.5e-06, + "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 + }, + "gemini-2.5-pro": { + "cache_read_input_token_cost": 3.125e-07, + "input_cost_per_token": 1.25e-06, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "litellm_provider": "vertex_ai-language-models", + "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": 1e-05, + "output_cost_per_token_above_200k_tokens": 1.5e-05, + "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 + }, + "gemini-2.5-pro-exp-03-25": { + "cache_read_input_token_cost": 3.125e-07, + "input_cost_per_token": 1.25e-06, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "litellm_provider": "vertex_ai-language-models", + "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": 1e-05, + "output_cost_per_token_above_200k_tokens": 1.5e-05, + "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 + }, + "gemini-2.5-pro-preview-03-25": { + "cache_read_input_token_cost": 3.125e-07, + "input_cost_per_audio_token": 1.25e-06, + "input_cost_per_token": 1.25e-06, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "litellm_provider": "vertex_ai-language-models", + "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": 1e-05, + "output_cost_per_token_above_200k_tokens": 1.5e-05, + "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 + }, + "gemini-2.5-pro-preview-05-06": { + "cache_read_input_token_cost": 3.125e-07, + "input_cost_per_audio_token": 1.25e-06, + "input_cost_per_token": 1.25e-06, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "litellm_provider": "vertex_ai-language-models", + "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": 1e-05, + "output_cost_per_token_above_200k_tokens": 1.5e-05, + "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 + }, + "gemini-2.5-pro-preview-06-05": { + "cache_read_input_token_cost": 3.125e-07, + "input_cost_per_audio_token": 1.25e-06, + "input_cost_per_token": 1.25e-06, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "litellm_provider": "vertex_ai-language-models", + "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": 1e-05, + "output_cost_per_token_above_200k_tokens": 1.5e-05, + "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 + }, + "gemini-2.5-pro-preview-tts": { + "cache_read_input_token_cost": 3.125e-07, + "input_cost_per_audio_token": 7e-07, + "input_cost_per_token": 1.25e-06, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "litellm_provider": "vertex_ai-language-models", + "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": 1e-05, + "output_cost_per_token_above_200k_tokens": 1.5e-05, + "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 + }, + "gemini-embedding-001": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "vertex_ai-embedding-models", + "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" + }, + "gemini-flash-experimental": { + "input_cost_per_character": 0, + "input_cost_per_token": 0, + "litellm_provider": "vertex_ai-language-models", + "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 + }, + "gemini-pro": { + "input_cost_per_character": 1.25e-07, + "input_cost_per_image": 0.0025, + "input_cost_per_token": 5e-07, + "input_cost_per_video_per_second": 0.002, + "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 32760, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_character": 3.75e-07, + "output_cost_per_token": 1.5e-06, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "gemini-pro-experimental": { + "input_cost_per_character": 0, + "input_cost_per_token": 0, + "litellm_provider": "vertex_ai-language-models", + "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 + }, + "gemini-pro-vision": { + "input_cost_per_image": 0.0025, + "input_cost_per_token": 5e-07, + "litellm_provider": "vertex_ai-vision-models", + "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": 1.5e-06, + "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 + }, + "gemini/gemini-1.5-flash": { + "input_cost_per_token": 7.5e-08, + "input_cost_per_token_above_128k_tokens": 1.5e-07, + "litellm_provider": "gemini", + "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-07, + "output_cost_per_token_above_128k_tokens": 6e-07, + "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 + }, + "gemini/gemini-1.5-flash-001": { + "cache_creation_input_token_cost": 1e-06, + "cache_read_input_token_cost": 1.875e-08, + "deprecation_date": "2025-05-24", + "input_cost_per_token": 7.5e-08, + "input_cost_per_token_above_128k_tokens": 1.5e-07, + "litellm_provider": "gemini", + "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-07, + "output_cost_per_token_above_128k_tokens": 6e-07, + "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 + }, + "gemini/gemini-1.5-flash-002": { + "cache_creation_input_token_cost": 1e-06, + "cache_read_input_token_cost": 1.875e-08, + "deprecation_date": "2025-09-24", + "input_cost_per_token": 7.5e-08, + "input_cost_per_token_above_128k_tokens": 1.5e-07, + "litellm_provider": "gemini", + "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-07, + "output_cost_per_token_above_128k_tokens": 6e-07, + "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 + }, + "gemini/gemini-1.5-flash-8b": { + "input_cost_per_token": 0, + "input_cost_per_token_above_128k_tokens": 0, + "litellm_provider": "gemini", + "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 + }, + "gemini/gemini-1.5-flash-8b-exp-0827": { + "input_cost_per_token": 0, + "input_cost_per_token_above_128k_tokens": 0, + "litellm_provider": "gemini", + "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 + }, + "gemini/gemini-1.5-flash-8b-exp-0924": { + "input_cost_per_token": 0, + "input_cost_per_token_above_128k_tokens": 0, + "litellm_provider": "gemini", + "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 + }, + "gemini/gemini-1.5-flash-exp-0827": { + "input_cost_per_token": 0, + "input_cost_per_token_above_128k_tokens": 0, + "litellm_provider": "gemini", + "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 + }, + "gemini/gemini-1.5-flash-latest": { + "input_cost_per_token": 7.5e-08, + "input_cost_per_token_above_128k_tokens": 1.5e-07, + "litellm_provider": "gemini", + "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-07, + "output_cost_per_token_above_128k_tokens": 6e-07, + "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 + }, + "gemini/gemini-1.5-pro": { + "input_cost_per_token": 3.5e-06, + "input_cost_per_token_above_128k_tokens": 7e-06, + "litellm_provider": "gemini", + "max_input_tokens": 2097152, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.05e-05, + "output_cost_per_token_above_128k_tokens": 2.1e-05, + "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 + }, + "gemini/gemini-1.5-pro-001": { + "deprecation_date": "2025-05-24", + "input_cost_per_token": 3.5e-06, + "input_cost_per_token_above_128k_tokens": 7e-06, + "litellm_provider": "gemini", + "max_input_tokens": 2097152, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.05e-05, + "output_cost_per_token_above_128k_tokens": 2.1e-05, + "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 + }, + "gemini/gemini-1.5-pro-002": { + "deprecation_date": "2025-09-24", + "input_cost_per_token": 3.5e-06, + "input_cost_per_token_above_128k_tokens": 7e-06, + "litellm_provider": "gemini", + "max_input_tokens": 2097152, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.05e-05, + "output_cost_per_token_above_128k_tokens": 2.1e-05, + "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 + }, + "gemini/gemini-1.5-pro-exp-0801": { + "input_cost_per_token": 3.5e-06, + "input_cost_per_token_above_128k_tokens": 7e-06, + "litellm_provider": "gemini", + "max_input_tokens": 2097152, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.05e-05, + "output_cost_per_token_above_128k_tokens": 2.1e-05, + "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 + }, + "gemini/gemini-1.5-pro-exp-0827": { + "input_cost_per_token": 0, + "input_cost_per_token_above_128k_tokens": 0, + "litellm_provider": "gemini", + "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 + }, + "gemini/gemini-1.5-pro-latest": { + "input_cost_per_token": 3.5e-06, + "input_cost_per_token_above_128k_tokens": 7e-06, + "litellm_provider": "gemini", + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.05e-06, + "output_cost_per_token_above_128k_tokens": 2.1e-05, + "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 + }, + "gemini/gemini-2.0-flash": { + "cache_read_input_token_cost": 2.5e-08, + "input_cost_per_audio_token": 7e-07, + "input_cost_per_token": 1e-07, + "litellm_provider": "gemini", + "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-07, + "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 + }, + "gemini/gemini-2.0-flash-001": { + "cache_read_input_token_cost": 2.5e-08, + "input_cost_per_audio_token": 7e-07, + "input_cost_per_token": 1e-07, + "litellm_provider": "gemini", + "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-07, + "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 + }, + "gemini/gemini-2.0-flash-exp": { + "cache_read_input_token_cost": 0.0, + "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, + "litellm_provider": "gemini", + "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 + }, + "gemini/gemini-2.0-flash-lite": { + "cache_read_input_token_cost": 1.875e-08, + "input_cost_per_audio_token": 7.5e-08, + "input_cost_per_token": 7.5e-08, + "litellm_provider": "gemini", + "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-07, + "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 + }, + "gemini/gemini-2.0-flash-lite-preview-02-05": { + "cache_read_input_token_cost": 1.875e-08, + "input_cost_per_audio_token": 7.5e-08, + "input_cost_per_token": 7.5e-08, + "litellm_provider": "gemini", + "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-07, + "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 + }, + "gemini/gemini-2.0-flash-live-001": { + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_audio_token": 2.1e-06, + "input_cost_per_image": 2.1e-06, + "input_cost_per_token": 3.5e-07, + "input_cost_per_video_per_second": 2.1e-06, + "litellm_provider": "gemini", + "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": 8.5e-06, + "output_cost_per_token": 1.5e-06, + "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 + }, + "gemini/gemini-2.0-flash-preview-image-generation": { + "cache_read_input_token_cost": 2.5e-08, + "input_cost_per_audio_token": 7e-07, + "input_cost_per_token": 1e-07, + "litellm_provider": "gemini", + "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-07, + "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 + }, + "gemini/gemini-2.0-flash-thinking-exp": { + "cache_read_input_token_cost": 0.0, + "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, + "litellm_provider": "gemini", + "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 + }, + "gemini/gemini-2.0-flash-thinking-exp-01-21": { + "cache_read_input_token_cost": 0.0, + "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, + "litellm_provider": "gemini", + "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 + }, + "gemini/gemini-2.0-pro-exp-02-05": { + "cache_read_input_token_cost": 0.0, + "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, + "litellm_provider": "gemini", + "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 + }, + "gemini/gemini-2.5-flash": { + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_audio_token": 1e-06, + "input_cost_per_token": 3e-07, + "litellm_provider": "gemini", + "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": 2.5e-06, + "output_cost_per_token": 2.5e-06, + "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 + }, + "gemini/gemini-2.5-flash-image-preview": { + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_audio_token": 1e-06, + "input_cost_per_token": 3e-07, + "litellm_provider": "gemini", + "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": 3e-05, + "output_cost_per_token": 3e-05, + "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 + }, + "gemini/gemini-2.5-flash-lite": { + "cache_read_input_token_cost": 2.5e-08, + "input_cost_per_audio_token": 5e-07, + "input_cost_per_token": 1e-07, + "litellm_provider": "gemini", + "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-07, + "output_cost_per_token": 4e-07, + "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 + }, + "gemini/gemini-2.5-flash-lite-preview-09-2025": { + "cache_read_input_token_cost": 2.5e-08, + "input_cost_per_audio_token": 3e-07, + "input_cost_per_token": 1e-07, + "litellm_provider": "gemini", + "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-07, + "output_cost_per_token": 4e-07, + "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 + }, + "gemini/gemini-2.5-flash-preview-09-2025": { + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_audio_token": 1e-06, + "input_cost_per_token": 3e-07, + "litellm_provider": "gemini", + "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": 2.5e-06, + "output_cost_per_token": 2.5e-06, + "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 + }, + "gemini/gemini-flash-latest": { + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_audio_token": 1e-06, + "input_cost_per_token": 3e-07, + "litellm_provider": "gemini", + "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": 2.5e-06, + "output_cost_per_token": 2.5e-06, + "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 + }, + "gemini/gemini-flash-lite-latest": { + "cache_read_input_token_cost": 2.5e-08, + "input_cost_per_audio_token": 3e-07, + "input_cost_per_token": 1e-07, + "litellm_provider": "gemini", + "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-07, + "output_cost_per_token": 4e-07, + "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 + }, + "gemini/gemini-2.5-flash-lite-preview-06-17": { + "cache_read_input_token_cost": 2.5e-08, + "input_cost_per_audio_token": 5e-07, + "input_cost_per_token": 1e-07, + "litellm_provider": "gemini", + "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-07, + "output_cost_per_token": 4e-07, + "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 + }, + "gemini/gemini-2.5-flash-preview-04-17": { + "cache_read_input_token_cost": 3.75e-08, + "input_cost_per_audio_token": 1e-06, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "gemini", + "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": 3.5e-06, + "output_cost_per_token": 6e-07, + "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 + }, + "gemini/gemini-2.5-flash-preview-05-20": { + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_audio_token": 1e-06, + "input_cost_per_token": 3e-07, + "litellm_provider": "gemini", + "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": 2.5e-06, + "output_cost_per_token": 2.5e-06, + "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 + }, + "gemini/gemini-2.5-flash-preview-tts": { + "cache_read_input_token_cost": 3.75e-08, + "input_cost_per_audio_token": 1e-06, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "gemini", + "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": 3.5e-06, + "output_cost_per_token": 6e-07, + "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 + }, + "gemini/gemini-2.5-pro": { + "cache_read_input_token_cost": 3.125e-07, + "input_cost_per_token": 1.25e-06, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "litellm_provider": "gemini", + "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": 1e-05, + "output_cost_per_token_above_200k_tokens": 1.5e-05, + "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 + }, + "gemini/gemini-2.5-pro-exp-03-25": { + "cache_read_input_token_cost": 0.0, + "input_cost_per_token": 0.0, + "input_cost_per_token_above_200k_tokens": 0.0, + "litellm_provider": "gemini", + "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": 0.0, + "output_cost_per_token_above_200k_tokens": 0.0, + "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 + }, + "gemini/gemini-2.5-pro-preview-03-25": { + "cache_read_input_token_cost": 3.125e-07, + "input_cost_per_audio_token": 7e-07, + "input_cost_per_token": 1.25e-06, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "litellm_provider": "gemini", + "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": 1e-05, + "output_cost_per_token_above_200k_tokens": 1.5e-05, + "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 + }, + "gemini/gemini-2.5-pro-preview-05-06": { + "cache_read_input_token_cost": 3.125e-07, + "input_cost_per_audio_token": 7e-07, + "input_cost_per_token": 1.25e-06, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "litellm_provider": "gemini", + "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": 1e-05, + "output_cost_per_token_above_200k_tokens": 1.5e-05, + "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 + }, + "gemini/gemini-2.5-pro-preview-06-05": { + "cache_read_input_token_cost": 3.125e-07, + "input_cost_per_audio_token": 7e-07, + "input_cost_per_token": 1.25e-06, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "litellm_provider": "gemini", + "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": 1e-05, + "output_cost_per_token_above_200k_tokens": 1.5e-05, + "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 + }, + "gemini/gemini-2.5-pro-preview-tts": { + "cache_read_input_token_cost": 3.125e-07, + "input_cost_per_audio_token": 7e-07, + "input_cost_per_token": 1.25e-06, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "litellm_provider": "gemini", + "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": 1e-05, + "output_cost_per_token_above_200k_tokens": 1.5e-05, + "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 + }, + "gemini/gemini-exp-1114": { + "input_cost_per_token": 0, + "input_cost_per_token_above_128k_tokens": 0, + "litellm_provider": "gemini", + "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 + }, + "gemini/gemini-exp-1206": { + "input_cost_per_token": 0, + "input_cost_per_token_above_128k_tokens": 0, + "litellm_provider": "gemini", + "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 + }, + "gemini/gemini-gemma-2-27b-it": { + "input_cost_per_token": 3.5e-07, + "litellm_provider": "gemini", + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.05e-06, + "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 + }, + "gemini/gemini-gemma-2-9b-it": { + "input_cost_per_token": 3.5e-07, + "litellm_provider": "gemini", + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.05e-06, + "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 + }, + "gemini/gemini-pro": { + "input_cost_per_token": 3.5e-07, + "input_cost_per_token_above_128k_tokens": 7e-07, + "litellm_provider": "gemini", + "max_input_tokens": 32760, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.05e-06, + "output_cost_per_token_above_128k_tokens": 2.1e-06, + "rpd": 30000, + "rpm": 360, + "source": "https://ai.google.dev/gemini-api/docs/models/gemini", + "supports_function_calling": true, + "supports_tool_choice": true, + "tpm": 120000 + }, + "gemini/gemini-pro-vision": { + "input_cost_per_token": 3.5e-07, + "input_cost_per_token_above_128k_tokens": 7e-07, + "litellm_provider": "gemini", + "max_input_tokens": 30720, + "max_output_tokens": 2048, + "max_tokens": 2048, + "mode": "chat", + "output_cost_per_token": 1.05e-06, + "output_cost_per_token_above_128k_tokens": 2.1e-06, + "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 + }, + "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, + "litellm_provider": "gemini", + "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": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "gemini/imagen-3.0-fast-generate-001": { + "litellm_provider": "gemini", + "mode": "image_generation", + "output_cost_per_image": 0.02, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" + }, + "gemini/imagen-3.0-generate-001": { + "litellm_provider": "gemini", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" + }, + "gemini/imagen-3.0-generate-002": { + "litellm_provider": "gemini", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" + }, + "gemini/imagen-4.0-fast-generate-001": { + "litellm_provider": "gemini", + "mode": "image_generation", + "output_cost_per_image": 0.02, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" + }, + "gemini/imagen-4.0-generate-001": { + "litellm_provider": "gemini", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" + }, + "gemini/imagen-4.0-ultra-generate-001": { + "litellm_provider": "gemini", + "mode": "image_generation", + "output_cost_per_image": 0.06, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" + }, + "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, + "litellm_provider": "gemini", + "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 + }, + "gemini/veo-2.0-generate-001": { + "litellm_provider": "gemini", + "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" + ] + }, + "gemini/veo-3.0-fast-generate-preview": { + "litellm_provider": "gemini", + "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" + ] + }, + "gemini/veo-3.0-generate-preview": { + "litellm_provider": "gemini", + "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" + ] + }, + "gpt-3.5-turbo": { + "input_cost_per_token": 0.5e-06, + "litellm_provider": "openai", + "max_input_tokens": 16385, + "max_output_tokens": 4096, + "max_tokens": 4097, + "mode": "chat", + "output_cost_per_token": 1.5e-06, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "gpt-3.5-turbo-0125": { + "input_cost_per_token": 5e-07, + "litellm_provider": "openai", + "max_input_tokens": 16385, + "max_output_tokens": 4096, + "max_tokens": 16385, + "mode": "chat", + "output_cost_per_token": 1.5e-06, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "gpt-3.5-turbo-0301": { + "input_cost_per_token": 1.5e-06, + "litellm_provider": "openai", + "max_input_tokens": 4097, + "max_output_tokens": 4096, + "max_tokens": 4097, + "mode": "chat", + "output_cost_per_token": 2e-06, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "gpt-3.5-turbo-0613": { + "input_cost_per_token": 1.5e-06, + "litellm_provider": "openai", + "max_input_tokens": 4097, + "max_output_tokens": 4096, + "max_tokens": 4097, + "mode": "chat", + "output_cost_per_token": 2e-06, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "gpt-3.5-turbo-1106": { + "input_cost_per_token": 1e-06, + "litellm_provider": "openai", + "max_input_tokens": 16385, + "max_output_tokens": 4096, + "max_tokens": 16385, + "mode": "chat", + "output_cost_per_token": 2e-06, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "gpt-3.5-turbo-16k": { + "input_cost_per_token": 3e-06, + "litellm_provider": "openai", + "max_input_tokens": 16385, + "max_output_tokens": 4096, + "max_tokens": 16385, + "mode": "chat", + "output_cost_per_token": 4e-06, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "gpt-3.5-turbo-16k-0613": { + "input_cost_per_token": 3e-06, + "litellm_provider": "openai", + "max_input_tokens": 16385, + "max_output_tokens": 4096, + "max_tokens": 16385, + "mode": "chat", + "output_cost_per_token": 4e-06, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "gpt-3.5-turbo-instruct": { + "input_cost_per_token": 1.5e-06, + "litellm_provider": "text-completion-openai", + "max_input_tokens": 8192, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "completion", + "output_cost_per_token": 2e-06 + }, + "gpt-3.5-turbo-instruct-0914": { + "input_cost_per_token": 1.5e-06, + "litellm_provider": "text-completion-openai", + "max_input_tokens": 8192, + "max_output_tokens": 4097, + "max_tokens": 4097, + "mode": "completion", + "output_cost_per_token": 2e-06 + }, + "gpt-4": { + "input_cost_per_token": 3e-05, + "litellm_provider": "openai", + "max_input_tokens": 8192, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 6e-05, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "gpt-4-0125-preview": { + "input_cost_per_token": 1e-05, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 3e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "gpt-4-0314": { + "input_cost_per_token": 3e-05, + "litellm_provider": "openai", + "max_input_tokens": 8192, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 6e-05, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "gpt-4-0613": { + "deprecation_date": "2025-06-06", + "input_cost_per_token": 3e-05, + "litellm_provider": "openai", + "max_input_tokens": 8192, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 6e-05, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "gpt-4-1106-preview": { + "input_cost_per_token": 1e-05, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 3e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "gpt-4-1106-vision-preview": { + "deprecation_date": "2024-12-06", + "input_cost_per_token": 1e-05, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 3e-05, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "gpt-4-32k": { + "input_cost_per_token": 6e-05, + "litellm_provider": "openai", + "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 + }, + "gpt-4-32k-0314": { + "input_cost_per_token": 6e-05, + "litellm_provider": "openai", + "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 + }, + "gpt-4-32k-0613": { + "input_cost_per_token": 6e-05, + "litellm_provider": "openai", + "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 + }, + "gpt-4-turbo": { + "input_cost_per_token": 1e-05, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 3e-05, + "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 + }, + "gpt-4-turbo-2024-04-09": { + "input_cost_per_token": 1e-05, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 3e-05, + "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 + }, + "gpt-4-turbo-preview": { + "input_cost_per_token": 1e-05, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 3e-05, + "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 + }, + "gpt-4-vision-preview": { + "deprecation_date": "2024-12-06", + "input_cost_per_token": 1e-05, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 3e-05, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "gpt-4.1": { + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_priority": 8.75e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_batches": 1e-06, + "input_cost_per_token_priority": 3.5e-06, + "litellm_provider": "openai", + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 8e-06, + "output_cost_per_token_batches": 4e-06, + "output_cost_per_token_priority": 1.4e-05, + "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 + }, + "gpt-4.1-2025-04-14": { + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_batches": 1e-06, + "litellm_provider": "openai", + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 8e-06, + "output_cost_per_token_batches": 4e-06, + "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 + }, + "gpt-4.1-mini": { + "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_priority": 1.75e-07, + "input_cost_per_token": 4e-07, + "input_cost_per_token_batches": 2e-07, + "input_cost_per_token_priority": 7e-07, + "litellm_provider": "openai", + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 1.6e-06, + "output_cost_per_token_batches": 8e-07, + "output_cost_per_token_priority": 2.8e-06, + "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 + }, + "gpt-4.1-mini-2025-04-14": { + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 4e-07, + "input_cost_per_token_batches": 2e-07, + "litellm_provider": "openai", + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 1.6e-06, + "output_cost_per_token_batches": 8e-07, + "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 + }, + "gpt-4.1-nano": { + "cache_read_input_token_cost": 2.5e-08, + "cache_read_input_token_cost_priority": 5e-08, + "input_cost_per_token": 1e-07, + "input_cost_per_token_batches": 5e-08, + "input_cost_per_token_priority": 2e-07, + "litellm_provider": "openai", + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 4e-07, + "output_cost_per_token_batches": 2e-07, + "output_cost_per_token_priority": 8e-07, + "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 + }, + "gpt-4.1-nano-2025-04-14": { + "cache_read_input_token_cost": 2.5e-08, + "input_cost_per_token": 1e-07, + "input_cost_per_token_batches": 5e-08, + "litellm_provider": "openai", + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 4e-07, + "output_cost_per_token_batches": 2e-07, + "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 + }, + "gpt-4.5-preview": { + "cache_read_input_token_cost": 3.75e-05, + "input_cost_per_token": 7.5e-05, + "input_cost_per_token_batches": 3.75e-05, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 0.00015, + "output_cost_per_token_batches": 7.5e-05, + "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 + }, + "gpt-4.5-preview-2025-02-27": { + "cache_read_input_token_cost": 3.75e-05, + "deprecation_date": "2025-07-14", + "input_cost_per_token": 7.5e-05, + "input_cost_per_token_batches": 3.75e-05, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 0.00015, + "output_cost_per_token_batches": 7.5e-05, + "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 + }, + "gpt-4o": { + "cache_read_input_token_cost": 1.25e-06, + "cache_read_input_token_cost_priority": 2.125e-06, + "input_cost_per_token": 2.5e-06, + "input_cost_per_token_batches": 1.25e-06, + "input_cost_per_token_priority": 4.25e-06, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "output_cost_per_token_priority": 1.7e-05, + "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 + }, + "gpt-4o-2024-05-13": { + "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-06, + "input_cost_per_token_priority": 8.75e-06, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "output_cost_per_token_batches": 7.5e-06, + "output_cost_per_token_priority": 2.625e-05, + "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 + }, + "gpt-4o-2024-08-06": { + "cache_read_input_token_cost": 1.25e-06, + "input_cost_per_token": 2.5e-06, + "input_cost_per_token_batches": 1.25e-06, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "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 + }, + "gpt-4o-2024-11-20": { + "cache_read_input_token_cost": 1.25e-06, + "input_cost_per_token": 2.5e-06, + "input_cost_per_token_batches": 1.25e-06, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "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 + }, + "gpt-4o-audio-preview": { + "input_cost_per_audio_token": 0.0001, + "input_cost_per_token": 2.5e-06, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_audio_token": 0.0002, + "output_cost_per_token": 1e-05, + "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 + }, + "gpt-4o-audio-preview-2024-10-01": { + "input_cost_per_audio_token": 0.0001, + "input_cost_per_token": 2.5e-06, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_audio_token": 0.0002, + "output_cost_per_token": 1e-05, + "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 + }, + "gpt-4o-audio-preview-2024-12-17": { + "input_cost_per_audio_token": 4e-05, + "input_cost_per_token": 2.5e-06, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_audio_token": 8e-05, + "output_cost_per_token": 1e-05, + "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 + }, + "gpt-4o-audio-preview-2025-06-03": { + "input_cost_per_audio_token": 4e-05, + "input_cost_per_token": 2.5e-06, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_audio_token": 8e-05, + "output_cost_per_token": 1e-05, + "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 + }, + "gpt-4o-mini": { + "cache_read_input_token_cost": 7.5e-08, + "cache_read_input_token_cost_priority": 1.25e-07, + "input_cost_per_token": 1.5e-07, + "input_cost_per_token_batches": 7.5e-08, + "input_cost_per_token_priority": 2.5e-07, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 6e-07, + "output_cost_per_token_batches": 3e-07, + "output_cost_per_token_priority": 1e-06, + "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 + }, + "gpt-4o-mini-2024-07-18": { + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_token": 1.5e-07, + "input_cost_per_token_batches": 7.5e-08, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 6e-07, + "output_cost_per_token_batches": 3e-07, + "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 + }, + "gpt-4o-mini-audio-preview": { + "input_cost_per_audio_token": 1e-05, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_audio_token": 2e-05, + "output_cost_per_token": 6e-07, + "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 + }, + "gpt-4o-mini-audio-preview-2024-12-17": { + "input_cost_per_audio_token": 1e-05, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_audio_token": 2e-05, + "output_cost_per_token": 6e-07, + "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 + }, + "gpt-4o-mini-realtime-preview": { + "cache_creation_input_audio_token_cost": 3e-07, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_audio_token": 1e-05, + "input_cost_per_token": 6e-07, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_audio_token": 2e-05, + "output_cost_per_token": 2.4e-06, + "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 + }, + "gpt-4o-mini-realtime-preview-2024-12-17": { + "cache_creation_input_audio_token_cost": 3e-07, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_audio_token": 1e-05, + "input_cost_per_token": 6e-07, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_audio_token": 2e-05, + "output_cost_per_token": 2.4e-06, + "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 + }, + "gpt-4o-mini-search-preview": { + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_token": 1.5e-07, + "input_cost_per_token_batches": 7.5e-08, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 6e-07, + "output_cost_per_token_batches": 3e-07, + "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 + }, + "gpt-4o-mini-search-preview-2025-03-11": { + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_token": 1.5e-07, + "input_cost_per_token_batches": 7.5e-08, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 6e-07, + "output_cost_per_token_batches": 3e-07, + "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 + }, + "gpt-4o-mini-transcribe": { + "input_cost_per_audio_token": 3e-06, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "openai", + "max_input_tokens": 16000, + "max_output_tokens": 2000, + "mode": "audio_transcription", + "output_cost_per_token": 5e-06, + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "gpt-4o-mini-tts": { + "input_cost_per_token": 2.5e-06, + "litellm_provider": "openai", + "mode": "audio_speech", + "output_cost_per_audio_token": 1.2e-05, + "output_cost_per_second": 0.00025, + "output_cost_per_token": 1e-05, + "supported_endpoints": [ + "/v1/audio/speech" + ], + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "audio" + ] + }, + "gpt-4o-realtime-preview": { + "cache_read_input_token_cost": 2.5e-06, + "input_cost_per_audio_token": 4e-05, + "input_cost_per_token": 5e-06, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_audio_token": 8e-05, + "output_cost_per_token": 2e-05, + "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 + }, + "gpt-4o-realtime-preview-2024-10-01": { + "cache_creation_input_audio_token_cost": 2e-05, + "cache_read_input_token_cost": 2.5e-06, + "input_cost_per_audio_token": 0.0001, + "input_cost_per_token": 5e-06, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_audio_token": 0.0002, + "output_cost_per_token": 2e-05, + "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 + }, + "gpt-4o-realtime-preview-2024-12-17": { + "cache_read_input_token_cost": 2.5e-06, + "input_cost_per_audio_token": 4e-05, + "input_cost_per_token": 5e-06, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_audio_token": 8e-05, + "output_cost_per_token": 2e-05, + "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 + }, + "gpt-4o-realtime-preview-2025-06-03": { + "cache_read_input_token_cost": 2.5e-06, + "input_cost_per_audio_token": 4e-05, + "input_cost_per_token": 5e-06, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_audio_token": 8e-05, + "output_cost_per_token": 2e-05, + "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 + }, + "gpt-4o-search-preview": { + "cache_read_input_token_cost": 1.25e-06, + "input_cost_per_token": 2.5e-06, + "input_cost_per_token_batches": 1.25e-06, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "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 + }, + "gpt-4o-search-preview-2025-03-11": { + "cache_read_input_token_cost": 1.25e-06, + "input_cost_per_token": 2.5e-06, + "input_cost_per_token_batches": 1.25e-06, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "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 + }, + "gpt-4o-transcribe": { + "input_cost_per_audio_token": 6e-06, + "input_cost_per_token": 2.5e-06, + "litellm_provider": "openai", + "max_input_tokens": 16000, + "max_output_tokens": 2000, + "mode": "audio_transcription", + "output_cost_per_token": 1e-05, + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "gpt-5": { + "cache_read_input_token_cost": 1.25e-07, + "cache_read_input_token_cost_flex": 6.25e-08, + "cache_read_input_token_cost_priority": 2.5e-07, + "input_cost_per_token": 1.25e-06, + "input_cost_per_token_flex": 6.25e-07, + "input_cost_per_token_priority": 2.5e-06, + "litellm_provider": "openai", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_flex": 5e-06, + "output_cost_per_token_priority": 2e-05, + "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 + }, + "gpt-5-2025-08-07": { + "cache_read_input_token_cost": 1.25e-07, + "cache_read_input_token_cost_flex": 6.25e-08, + "cache_read_input_token_cost_priority": 2.5e-07, + "input_cost_per_token": 1.25e-06, + "input_cost_per_token_flex": 6.25e-07, + "input_cost_per_token_priority": 2.5e-06, + "litellm_provider": "openai", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_flex": 5e-06, + "output_cost_per_token_priority": 2e-05, + "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 + }, + "gpt-5-chat": { + "cache_read_input_token_cost": 1.25e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "openai", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "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 + }, + "gpt-5-chat-latest": { + "cache_read_input_token_cost": 1.25e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "openai", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "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 + }, + "gpt-5-codex": { + "cache_read_input_token_cost": 1.25e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "openai", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "responses", + "output_cost_per_token": 1e-05, + "supported_endpoints": [ + "/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": false, + "supports_response_schema": true, + "supports_system_messages": false, + "supports_tool_choice": true, + "supports_vision": true + }, + "gpt-5-mini": { + "cache_read_input_token_cost": 2.5e-08, + "cache_read_input_token_cost_flex": 1.25e-08, + "cache_read_input_token_cost_priority": 4.5e-08, + "input_cost_per_token": 2.5e-07, + "input_cost_per_token_flex": 1.25e-07, + "input_cost_per_token_priority": 4.5e-07, + "litellm_provider": "openai", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2e-06, + "output_cost_per_token_flex": 1e-06, + "output_cost_per_token_priority": 3.6e-06, + "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 + }, + "gpt-5-mini-2025-08-07": { + "cache_read_input_token_cost": 2.5e-08, + "cache_read_input_token_cost_flex": 1.25e-08, + "cache_read_input_token_cost_priority": 4.5e-08, + "input_cost_per_token": 2.5e-07, + "input_cost_per_token_flex": 1.25e-07, + "input_cost_per_token_priority": 4.5e-07, + "litellm_provider": "openai", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2e-06, + "output_cost_per_token_flex": 1e-06, + "output_cost_per_token_priority": 3.6e-06, + "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 + }, + "gpt-5-nano": { + "cache_read_input_token_cost": 5e-09, + "cache_read_input_token_cost_flex": 2.5e-09, + "input_cost_per_token": 5e-08, + "input_cost_per_token_flex": 2.5e-08, + "input_cost_per_token_priority": 2.5e-06, + "litellm_provider": "openai", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4e-07, + "output_cost_per_token_flex": 2e-07, + "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 + }, + "gpt-5-nano-2025-08-07": { + "cache_read_input_token_cost": 5e-09, + "cache_read_input_token_cost_flex": 2.5e-09, + "input_cost_per_token": 5e-08, + "input_cost_per_token_flex": 2.5e-08, + "litellm_provider": "openai", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4e-07, + "output_cost_per_token_flex": 2e-07, + "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 + }, + "gpt-image-1": { + "input_cost_per_pixel": 4.0054321e-08, + "litellm_provider": "openai", + "mode": "image_generation", + "output_cost_per_pixel": 0.0, + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "gpt-realtime": { + "cache_creation_input_audio_token_cost": 4e-07, + "cache_read_input_token_cost": 4e-07, + "input_cost_per_audio_token": 3.2e-05, + "input_cost_per_image": 5e-06, + "input_cost_per_token": 4e-06, + "litellm_provider": "openai", + "max_input_tokens": 32000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_audio_token": 6.4e-05, + "output_cost_per_token": 1.6e-05, + "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 + }, + "gpt-realtime-2025-08-28": { + "cache_creation_input_audio_token_cost": 4e-07, + "cache_read_input_token_cost": 4e-07, + "input_cost_per_audio_token": 3.2e-05, + "input_cost_per_image": 5e-06, + "input_cost_per_token": 4e-06, + "litellm_provider": "openai", + "max_input_tokens": 32000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_audio_token": 6.4e-05, + "output_cost_per_token": 1.6e-05, + "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 + }, + "gradient_ai/alibaba-qwen3-32b": { + "litellm_provider": "gradient_ai", + "max_tokens": 2048, + "mode": "chat", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supported_modalities": [ + "text" + ], + "supports_tool_choice": false + }, + "gradient_ai/anthropic-claude-3-opus": { + "input_cost_per_token": 1.5e-05, + "litellm_provider": "gradient_ai", + "max_tokens": 1024, + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supported_modalities": [ + "text" + ], + "supports_tool_choice": false + }, + "gradient_ai/anthropic-claude-3.5-haiku": { + "input_cost_per_token": 8e-07, + "litellm_provider": "gradient_ai", + "max_tokens": 1024, + "mode": "chat", + "output_cost_per_token": 4e-06, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supported_modalities": [ + "text" + ], + "supports_tool_choice": false + }, + "gradient_ai/anthropic-claude-3.5-sonnet": { + "input_cost_per_token": 3e-06, + "litellm_provider": "gradient_ai", + "max_tokens": 1024, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supported_modalities": [ + "text" + ], + "supports_tool_choice": false + }, + "gradient_ai/anthropic-claude-3.7-sonnet": { + "input_cost_per_token": 3e-06, + "litellm_provider": "gradient_ai", + "max_tokens": 1024, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supported_modalities": [ + "text" + ], + "supports_tool_choice": false + }, + "gradient_ai/deepseek-r1-distill-llama-70b": { + "input_cost_per_token": 9.9e-07, + "litellm_provider": "gradient_ai", + "max_tokens": 8000, + "mode": "chat", + "output_cost_per_token": 9.9e-07, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supported_modalities": [ + "text" + ], + "supports_tool_choice": false + }, + "gradient_ai/llama3-8b-instruct": { + "input_cost_per_token": 2e-07, + "litellm_provider": "gradient_ai", + "max_tokens": 512, + "mode": "chat", + "output_cost_per_token": 2e-07, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supported_modalities": [ + "text" + ], + "supports_tool_choice": false + }, + "gradient_ai/llama3.3-70b-instruct": { + "input_cost_per_token": 6.5e-07, + "litellm_provider": "gradient_ai", + "max_tokens": 2048, + "mode": "chat", + "output_cost_per_token": 6.5e-07, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supported_modalities": [ + "text" + ], + "supports_tool_choice": false + }, + "gradient_ai/mistral-nemo-instruct-2407": { + "input_cost_per_token": 3e-07, + "litellm_provider": "gradient_ai", + "max_tokens": 512, + "mode": "chat", + "output_cost_per_token": 3e-07, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supported_modalities": [ + "text" + ], + "supports_tool_choice": false + }, + "gradient_ai/openai-gpt-4o": { + "litellm_provider": "gradient_ai", + "max_tokens": 16384, + "mode": "chat", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supported_modalities": [ + "text" + ], + "supports_tool_choice": false + }, + "gradient_ai/openai-gpt-4o-mini": { + "litellm_provider": "gradient_ai", + "max_tokens": 16384, + "mode": "chat", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supported_modalities": [ + "text" + ], + "supports_tool_choice": false + }, + "gradient_ai/openai-o3": { + "input_cost_per_token": 2e-06, + "litellm_provider": "gradient_ai", + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 8e-06, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supported_modalities": [ + "text" + ], + "supports_tool_choice": false + }, + "gradient_ai/openai-o3-mini": { + "input_cost_per_token": 1.1e-06, + "litellm_provider": "gradient_ai", + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supported_modalities": [ + "text" + ], + "supports_tool_choice": false + }, + "groq/deepseek-r1-distill-llama-70b": { + "input_cost_per_token": 7.5e-07, + "litellm_provider": "groq", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 9.9e-07, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "groq/distil-whisper-large-v3-en": { + "input_cost_per_second": 5.56e-06, + "litellm_provider": "groq", + "mode": "audio_transcription", + "output_cost_per_second": 0.0 + }, + "groq/gemma-7b-it": { + "deprecation_date": "2024-12-18", + "input_cost_per_token": 7e-08, + "litellm_provider": "groq", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 7e-08, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "groq/gemma2-9b-it": { + "input_cost_per_token": 2e-07, + "litellm_provider": "groq", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2e-07, + "supports_function_calling": false, + "supports_response_schema": true, + "supports_tool_choice": false + }, + "groq/llama-3.1-405b-reasoning": { + "input_cost_per_token": 5.9e-07, + "litellm_provider": "groq", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 7.9e-07, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "groq/llama-3.1-70b-versatile": { + "deprecation_date": "2025-01-24", + "input_cost_per_token": 5.9e-07, + "litellm_provider": "groq", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 7.9e-07, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "groq/llama-3.1-8b-instant": { + "input_cost_per_token": 5e-08, + "litellm_provider": "groq", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 8e-08, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "groq/llama-3.2-11b-text-preview": { + "deprecation_date": "2024-10-28", + "input_cost_per_token": 1.8e-07, + "litellm_provider": "groq", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.8e-07, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "groq/llama-3.2-11b-vision-preview": { + "deprecation_date": "2025-04-14", + "input_cost_per_token": 1.8e-07, + "litellm_provider": "groq", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.8e-07, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "groq/llama-3.2-1b-preview": { + "deprecation_date": "2025-04-14", + "input_cost_per_token": 4e-08, + "litellm_provider": "groq", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 4e-08, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "groq/llama-3.2-3b-preview": { + "deprecation_date": "2025-04-14", + "input_cost_per_token": 6e-08, + "litellm_provider": "groq", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 6e-08, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "groq/llama-3.2-90b-text-preview": { + "deprecation_date": "2024-11-25", + "input_cost_per_token": 9e-07, + "litellm_provider": "groq", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 9e-07, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "groq/llama-3.2-90b-vision-preview": { + "deprecation_date": "2025-04-14", + "input_cost_per_token": 9e-07, + "litellm_provider": "groq", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 9e-07, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "groq/llama-3.3-70b-specdec": { + "deprecation_date": "2025-04-14", + "input_cost_per_token": 5.9e-07, + "litellm_provider": "groq", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 9.9e-07, + "supports_tool_choice": true + }, + "groq/llama-3.3-70b-versatile": { + "input_cost_per_token": 5.9e-07, + "litellm_provider": "groq", + "max_input_tokens": 128000, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 7.9e-07, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "groq/llama-guard-3-8b": { + "input_cost_per_token": 2e-07, + "litellm_provider": "groq", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2e-07 + }, + "groq/llama2-70b-4096": { + "input_cost_per_token": 7e-07, + "litellm_provider": "groq", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 8e-07, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "groq/llama3-groq-70b-8192-tool-use-preview": { + "deprecation_date": "2025-01-06", + "input_cost_per_token": 8.9e-07, + "litellm_provider": "groq", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 8.9e-07, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "groq/llama3-groq-8b-8192-tool-use-preview": { + "deprecation_date": "2025-01-06", + "input_cost_per_token": 1.9e-07, + "litellm_provider": "groq", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.9e-07, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "groq/meta-llama/llama-4-maverick-17b-128e-instruct": { + "input_cost_per_token": 2e-07, + "litellm_provider": "groq", + "max_input_tokens": 131072, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 6e-07, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "groq/meta-llama/llama-4-scout-17b-16e-instruct": { + "input_cost_per_token": 1.1e-07, + "litellm_provider": "groq", + "max_input_tokens": 131072, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 3.4e-07, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "groq/mistral-saba-24b": { + "input_cost_per_token": 7.9e-07, + "litellm_provider": "groq", + "max_input_tokens": 32000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 7.9e-07 + }, + "groq/mixtral-8x7b-32768": { + "deprecation_date": "2025-03-20", + "input_cost_per_token": 2.4e-07, + "litellm_provider": "groq", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 2.4e-07, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "groq/moonshotai/kimi-k2-instruct": { + "input_cost_per_token": 1e-06, + "litellm_provider": "groq", + "max_input_tokens": 131072, + "max_output_tokens": 16384, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 3e-06, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "groq/openai/gpt-oss-120b": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "groq", + "max_input_tokens": 131072, + "max_output_tokens": 32766, + "max_tokens": 32766, + "mode": "chat", + "output_cost_per_token": 7.5e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_web_search": true + }, + "groq/openai/gpt-oss-20b": { + "input_cost_per_token": 1e-07, + "litellm_provider": "groq", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 5e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_web_search": true + }, + "groq/playai-tts": { + "input_cost_per_character": 5e-05, + "litellm_provider": "groq", + "max_input_tokens": 10000, + "max_output_tokens": 10000, + "max_tokens": 10000, + "mode": "audio_speech" + }, + "groq/qwen/qwen3-32b": { + "input_cost_per_token": 2.9e-07, + "litellm_provider": "groq", + "max_input_tokens": 131000, + "max_output_tokens": 131000, + "max_tokens": 131000, + "mode": "chat", + "output_cost_per_token": 5.9e-07, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "groq/whisper-large-v3": { + "input_cost_per_second": 3.083e-05, + "litellm_provider": "groq", + "mode": "audio_transcription", + "output_cost_per_second": 0.0 + }, + "groq/whisper-large-v3-turbo": { + "input_cost_per_second": 1.111e-05, + "litellm_provider": "groq", + "mode": "audio_transcription", + "output_cost_per_second": 0.0 + }, + "hd/1024-x-1024/dall-e-3": { + "input_cost_per_pixel": 7.629e-08, + "litellm_provider": "openai", + "mode": "image_generation", + "output_cost_per_pixel": 0.0 + }, + "hd/1024-x-1792/dall-e-3": { + "input_cost_per_pixel": 6.539e-08, + "litellm_provider": "openai", + "mode": "image_generation", + "output_cost_per_pixel": 0.0 + }, + "hd/1792-x-1024/dall-e-3": { + "input_cost_per_pixel": 6.539e-08, + "litellm_provider": "openai", + "mode": "image_generation", + "output_cost_per_pixel": 0.0 + }, + "heroku/claude-3-5-haiku": { + "litellm_provider": "heroku", + "max_tokens": 4096, + "mode": "chat", + "supports_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "heroku/claude-3-5-sonnet-latest": { + "litellm_provider": "heroku", + "max_tokens": 8192, + "mode": "chat", + "supports_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "heroku/claude-3-7-sonnet": { + "litellm_provider": "heroku", + "max_tokens": 8192, + "mode": "chat", + "supports_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "heroku/claude-4-sonnet": { + "litellm_provider": "heroku", + "max_tokens": 8192, + "mode": "chat", + "supports_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "high/1024-x-1024/gpt-image-1": { + "input_cost_per_pixel": 1.59263611e-07, + "litellm_provider": "openai", + "mode": "image_generation", + "output_cost_per_pixel": 0.0, + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "high/1024-x-1536/gpt-image-1": { + "input_cost_per_pixel": 1.58945719e-07, + "litellm_provider": "openai", + "mode": "image_generation", + "output_cost_per_pixel": 0.0, + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "high/1536-x-1024/gpt-image-1": { + "input_cost_per_pixel": 1.58945719e-07, + "litellm_provider": "openai", + "mode": "image_generation", + "output_cost_per_pixel": 0.0, + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "hyperbolic/NousResearch/Hermes-3-Llama-3.1-70B": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "hyperbolic", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 3e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "hyperbolic/Qwen/QwQ-32B": { + "input_cost_per_token": 2e-07, + "litellm_provider": "hyperbolic", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "hyperbolic/Qwen/Qwen2.5-72B-Instruct": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "hyperbolic", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 3e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "hyperbolic/Qwen/Qwen2.5-Coder-32B-Instruct": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "hyperbolic", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 3e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "hyperbolic/Qwen/Qwen3-235B-A22B": { + "input_cost_per_token": 2e-06, + "litellm_provider": "hyperbolic", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2e-06, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "hyperbolic/deepseek-ai/DeepSeek-R1": { + "input_cost_per_token": 4e-07, + "litellm_provider": "hyperbolic", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 4e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "hyperbolic/deepseek-ai/DeepSeek-R1-0528": { + "input_cost_per_token": 2.5e-07, + "litellm_provider": "hyperbolic", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.5e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "hyperbolic/deepseek-ai/DeepSeek-V3": { + "input_cost_per_token": 2e-07, + "litellm_provider": "hyperbolic", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 2e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "hyperbolic/deepseek-ai/DeepSeek-V3-0324": { + "input_cost_per_token": 4e-07, + "litellm_provider": "hyperbolic", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 4e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "hyperbolic/meta-llama/Llama-3.2-3B-Instruct": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "hyperbolic", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 3e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "hyperbolic/meta-llama/Llama-3.3-70B-Instruct": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "hyperbolic", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 3e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "hyperbolic/meta-llama/Meta-Llama-3-70B-Instruct": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "hyperbolic", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 3e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "hyperbolic/meta-llama/Meta-Llama-3.1-405B-Instruct": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "hyperbolic", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 3e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "hyperbolic/meta-llama/Meta-Llama-3.1-70B-Instruct": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "hyperbolic", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 3e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "hyperbolic/meta-llama/Meta-Llama-3.1-8B-Instruct": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "hyperbolic", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 3e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "hyperbolic/moonshotai/Kimi-K2-Instruct": { + "input_cost_per_token": 2e-06, + "litellm_provider": "hyperbolic", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2e-06, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "j2-light": { + "input_cost_per_token": 3e-06, + "litellm_provider": "ai21", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "completion", + "output_cost_per_token": 3e-06 + }, + "j2-mid": { + "input_cost_per_token": 1e-05, + "litellm_provider": "ai21", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "completion", + "output_cost_per_token": 1e-05 + }, + "j2-ultra": { + "input_cost_per_token": 1.5e-05, + "litellm_provider": "ai21", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "completion", + "output_cost_per_token": 1.5e-05 + }, + "jamba-1.5": { + "input_cost_per_token": 2e-07, + "litellm_provider": "ai21", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 4e-07, + "supports_tool_choice": true + }, + "jamba-1.5-large": { + "input_cost_per_token": 2e-06, + "litellm_provider": "ai21", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 8e-06, + "supports_tool_choice": true + }, + "jamba-1.5-large@001": { + "input_cost_per_token": 2e-06, + "litellm_provider": "ai21", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 8e-06, + "supports_tool_choice": true + }, + "jamba-1.5-mini": { + "input_cost_per_token": 2e-07, + "litellm_provider": "ai21", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 4e-07, + "supports_tool_choice": true + }, + "jamba-1.5-mini@001": { + "input_cost_per_token": 2e-07, + "litellm_provider": "ai21", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 4e-07, + "supports_tool_choice": true + }, + "jamba-large-1.6": { + "input_cost_per_token": 2e-06, + "litellm_provider": "ai21", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 8e-06, + "supports_tool_choice": true + }, + "jamba-large-1.7": { + "input_cost_per_token": 2e-06, + "litellm_provider": "ai21", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 8e-06, + "supports_tool_choice": true + }, + "jamba-mini-1.6": { + "input_cost_per_token": 2e-07, + "litellm_provider": "ai21", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 4e-07, + "supports_tool_choice": true + }, + "jamba-mini-1.7": { + "input_cost_per_token": 2e-07, + "litellm_provider": "ai21", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 4e-07, + "supports_tool_choice": true + }, + "jina-reranker-v2-base-multilingual": { + "input_cost_per_token": 1.8e-08, + "litellm_provider": "jina_ai", + "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-08 + }, + "lambda_ai/deepseek-llama3.3-70b": { + "input_cost_per_token": 2e-07, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 6e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "lambda_ai/deepseek-r1-0528": { + "input_cost_per_token": 2e-07, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 6e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "lambda_ai/deepseek-r1-671b": { + "input_cost_per_token": 8e-07, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 8e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "lambda_ai/deepseek-v3-0324": { + "input_cost_per_token": 2e-07, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 6e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "lambda_ai/hermes3-405b": { + "input_cost_per_token": 8e-07, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 8e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "lambda_ai/hermes3-70b": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 3e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "lambda_ai/hermes3-8b": { + "input_cost_per_token": 2.5e-08, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4e-08, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "lambda_ai/lfm-40b": { + "input_cost_per_token": 1e-07, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "lambda_ai/lfm-7b": { + "input_cost_per_token": 2.5e-08, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4e-08, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "lambda_ai/llama-4-maverick-17b-128e-instruct-fp8": { + "input_cost_per_token": 5e-08, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 8192, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "lambda_ai/llama-4-scout-17b-16e-instruct": { + "input_cost_per_token": 5e-08, + "litellm_provider": "lambda_ai", + "max_input_tokens": 16384, + "max_output_tokens": 8192, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "lambda_ai/llama3.1-405b-instruct-fp8": { + "input_cost_per_token": 8e-07, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 8e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "lambda_ai/llama3.1-70b-instruct-fp8": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 3e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "lambda_ai/llama3.1-8b-instruct": { + "input_cost_per_token": 2.5e-08, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4e-08, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "lambda_ai/llama3.1-nemotron-70b-instruct-fp8": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 3e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "lambda_ai/llama3.2-11b-vision-instruct": { + "input_cost_per_token": 1.5e-08, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.5e-08, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "lambda_ai/llama3.2-3b-instruct": { + "input_cost_per_token": 1.5e-08, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.5e-08, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "lambda_ai/llama3.3-70b-instruct-fp8": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 3e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "lambda_ai/qwen25-coder-32b-instruct": { + "input_cost_per_token": 5e-08, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "lambda_ai/qwen3-32b-fp8": { + "input_cost_per_token": 5e-08, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "low/1024-x-1024/gpt-image-1": { + "input_cost_per_pixel": 1.0490417e-08, + "litellm_provider": "openai", + "mode": "image_generation", + "output_cost_per_pixel": 0.0, + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "low/1024-x-1536/gpt-image-1": { + "input_cost_per_pixel": 1.0172526e-08, + "litellm_provider": "openai", + "mode": "image_generation", + "output_cost_per_pixel": 0.0, + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "low/1536-x-1024/gpt-image-1": { + "input_cost_per_pixel": 1.0172526e-08, + "litellm_provider": "openai", + "mode": "image_generation", + "output_cost_per_pixel": 0.0, + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "luminous-base": { + "input_cost_per_token": 3e-05, + "litellm_provider": "aleph_alpha", + "max_tokens": 2048, + "mode": "completion", + "output_cost_per_token": 3.3e-05 + }, + "luminous-base-control": { + "input_cost_per_token": 3.75e-05, + "litellm_provider": "aleph_alpha", + "max_tokens": 2048, + "mode": "chat", + "output_cost_per_token": 4.125e-05 + }, + "luminous-extended": { + "input_cost_per_token": 4.5e-05, + "litellm_provider": "aleph_alpha", + "max_tokens": 2048, + "mode": "completion", + "output_cost_per_token": 4.95e-05 + }, + "luminous-extended-control": { + "input_cost_per_token": 5.625e-05, + "litellm_provider": "aleph_alpha", + "max_tokens": 2048, + "mode": "chat", + "output_cost_per_token": 6.1875e-05 + }, + "luminous-supreme": { + "input_cost_per_token": 0.000175, + "litellm_provider": "aleph_alpha", + "max_tokens": 2048, + "mode": "completion", + "output_cost_per_token": 0.0001925 + }, + "luminous-supreme-control": { + "input_cost_per_token": 0.00021875, + "litellm_provider": "aleph_alpha", + "max_tokens": 2048, + "mode": "chat", + "output_cost_per_token": 0.000240625 + }, + "max-x-max/50-steps/stability.stable-diffusion-xl-v0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "max_tokens": 77, + "mode": "image_generation", + "output_cost_per_image": 0.036 + }, + "max-x-max/max-steps/stability.stable-diffusion-xl-v0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "max_tokens": 77, + "mode": "image_generation", + "output_cost_per_image": 0.072 + }, + "medium/1024-x-1024/gpt-image-1": { + "input_cost_per_pixel": 4.0054321e-08, + "litellm_provider": "openai", + "mode": "image_generation", + "output_cost_per_pixel": 0.0, + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "medium/1024-x-1536/gpt-image-1": { + "input_cost_per_pixel": 4.0054321e-08, + "litellm_provider": "openai", + "mode": "image_generation", + "output_cost_per_pixel": 0.0, + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "medium/1536-x-1024/gpt-image-1": { + "input_cost_per_pixel": 4.0054321e-08, + "litellm_provider": "openai", + "mode": "image_generation", + "output_cost_per_pixel": 0.0, + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "medlm-large": { + "input_cost_per_character": 5e-06, + "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 8192, + "max_output_tokens": 1024, + "max_tokens": 1024, + "mode": "chat", + "output_cost_per_character": 1.5e-05, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "supports_tool_choice": true + }, + "medlm-medium": { + "input_cost_per_character": 5e-07, + "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 32768, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_character": 1e-06, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "supports_tool_choice": true + }, + "meta.llama2-13b-chat-v1": { + "input_cost_per_token": 7.5e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1e-06 + }, + "meta.llama2-70b-chat-v1": { + "input_cost_per_token": 1.95e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2.56e-06 + }, + "meta.llama3-1-405b-instruct-v1:0": { + "input_cost_per_token": 5.32e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.6e-05, + "supports_function_calling": true, + "supports_tool_choice": false + }, + "meta.llama3-1-70b-instruct-v1:0": { + "input_cost_per_token": 9.9e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 2048, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 9.9e-07, + "supports_function_calling": true, + "supports_tool_choice": false + }, + "meta.llama3-1-8b-instruct-v1:0": { + "input_cost_per_token": 2.2e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 2048, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.2e-07, + "supports_function_calling": true, + "supports_tool_choice": false + }, + "meta.llama3-2-11b-instruct-v1:0": { + "input_cost_per_token": 3.5e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3.5e-07, + "supports_function_calling": true, + "supports_tool_choice": false, + "supports_vision": true + }, + "meta.llama3-2-1b-instruct-v1:0": { + "input_cost_per_token": 1e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-07, + "supports_function_calling": true, + "supports_tool_choice": false + }, + "meta.llama3-2-3b-instruct-v1:0": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.5e-07, + "supports_function_calling": true, + "supports_tool_choice": false + }, + "meta.llama3-2-90b-instruct-v1:0": { + "input_cost_per_token": 2e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2e-06, + "supports_function_calling": true, + "supports_tool_choice": false, + "supports_vision": true + }, + "meta.llama3-3-70b-instruct-v1:0": { + "input_cost_per_token": 7.2e-07, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 7.2e-07, + "supports_function_calling": true, + "supports_tool_choice": false + }, + "meta.llama3-70b-instruct-v1:0": { + "input_cost_per_token": 2.65e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 3.5e-06 + }, + "meta.llama3-8b-instruct-v1:0": { + "input_cost_per_token": 3e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 6e-07 + }, + "meta.llama4-maverick-17b-instruct-v1:0": { + "input_cost_per_token": 2.4e-07, + "input_cost_per_token_batches": 1.2e-07, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 9.7e-07, + "output_cost_per_token_batches": 4.85e-07, + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text", + "code" + ], + "supports_function_calling": true, + "supports_tool_choice": false + }, + "meta.llama4-scout-17b-instruct-v1:0": { + "input_cost_per_token": 1.7e-07, + "input_cost_per_token_batches": 8.5e-08, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 6.6e-07, + "output_cost_per_token_batches": 3.3e-07, + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text", + "code" + ], + "supports_function_calling": true, + "supports_tool_choice": false + }, + "meta_llama/Llama-3.3-70B-Instruct": { + "litellm_provider": "meta_llama", + "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 + }, + "meta_llama/Llama-3.3-8B-Instruct": { + "litellm_provider": "meta_llama", + "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 + }, + "meta_llama/Llama-4-Maverick-17B-128E-Instruct-FP8": { + "litellm_provider": "meta_llama", + "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 + }, + "meta_llama/Llama-4-Scout-17B-16E-Instruct-FP8": { + "litellm_provider": "meta_llama", + "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 + }, + "mistral.mistral-7b-instruct-v0:2": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 2e-07, + "supports_tool_choice": true + }, + "mistral.mistral-large-2402-v1:0": { + "input_cost_per_token": 8e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 2.4e-05, + "supports_function_calling": true + }, + "mistral.mistral-large-2407-v1:0": { + "input_cost_per_token": 3e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 9e-06, + "supports_function_calling": true, + "supports_tool_choice": true + }, + "mistral.mistral-small-2402-v1:0": { + "input_cost_per_token": 1e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 3e-06, + "supports_function_calling": true + }, + "mistral.mixtral-8x7b-instruct-v0:1": { + "input_cost_per_token": 4.5e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 7e-07, + "supports_tool_choice": true + }, + "mistral/codestral-2405": { + "input_cost_per_token": 1e-06, + "litellm_provider": "mistral", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 3e-06, + "supports_assistant_prefill": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/codestral-latest": { + "input_cost_per_token": 1e-06, + "litellm_provider": "mistral", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 3e-06, + "supports_assistant_prefill": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/codestral-mamba-latest": { + "input_cost_per_token": 2.5e-07, + "litellm_provider": "mistral", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 2.5e-07, + "source": "https://mistral.ai/technology/", + "supports_assistant_prefill": true, + "supports_tool_choice": true + }, + "mistral/devstral-medium-2507": { + "input_cost_per_token": 4e-07, + "litellm_provider": "mistral", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2e-06, + "source": "https://mistral.ai/news/devstral", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/devstral-small-2505": { + "input_cost_per_token": 1e-07, + "litellm_provider": "mistral", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3e-07, + "source": "https://mistral.ai/news/devstral", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/devstral-small-2507": { + "input_cost_per_token": 1e-07, + "litellm_provider": "mistral", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3e-07, + "source": "https://mistral.ai/news/devstral", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/magistral-medium-2506": { + "input_cost_per_token": 2e-06, + "litellm_provider": "mistral", + "max_input_tokens": 40000, + "max_output_tokens": 40000, + "max_tokens": 40000, + "mode": "chat", + "output_cost_per_token": 5e-06, + "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 + }, + "mistral/magistral-medium-latest": { + "input_cost_per_token": 2e-06, + "litellm_provider": "mistral", + "max_input_tokens": 40000, + "max_output_tokens": 40000, + "max_tokens": 40000, + "mode": "chat", + "output_cost_per_token": 5e-06, + "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 + }, + "mistral/magistral-small-2506": { + "input_cost_per_token": 5e-07, + "litellm_provider": "mistral", + "max_input_tokens": 40000, + "max_output_tokens": 40000, + "max_tokens": 40000, + "mode": "chat", + "output_cost_per_token": 1.5e-06, + "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 + }, + "mistral/magistral-small-latest": { + "input_cost_per_token": 5e-07, + "litellm_provider": "mistral", + "max_input_tokens": 40000, + "max_output_tokens": 40000, + "max_tokens": 40000, + "mode": "chat", + "output_cost_per_token": 1.5e-06, + "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 + }, + "mistral/mistral-embed": { + "input_cost_per_token": 1e-07, + "litellm_provider": "mistral", + "max_input_tokens": 8192, + "max_tokens": 8192, + "mode": "embedding" + }, + "mistral/mistral-large-2402": { + "input_cost_per_token": 4e-06, + "litellm_provider": "mistral", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 1.2e-05, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/mistral-large-2407": { + "input_cost_per_token": 3e-06, + "litellm_provider": "mistral", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 9e-06, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/mistral-large-2411": { + "input_cost_per_token": 2e-06, + "litellm_provider": "mistral", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-06, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/mistral-large-latest": { + "input_cost_per_token": 2e-06, + "litellm_provider": "mistral", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-06, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/mistral-medium": { + "input_cost_per_token": 2.7e-06, + "litellm_provider": "mistral", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 8.1e-06, + "supports_assistant_prefill": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/mistral-medium-2312": { + "input_cost_per_token": 2.7e-06, + "litellm_provider": "mistral", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 8.1e-06, + "supports_assistant_prefill": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/mistral-medium-2505": { + "input_cost_per_token": 4e-07, + "litellm_provider": "mistral", + "max_input_tokens": 131072, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 2e-06, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/mistral-medium-latest": { + "input_cost_per_token": 4e-07, + "litellm_provider": "mistral", + "max_input_tokens": 131072, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 2e-06, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/mistral-small": { + "input_cost_per_token": 1e-07, + "litellm_provider": "mistral", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 3e-07, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/mistral-small-latest": { + "input_cost_per_token": 1e-07, + "litellm_provider": "mistral", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 3e-07, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/mistral-tiny": { + "input_cost_per_token": 2.5e-07, + "litellm_provider": "mistral", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 2.5e-07, + "supports_assistant_prefill": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/open-codestral-mamba": { + "input_cost_per_token": 2.5e-07, + "litellm_provider": "mistral", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 2.5e-07, + "source": "https://mistral.ai/technology/", + "supports_assistant_prefill": true, + "supports_tool_choice": true + }, + "mistral/open-mistral-7b": { + "input_cost_per_token": 2.5e-07, + "litellm_provider": "mistral", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 2.5e-07, + "supports_assistant_prefill": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/open-mistral-nemo": { + "input_cost_per_token": 3e-07, + "litellm_provider": "mistral", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3e-07, + "source": "https://mistral.ai/technology/", + "supports_assistant_prefill": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/open-mistral-nemo-2407": { + "input_cost_per_token": 3e-07, + "litellm_provider": "mistral", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3e-07, + "source": "https://mistral.ai/technology/", + "supports_assistant_prefill": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/open-mixtral-8x22b": { + "input_cost_per_token": 2e-06, + "litellm_provider": "mistral", + "max_input_tokens": 65336, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 6e-06, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/open-mixtral-8x7b": { + "input_cost_per_token": 7e-07, + "litellm_provider": "mistral", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 7e-07, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/pixtral-12b-2409": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "mistral", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.5e-07, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "mistral/pixtral-large-2411": { + "input_cost_per_token": 2e-06, + "litellm_provider": "mistral", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-06, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "mistral/pixtral-large-latest": { + "input_cost_per_token": 2e-06, + "litellm_provider": "mistral", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-06, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "moonshot/kimi-k2-0711-preview": { + "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token": 6e-07, + "litellm_provider": "moonshot", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.5e-06, + "source": "https://platform.moonshot.ai/docs/pricing/chat#generation-model-kimi-k2", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_web_search": true + }, + "moonshot/kimi-latest": { + "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "moonshot", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 5e-06, + "source": "https://platform.moonshot.ai/docs/pricing", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "moonshot/kimi-latest-128k": { + "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "moonshot", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 5e-06, + "source": "https://platform.moonshot.ai/docs/pricing", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "moonshot/kimi-latest-32k": { + "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token": 1e-06, + "litellm_provider": "moonshot", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 3e-06, + "source": "https://platform.moonshot.ai/docs/pricing", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "moonshot/kimi-latest-8k": { + "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token": 2e-07, + "litellm_provider": "moonshot", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2e-06, + "source": "https://platform.moonshot.ai/docs/pricing", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "moonshot/kimi-thinking-preview": { + "input_cost_per_token": 3e-05, + "litellm_provider": "moonshot", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 3e-05, + "source": "https://platform.moonshot.ai/docs/pricing", + "supports_vision": true + }, + "moonshot/moonshot-v1-128k": { + "input_cost_per_token": 2e-06, + "litellm_provider": "moonshot", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 5e-06, + "source": "https://platform.moonshot.ai/docs/pricing", + "supports_function_calling": true, + "supports_tool_choice": true + }, + "moonshot/moonshot-v1-128k-0430": { + "input_cost_per_token": 2e-06, + "litellm_provider": "moonshot", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 5e-06, + "source": "https://platform.moonshot.ai/docs/pricing", + "supports_function_calling": true, + "supports_tool_choice": true + }, + "moonshot/moonshot-v1-128k-vision-preview": { + "input_cost_per_token": 2e-06, + "litellm_provider": "moonshot", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 5e-06, + "source": "https://platform.moonshot.ai/docs/pricing", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "moonshot/moonshot-v1-32k": { + "input_cost_per_token": 1e-06, + "litellm_provider": "moonshot", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 3e-06, + "source": "https://platform.moonshot.ai/docs/pricing", + "supports_function_calling": true, + "supports_tool_choice": true + }, + "moonshot/moonshot-v1-32k-0430": { + "input_cost_per_token": 1e-06, + "litellm_provider": "moonshot", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 3e-06, + "source": "https://platform.moonshot.ai/docs/pricing", + "supports_function_calling": true, + "supports_tool_choice": true + }, + "moonshot/moonshot-v1-32k-vision-preview": { + "input_cost_per_token": 1e-06, + "litellm_provider": "moonshot", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 3e-06, + "source": "https://platform.moonshot.ai/docs/pricing", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "moonshot/moonshot-v1-8k": { + "input_cost_per_token": 2e-07, + "litellm_provider": "moonshot", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2e-06, + "source": "https://platform.moonshot.ai/docs/pricing", + "supports_function_calling": true, + "supports_tool_choice": true + }, + "moonshot/moonshot-v1-8k-0430": { + "input_cost_per_token": 2e-07, + "litellm_provider": "moonshot", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2e-06, + "source": "https://platform.moonshot.ai/docs/pricing", + "supports_function_calling": true, + "supports_tool_choice": true + }, + "moonshot/moonshot-v1-8k-vision-preview": { + "input_cost_per_token": 2e-07, + "litellm_provider": "moonshot", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2e-06, + "source": "https://platform.moonshot.ai/docs/pricing", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "moonshot/moonshot-v1-auto": { + "input_cost_per_token": 2e-06, + "litellm_provider": "moonshot", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 5e-06, + "source": "https://platform.moonshot.ai/docs/pricing", + "supports_function_calling": true, + "supports_tool_choice": true + }, + "morph/morph-v3-fast": { + "input_cost_per_token": 8e-07, + "litellm_provider": "morph", + "max_input_tokens": 16000, + "max_output_tokens": 16000, + "max_tokens": 16000, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "supports_function_calling": false, + "supports_parallel_function_calling": false, + "supports_system_messages": true, + "supports_tool_choice": false, + "supports_vision": false + }, + "morph/morph-v3-large": { + "input_cost_per_token": 9e-07, + "litellm_provider": "morph", + "max_input_tokens": 16000, + "max_output_tokens": 16000, + "max_tokens": 16000, + "mode": "chat", + "output_cost_per_token": 1.9e-06, + "supports_function_calling": false, + "supports_parallel_function_calling": false, + "supports_system_messages": true, + "supports_tool_choice": false, + "supports_vision": false + }, + "multimodalembedding": { + "input_cost_per_character": 2e-07, + "input_cost_per_image": 0.0001, + "input_cost_per_token": 8e-07, + "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, + "litellm_provider": "vertex_ai-embedding-models", + "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" + ] + }, + "multimodalembedding@001": { + "input_cost_per_character": 2e-07, + "input_cost_per_image": 0.0001, + "input_cost_per_token": 8e-07, + "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, + "litellm_provider": "vertex_ai-embedding-models", + "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" + ] + }, + "nscale/Qwen/QwQ-32B": { + "input_cost_per_token": 1.8e-07, + "litellm_provider": "nscale", + "mode": "chat", + "output_cost_per_token": 2e-07, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" + }, + "nscale/Qwen/Qwen2.5-Coder-32B-Instruct": { + "input_cost_per_token": 6e-08, + "litellm_provider": "nscale", + "mode": "chat", + "output_cost_per_token": 2e-07, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" + }, + "nscale/Qwen/Qwen2.5-Coder-3B-Instruct": { + "input_cost_per_token": 1e-08, + "litellm_provider": "nscale", + "mode": "chat", + "output_cost_per_token": 3e-08, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" + }, + "nscale/Qwen/Qwen2.5-Coder-7B-Instruct": { + "input_cost_per_token": 1e-08, + "litellm_provider": "nscale", + "mode": "chat", + "output_cost_per_token": 3e-08, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" + }, + "nscale/black-forest-labs/FLUX.1-schnell": { + "input_cost_per_pixel": 1.3e-09, + "litellm_provider": "nscale", + "mode": "image_generation", + "output_cost_per_pixel": 0.0, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#image-models", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "nscale/deepseek-ai/DeepSeek-R1-Distill-Llama-70B": { + "input_cost_per_token": 3.75e-07, + "litellm_provider": "nscale", + "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-07, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" + }, + "nscale/deepseek-ai/DeepSeek-R1-Distill-Llama-8B": { + "input_cost_per_token": 2.5e-08, + "litellm_provider": "nscale", + "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-08, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" + }, + "nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B": { + "input_cost_per_token": 9e-08, + "litellm_provider": "nscale", + "metadata": { + "notes": "Pricing listed as $0.18/1M tokens total. Assumed 50/50 split for input/output." + }, + "mode": "chat", + "output_cost_per_token": 9e-08, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" + }, + "nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B": { + "input_cost_per_token": 7e-08, + "litellm_provider": "nscale", + "metadata": { + "notes": "Pricing listed as $0.14/1M tokens total. Assumed 50/50 split for input/output." + }, + "mode": "chat", + "output_cost_per_token": 7e-08, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" + }, + "nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "nscale", + "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-07, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" + }, + "nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B": { + "input_cost_per_token": 2e-07, + "litellm_provider": "nscale", + "metadata": { + "notes": "Pricing listed as $0.40/1M tokens total. Assumed 50/50 split for input/output." + }, + "mode": "chat", + "output_cost_per_token": 2e-07, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" + }, + "nscale/meta-llama/Llama-3.1-8B-Instruct": { + "input_cost_per_token": 3e-08, + "litellm_provider": "nscale", + "metadata": { + "notes": "Pricing listed as $0.06/1M tokens total. Assumed 50/50 split for input/output." + }, + "mode": "chat", + "output_cost_per_token": 3e-08, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" + }, + "nscale/meta-llama/Llama-3.3-70B-Instruct": { + "input_cost_per_token": 2e-07, + "litellm_provider": "nscale", + "metadata": { + "notes": "Pricing listed as $0.40/1M tokens total. Assumed 50/50 split for input/output." + }, + "mode": "chat", + "output_cost_per_token": 2e-07, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" + }, + "nscale/meta-llama/Llama-4-Scout-17B-16E-Instruct": { + "input_cost_per_token": 9e-08, + "litellm_provider": "nscale", + "mode": "chat", + "output_cost_per_token": 2.9e-07, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" + }, + "nscale/mistralai/mixtral-8x22b-instruct-v0.1": { + "input_cost_per_token": 6e-07, + "litellm_provider": "nscale", + "metadata": { + "notes": "Pricing listed as $1.20/1M tokens total. Assumed 50/50 split for input/output." + }, + "mode": "chat", + "output_cost_per_token": 6e-07, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" + }, + "nscale/stabilityai/stable-diffusion-xl-base-1.0": { + "input_cost_per_pixel": 3e-09, + "litellm_provider": "nscale", + "mode": "image_generation", + "output_cost_per_pixel": 0.0, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#image-models", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "o1": { + "cache_read_input_token_cost": 7.5e-06, + "input_cost_per_token": 1.5e-05, + "litellm_provider": "openai", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 6e-05, + "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 + }, + "o1-2024-12-17": { + "cache_read_input_token_cost": 7.5e-06, + "input_cost_per_token": 1.5e-05, + "litellm_provider": "openai", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 6e-05, + "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 + }, + "o1-mini": { + "cache_read_input_token_cost": 5.5e-07, + "input_cost_per_token": 1.1e-06, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_vision": true + }, + "o1-mini-2024-09-12": { + "cache_read_input_token_cost": 1.5e-06, + "input_cost_per_token": 3e-06, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1.2e-05, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_vision": true + }, + "o1-preview": { + "cache_read_input_token_cost": 7.5e-06, + "input_cost_per_token": 1.5e-05, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 6e-05, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_vision": true + }, + "o1-preview-2024-09-12": { + "cache_read_input_token_cost": 7.5e-06, + "input_cost_per_token": 1.5e-05, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 6e-05, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_vision": true + }, + "o1-pro": { + "input_cost_per_token": 0.00015, + "input_cost_per_token_batches": 7.5e-05, + "litellm_provider": "openai", + "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 + }, + "o1-pro-2025-03-19": { + "input_cost_per_token": 0.00015, + "input_cost_per_token_batches": 7.5e-05, + "litellm_provider": "openai", + "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 + }, + "o3": { + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_flex": 2.5e-07, + "cache_read_input_token_cost_priority": 8.75e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_flex": 1e-06, + "input_cost_per_token_priority": 3.5e-06, + "litellm_provider": "openai", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 8e-06, + "output_cost_per_token_flex": 4e-06, + "output_cost_per_token_priority": 1.4e-05, + "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_vision": true + }, + "o3-2025-04-16": { + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "openai", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 8e-06, + "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_vision": true + }, + "o3-deep-research": { + "cache_read_input_token_cost": 2.5e-06, + "input_cost_per_token": 1e-05, + "input_cost_per_token_batches": 5e-06, + "litellm_provider": "openai", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "responses", + "output_cost_per_token": 4e-05, + "output_cost_per_token_batches": 2e-05, + "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 + }, + "o3-deep-research-2025-06-26": { + "cache_read_input_token_cost": 2.5e-06, + "input_cost_per_token": 1e-05, + "input_cost_per_token_batches": 5e-06, + "litellm_provider": "openai", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "responses", + "output_cost_per_token": 4e-05, + "output_cost_per_token_batches": 2e-05, + "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 + }, + "o3-mini": { + "cache_read_input_token_cost": 5.5e-07, + "input_cost_per_token": 1.1e-06, + "litellm_provider": "openai", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "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 + }, + "o3-mini-2025-01-31": { + "cache_read_input_token_cost": 5.5e-07, + "input_cost_per_token": 1.1e-06, + "litellm_provider": "openai", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "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 + }, + "o3-pro": { + "input_cost_per_token": 2e-05, + "input_cost_per_token_batches": 1e-05, + "litellm_provider": "openai", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "responses", + "output_cost_per_token": 8e-05, + "output_cost_per_token_batches": 4e-05, + "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 + }, + "o3-pro-2025-06-10": { + "input_cost_per_token": 2e-05, + "input_cost_per_token_batches": 1e-05, + "litellm_provider": "openai", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "responses", + "output_cost_per_token": 8e-05, + "output_cost_per_token_batches": 4e-05, + "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 + }, + "o4-mini": { + "cache_read_input_token_cost": 2.75e-07, + "cache_read_input_token_cost_flex": 1.375e-07, + "cache_read_input_token_cost_priority": 5e-07, + "input_cost_per_token": 1.1e-06, + "input_cost_per_token_flex": 5.5e-07, + "input_cost_per_token_priority": 2e-06, + "litellm_provider": "openai", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "output_cost_per_token_flex": 2.2e-06, + "output_cost_per_token_priority": 8e-06, + "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 + }, + "o4-mini-2025-04-16": { + "cache_read_input_token_cost": 2.75e-07, + "input_cost_per_token": 1.1e-06, + "litellm_provider": "openai", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "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 + }, + "o4-mini-deep-research": { + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_batches": 1e-06, + "litellm_provider": "openai", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "responses", + "output_cost_per_token": 8e-06, + "output_cost_per_token_batches": 4e-06, + "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 + }, + "o4-mini-deep-research-2025-06-26": { + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_batches": 1e-06, + "litellm_provider": "openai", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "responses", + "output_cost_per_token": 8e-06, + "output_cost_per_token_batches": 4e-06, + "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 + }, + "oci/meta.llama-3.1-405b-instruct": { + "input_cost_per_token": 1.068e-05, + "litellm_provider": "oci", + "max_input_tokens": 128000, + "max_output_tokens": 4000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.068e-05, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", + "supports_function_calling": true, + "supports_response_schema": false + }, + "oci/meta.llama-3.2-90b-vision-instruct": { + "input_cost_per_token": 2e-06, + "litellm_provider": "oci", + "max_input_tokens": 128000, + "max_output_tokens": 4000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2e-06, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", + "supports_function_calling": true, + "supports_response_schema": false + }, + "oci/meta.llama-3.3-70b-instruct": { + "input_cost_per_token": 7.2e-07, + "litellm_provider": "oci", + "max_input_tokens": 128000, + "max_output_tokens": 4000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 7.2e-07, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", + "supports_function_calling": true, + "supports_response_schema": false + }, + "oci/meta.llama-4-maverick-17b-128e-instruct-fp8": { + "input_cost_per_token": 7.2e-07, + "litellm_provider": "oci", + "max_input_tokens": 512000, + "max_output_tokens": 4000, + "max_tokens": 512000, + "mode": "chat", + "output_cost_per_token": 7.2e-07, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", + "supports_function_calling": true, + "supports_response_schema": false + }, + "oci/meta.llama-4-scout-17b-16e-instruct": { + "input_cost_per_token": 7.2e-07, + "litellm_provider": "oci", + "max_input_tokens": 192000, + "max_output_tokens": 4000, + "max_tokens": 192000, + "mode": "chat", + "output_cost_per_token": 7.2e-07, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", + "supports_function_calling": true, + "supports_response_schema": false + }, + "oci/xai.grok-3": { + "input_cost_per_token": 3e-06, + "litellm_provider": "oci", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.5e-07, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", + "supports_function_calling": true, + "supports_response_schema": false + }, + "oci/xai.grok-3-fast": { + "input_cost_per_token": 5e-06, + "litellm_provider": "oci", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.5e-05, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", + "supports_function_calling": true, + "supports_response_schema": false + }, + "oci/xai.grok-3-mini": { + "input_cost_per_token": 3e-07, + "litellm_provider": "oci", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 5e-07, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", + "supports_function_calling": true, + "supports_response_schema": false + }, + "oci/xai.grok-3-mini-fast": { + "input_cost_per_token": 6e-07, + "litellm_provider": "oci", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4e-06, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", + "supports_function_calling": true, + "supports_response_schema": false + }, + "oci/xai.grok-4": { + "input_cost_per_token": 3e-06, + "litellm_provider": "oci", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.5e-07, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", + "supports_function_calling": true, + "supports_response_schema": false + }, + "ollama/codegeex4": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 32768, + "max_output_tokens": 8192, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0.0, + "supports_function_calling": false + }, + "ollama/codegemma": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "completion", + "output_cost_per_token": 0.0 + }, + "ollama/codellama": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "completion", + "output_cost_per_token": 0.0 + }, + "ollama/deepseek-coder-v2-base": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "completion", + "output_cost_per_token": 0.0, + "supports_function_calling": true + }, + "ollama/deepseek-coder-v2-instruct": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 32768, + "max_output_tokens": 8192, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0.0, + "supports_function_calling": true + }, + "ollama/deepseek-coder-v2-lite-base": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "completion", + "output_cost_per_token": 0.0, + "supports_function_calling": true + }, + "ollama/deepseek-coder-v2-lite-instruct": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 32768, + "max_output_tokens": 8192, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0.0, + "supports_function_calling": true + }, + "ollama/deepseek-v3.1:671b-cloud" : { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 163840, + "max_output_tokens": 163840, + "max_tokens": 163840, + "mode": "chat", + "output_cost_per_token": 0.0, + "supports_function_calling": true + }, + "ollama/gpt-oss:120b-cloud" : { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 0.0, + "supports_function_calling": true + }, + "ollama/gpt-oss:20b-cloud" : { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 0.0, + "supports_function_calling": true + }, + "ollama/internlm2_5-20b-chat": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 32768, + "max_output_tokens": 8192, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0.0, + "supports_function_calling": true + }, + "ollama/llama2": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.0 + }, + "ollama/llama2-uncensored": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "completion", + "output_cost_per_token": 0.0 + }, + "ollama/llama2:13b": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.0 + }, + "ollama/llama2:70b": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.0 + }, + "ollama/llama2:7b": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.0 + }, + "ollama/llama3": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.0 + }, + "ollama/llama3.1": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0.0, + "supports_function_calling": true + }, + "ollama/llama3:70b": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.0 + }, + "ollama/llama3:8b": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.0 + }, + "ollama/mistral": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "completion", + "output_cost_per_token": 0.0, + "supports_function_calling": true + }, + "ollama/mistral-7B-Instruct-v0.1": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.0, + "supports_function_calling": true + }, + "ollama/mistral-7B-Instruct-v0.2": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0.0, + "supports_function_calling": true + }, + "ollama/mistral-large-instruct-2407": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 65536, + "max_output_tokens": 8192, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 0.0, + "supports_function_calling": true + }, + "ollama/mixtral-8x22B-Instruct-v0.1": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 65536, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 0.0, + "supports_function_calling": true + }, + "ollama/mixtral-8x7B-Instruct-v0.1": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0.0, + "supports_function_calling": true + }, + "ollama/orca-mini": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "completion", + "output_cost_per_token": 0.0 + }, + "ollama/qwen3-coder:480b-cloud": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 0.0, + "supports_function_calling": true + }, + "ollama/vicuna": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 2048, + "max_output_tokens": 2048, + "max_tokens": 2048, + "mode": "completion", + "output_cost_per_token": 0.0 + }, + "omni-moderation-2024-09-26": { + "input_cost_per_token": 0.0, + "litellm_provider": "openai", + "max_input_tokens": 32768, + "max_output_tokens": 0, + "max_tokens": 32768, + "mode": "moderation", + "output_cost_per_token": 0.0 + }, + "omni-moderation-latest": { + "input_cost_per_token": 0.0, + "litellm_provider": "openai", + "max_input_tokens": 32768, + "max_output_tokens": 0, + "max_tokens": 32768, + "mode": "moderation", + "output_cost_per_token": 0.0 + }, + "omni-moderation-latest-intents": { + "input_cost_per_token": 0.0, + "litellm_provider": "openai", + "max_input_tokens": 32768, + "max_output_tokens": 0, + "max_tokens": 32768, + "mode": "moderation", + "output_cost_per_token": 0.0 + }, + "openai.gpt-oss-120b-1:0": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-07, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "openai.gpt-oss-20b-1:0": { + "input_cost_per_token": 7e-08, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3e-07, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "openrouter/anthropic/claude-2": { + "input_cost_per_token": 1.102e-05, + "litellm_provider": "openrouter", + "max_output_tokens": 8191, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 3.268e-05, + "supports_tool_choice": true + }, + "openrouter/anthropic/claude-3-5-haiku": { + "input_cost_per_token": 1e-06, + "litellm_provider": "openrouter", + "max_tokens": 200000, + "mode": "chat", + "output_cost_per_token": 5e-06, + "supports_function_calling": true, + "supports_tool_choice": true + }, + "openrouter/anthropic/claude-3-5-haiku-20241022": { + "input_cost_per_token": 1e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 5e-06, + "supports_function_calling": true, + "supports_tool_choice": true, + "tool_use_system_prompt_tokens": 264 + }, + "openrouter/anthropic/claude-3-haiku": { + "input_cost_per_image": 0.0004, + "input_cost_per_token": 2.5e-07, + "litellm_provider": "openrouter", + "max_tokens": 200000, + "mode": "chat", + "output_cost_per_token": 1.25e-06, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "openrouter/anthropic/claude-3-haiku-20240307": { + "input_cost_per_token": 2.5e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.25e-06, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 264 + }, + "openrouter/anthropic/claude-3-opus": { + "input_cost_per_token": 1.5e-05, + "litellm_provider": "openrouter", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 395 + }, + "openrouter/anthropic/claude-3-sonnet": { + "input_cost_per_image": 0.0048, + "input_cost_per_token": 3e-06, + "litellm_provider": "openrouter", + "max_tokens": 200000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "openrouter/anthropic/claude-3.5-sonnet": { + "input_cost_per_token": 3e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "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 + }, + "openrouter/anthropic/claude-3.5-sonnet:beta": { + "input_cost_per_token": 3e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159 + }, + "openrouter/anthropic/claude-3.7-sonnet": { + "input_cost_per_image": 0.0048, + "input_cost_per_token": 3e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 200000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "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 + }, + "openrouter/anthropic/claude-3.7-sonnet:beta": { + "input_cost_per_image": 0.0048, + "input_cost_per_token": 3e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 200000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159 + }, + "openrouter/anthropic/claude-instant-v1": { + "input_cost_per_token": 1.63e-06, + "litellm_provider": "openrouter", + "max_output_tokens": 8191, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 5.51e-06, + "supports_tool_choice": true + }, + "openrouter/anthropic/claude-opus-4": { + "input_cost_per_image": 0.0048, + "input_cost_per_token": 1.5e-05, + "litellm_provider": "openrouter", + "max_input_tokens": 200000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "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 + }, + "openrouter/anthropic/claude-opus-4.1": { + "input_cost_per_image": 0.0048, + "input_cost_per_token": 1.5e-05, + "litellm_provider": "openrouter", + "max_input_tokens": 200000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "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 + }, + "openrouter/anthropic/claude-sonnet-4": { + "input_cost_per_image": 0.0048, + "input_cost_per_token": 3e-06, + "input_cost_per_token_above_200k_tokens": 6e-06, + "output_cost_per_token_above_200k_tokens": 2.25e-05, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "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 + }, + "openrouter/bytedance/ui-tars-1.5-7b": { + "input_cost_per_token": 1e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 2048, + "max_tokens": 2048, + "mode": "chat", + "output_cost_per_token": 2e-07, + "source": "https://openrouter.ai/api/v1/models/bytedance/ui-tars-1.5-7b", + "supports_tool_choice": true + }, + "openrouter/cognitivecomputations/dolphin-mixtral-8x7b": { + "input_cost_per_token": 5e-07, + "litellm_provider": "openrouter", + "max_tokens": 32769, + "mode": "chat", + "output_cost_per_token": 5e-07, + "supports_tool_choice": true + }, + "openrouter/cohere/command-r-plus": { + "input_cost_per_token": 3e-06, + "litellm_provider": "openrouter", + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_tool_choice": true + }, + "openrouter/databricks/dbrx-instruct": { + "input_cost_per_token": 6e-07, + "litellm_provider": "openrouter", + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 6e-07, + "supports_tool_choice": true + }, + "openrouter/deepseek/deepseek-chat": { + "input_cost_per_token": 1.4e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 65536, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2.8e-07, + "supports_prompt_caching": true, + "supports_tool_choice": true + }, + "openrouter/deepseek/deepseek-chat-v3-0324": { + "input_cost_per_token": 1.4e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 65536, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2.8e-07, + "supports_prompt_caching": true, + "supports_tool_choice": true + }, + "openrouter/deepseek/deepseek-chat-v3.1": { + "input_cost_per_token": 2e-07, + "input_cost_per_token_cache_hit": 2e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 163840, + "max_output_tokens": 163840, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 8e-07, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "openrouter/deepseek/deepseek-coder": { + "input_cost_per_token": 1.4e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 66000, + "max_output_tokens": 4096, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2.8e-07, + "supports_prompt_caching": true, + "supports_tool_choice": true + }, + "openrouter/deepseek/deepseek-r1": { + "input_cost_per_token": 5.5e-07, + "input_cost_per_token_cache_hit": 1.4e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 65336, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2.19e-06, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "openrouter/deepseek/deepseek-r1-0528": { + "input_cost_per_token": 5e-07, + "input_cost_per_token_cache_hit": 1.4e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 65336, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2.15e-06, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "openrouter/fireworks/firellava-13b": { + "input_cost_per_token": 2e-07, + "litellm_provider": "openrouter", + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2e-07, + "supports_tool_choice": true + }, + "openrouter/google/gemini-2.0-flash-001": { + "input_cost_per_audio_token": 7e-07, + "input_cost_per_token": 1e-07, + "litellm_provider": "openrouter", + "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-07, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "openrouter/google/gemini-2.5-flash": { + "input_cost_per_audio_token": 7e-07, + "input_cost_per_token": 3e-07, + "litellm_provider": "openrouter", + "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": 2.5e-06, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "openrouter/google/gemini-2.5-pro": { + "input_cost_per_audio_token": 7e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "openrouter", + "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": 1e-05, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "openrouter/google/gemini-pro-1.5": { + "input_cost_per_image": 0.00265, + "input_cost_per_token": 2.5e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 7.5e-06, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "openrouter/google/gemini-pro-vision": { + "input_cost_per_image": 0.0025, + "input_cost_per_token": 1.25e-07, + "litellm_provider": "openrouter", + "max_tokens": 45875, + "mode": "chat", + "output_cost_per_token": 3.75e-07, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "openrouter/google/palm-2-chat-bison": { + "input_cost_per_token": 5e-07, + "litellm_provider": "openrouter", + "max_tokens": 25804, + "mode": "chat", + "output_cost_per_token": 5e-07, + "supports_tool_choice": true + }, + "openrouter/google/palm-2-codechat-bison": { + "input_cost_per_token": 5e-07, + "litellm_provider": "openrouter", + "max_tokens": 20070, + "mode": "chat", + "output_cost_per_token": 5e-07, + "supports_tool_choice": true + }, + "openrouter/gryphe/mythomax-l2-13b": { + "input_cost_per_token": 1.875e-06, + "litellm_provider": "openrouter", + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.875e-06, + "supports_tool_choice": true + }, + "openrouter/jondurbin/airoboros-l2-70b-2.1": { + "input_cost_per_token": 1.3875e-05, + "litellm_provider": "openrouter", + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.3875e-05, + "supports_tool_choice": true + }, + "openrouter/mancer/weaver": { + "input_cost_per_token": 5.625e-06, + "litellm_provider": "openrouter", + "max_tokens": 8000, + "mode": "chat", + "output_cost_per_token": 5.625e-06, + "supports_tool_choice": true + }, + "openrouter/meta-llama/codellama-34b-instruct": { + "input_cost_per_token": 5e-07, + "litellm_provider": "openrouter", + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 5e-07, + "supports_tool_choice": true + }, + "openrouter/meta-llama/llama-2-13b-chat": { + "input_cost_per_token": 2e-07, + "litellm_provider": "openrouter", + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2e-07, + "supports_tool_choice": true + }, + "openrouter/meta-llama/llama-2-70b-chat": { + "input_cost_per_token": 1.5e-06, + "litellm_provider": "openrouter", + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.5e-06, + "supports_tool_choice": true + }, + "openrouter/meta-llama/llama-3-70b-instruct": { + "input_cost_per_token": 5.9e-07, + "litellm_provider": "openrouter", + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 7.9e-07, + "supports_tool_choice": true + }, + "openrouter/meta-llama/llama-3-70b-instruct:nitro": { + "input_cost_per_token": 9e-07, + "litellm_provider": "openrouter", + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 9e-07, + "supports_tool_choice": true + }, + "openrouter/meta-llama/llama-3-8b-instruct:extended": { + "input_cost_per_token": 2.25e-07, + "litellm_provider": "openrouter", + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 2.25e-06, + "supports_tool_choice": true + }, + "openrouter/meta-llama/llama-3-8b-instruct:free": { + "input_cost_per_token": 0.0, + "litellm_provider": "openrouter", + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.0, + "supports_tool_choice": true + }, + "openrouter/microsoft/wizardlm-2-8x22b:nitro": { + "input_cost_per_token": 1e-06, + "litellm_provider": "openrouter", + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1e-06, + "supports_tool_choice": true + }, + "openrouter/mistralai/mistral-7b-instruct": { + "input_cost_per_token": 1.3e-07, + "litellm_provider": "openrouter", + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.3e-07, + "supports_tool_choice": true + }, + "openrouter/mistralai/mistral-7b-instruct:free": { + "input_cost_per_token": 0.0, + "litellm_provider": "openrouter", + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.0, + "supports_tool_choice": true + }, + "openrouter/mistralai/mistral-large": { + "input_cost_per_token": 8e-06, + "litellm_provider": "openrouter", + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 2.4e-05, + "supports_tool_choice": true + }, + "openrouter/mistralai/mistral-small-3.1-24b-instruct": { + "input_cost_per_token": 1e-07, + "litellm_provider": "openrouter", + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 3e-07, + "supports_tool_choice": true + }, + "openrouter/mistralai/mistral-small-3.2-24b-instruct": { + "input_cost_per_token": 1e-07, + "litellm_provider": "openrouter", + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 3e-07, + "supports_tool_choice": true + }, + "openrouter/mistralai/mixtral-8x22b-instruct": { + "input_cost_per_token": 6.5e-07, + "litellm_provider": "openrouter", + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 6.5e-07, + "supports_tool_choice": true + }, + "openrouter/nousresearch/nous-hermes-llama2-13b": { + "input_cost_per_token": 2e-07, + "litellm_provider": "openrouter", + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2e-07, + "supports_tool_choice": true + }, + "openrouter/openai/gpt-3.5-turbo": { + "input_cost_per_token": 1.5e-06, + "litellm_provider": "openrouter", + "max_tokens": 4095, + "mode": "chat", + "output_cost_per_token": 2e-06, + "supports_tool_choice": true + }, + "openrouter/openai/gpt-3.5-turbo-16k": { + "input_cost_per_token": 3e-06, + "litellm_provider": "openrouter", + "max_tokens": 16383, + "mode": "chat", + "output_cost_per_token": 4e-06, + "supports_tool_choice": true + }, + "openrouter/openai/gpt-4": { + "input_cost_per_token": 3e-05, + "litellm_provider": "openrouter", + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 6e-05, + "supports_tool_choice": true + }, + "openrouter/openai/gpt-4-vision-preview": { + "input_cost_per_image": 0.01445, + "input_cost_per_token": 1e-05, + "litellm_provider": "openrouter", + "max_tokens": 130000, + "mode": "chat", + "output_cost_per_token": 3e-05, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "openrouter/openai/gpt-4.1": { + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 8e-06, + "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 + }, + "openrouter/openai/gpt-4.1-2025-04-14": { + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 8e-06, + "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 + }, + "openrouter/openai/gpt-4.1-mini": { + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 4e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 1.6e-06, + "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 + }, + "openrouter/openai/gpt-4.1-mini-2025-04-14": { + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 4e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 1.6e-06, + "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 + }, + "openrouter/openai/gpt-4.1-nano": { + "cache_read_input_token_cost": 2.5e-08, + "input_cost_per_token": 1e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 4e-07, + "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 + }, + "openrouter/openai/gpt-4.1-nano-2025-04-14": { + "cache_read_input_token_cost": 2.5e-08, + "input_cost_per_token": 1e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 4e-07, + "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 + }, + "openrouter/openai/gpt-4o": { + "input_cost_per_token": 2.5e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "openrouter/openai/gpt-4o-2024-05-13": { + "input_cost_per_token": 5e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "openrouter/openai/gpt-5-chat": { + "cache_read_input_token_cost": 1.25e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_reasoning": true, + "supports_tool_choice": true + }, + "openrouter/openai/gpt-5-codex": { + "cache_read_input_token_cost": 1.25e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_reasoning": true, + "supports_tool_choice": true + }, + "openrouter/openai/gpt-5": { + "cache_read_input_token_cost": 1.25e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_reasoning": true, + "supports_tool_choice": true + }, + "openrouter/openai/gpt-5-mini": { + "cache_read_input_token_cost": 2.5e-08, + "input_cost_per_token": 2.5e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2e-06, + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_reasoning": true, + "supports_tool_choice": true + }, + "openrouter/openai/gpt-5-nano": { + "cache_read_input_token_cost": 5e-09, + "input_cost_per_token": 5e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4e-07, + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_reasoning": true, + "supports_tool_choice": true + }, + "openrouter/openai/gpt-oss-120b": { + "input_cost_per_token": 1.8e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 8e-07, + "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 + }, + "openrouter/openai/gpt-oss-20b": { + "input_cost_per_token": 1.8e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 8e-07, + "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 + }, + "openrouter/openai/o1": { + "cache_read_input_token_cost": 7.5e-06, + "input_cost_per_token": 1.5e-05, + "litellm_provider": "openrouter", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 6e-05, + "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 + }, + "openrouter/openai/o1-mini": { + "input_cost_per_token": 3e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 128000, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1.2e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "openrouter/openai/o1-mini-2024-09-12": { + "input_cost_per_token": 3e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 128000, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1.2e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "openrouter/openai/o1-preview": { + "input_cost_per_token": 1.5e-05, + "litellm_provider": "openrouter", + "max_input_tokens": 128000, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 6e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "openrouter/openai/o1-preview-2024-09-12": { + "input_cost_per_token": 1.5e-05, + "litellm_provider": "openrouter", + "max_input_tokens": 128000, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 6e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "openrouter/openai/o3-mini": { + "input_cost_per_token": 1.1e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 128000, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "openrouter/openai/o3-mini-high": { + "input_cost_per_token": 1.1e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 128000, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "openrouter/pygmalionai/mythalion-13b": { + "input_cost_per_token": 1.875e-06, + "litellm_provider": "openrouter", + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.875e-06, + "supports_tool_choice": true + }, + "openrouter/qwen/qwen-2.5-coder-32b-instruct": { + "input_cost_per_token": 1.8e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 33792, + "max_output_tokens": 33792, + "max_tokens": 33792, + "mode": "chat", + "output_cost_per_token": 1.8e-07, + "supports_tool_choice": true + }, + "openrouter/qwen/qwen-vl-plus": { + "input_cost_per_token": 2.1e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 8192, + "max_output_tokens": 2048, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 6.3e-07, + "supports_tool_choice": true + }, + "openrouter/qwen/qwen3-coder": { + "input_cost_per_token": 1e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 5e-06, + "source": "https://openrouter.ai/qwen/qwen3-coder", + "supports_tool_choice": true + }, + "openrouter/switchpoint/router": { + "input_cost_per_token": 8.5e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 3.4e-06, + "source": "https://openrouter.ai/switchpoint/router", + "supports_tool_choice": true + }, + "openrouter/undi95/remm-slerp-l2-13b": { + "input_cost_per_token": 1.875e-06, + "litellm_provider": "openrouter", + "max_tokens": 6144, + "mode": "chat", + "output_cost_per_token": 1.875e-06, + "supports_tool_choice": true + }, + "openrouter/x-ai/grok-4": { + "input_cost_per_token": 3e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "source": "https://openrouter.ai/x-ai/grok-4", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_web_search": true + }, + "openrouter/x-ai/grok-4-fast:free": { + "input_cost_per_token": 0, + "litellm_provider": "openrouter", + "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 + }, + "ovhcloud/DeepSeek-R1-Distill-Llama-70B": { + "input_cost_per_token": 6.7e-07, + "litellm_provider": "ovhcloud", + "max_input_tokens": 131000, + "max_output_tokens": 131000, + "max_tokens": 131000, + "mode": "chat", + "output_cost_per_token": 6.7e-07, + "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 + }, + "ovhcloud/Llama-3.1-8B-Instruct": { + "input_cost_per_token": 1e-07, + "litellm_provider": "ovhcloud", + "max_input_tokens": 131000, + "max_output_tokens": 131000, + "max_tokens": 131000, + "mode": "chat", + "output_cost_per_token": 1e-07, + "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 + }, + "ovhcloud/Meta-Llama-3_1-70B-Instruct": { + "input_cost_per_token": 6.7e-07, + "litellm_provider": "ovhcloud", + "max_input_tokens": 131000, + "max_output_tokens": 131000, + "max_tokens": 131000, + "mode": "chat", + "output_cost_per_token": 6.7e-07, + "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 + }, + "ovhcloud/Meta-Llama-3_3-70B-Instruct": { + "input_cost_per_token": 6.7e-07, + "litellm_provider": "ovhcloud", + "max_input_tokens": 131000, + "max_output_tokens": 131000, + "max_tokens": 131000, + "mode": "chat", + "output_cost_per_token": 6.7e-07, + "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 + }, + "ovhcloud/Mistral-7B-Instruct-v0.3": { + "input_cost_per_token": 1e-07, + "litellm_provider": "ovhcloud", + "max_input_tokens": 127000, + "max_output_tokens": 127000, + "max_tokens": 127000, + "mode": "chat", + "output_cost_per_token": 1e-07, + "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 + }, + "ovhcloud/Mistral-Nemo-Instruct-2407": { + "input_cost_per_token": 1.3e-07, + "litellm_provider": "ovhcloud", + "max_input_tokens": 118000, + "max_output_tokens": 118000, + "max_tokens": 118000, + "mode": "chat", + "output_cost_per_token": 1.3e-07, + "source": "https://endpoints.ai.cloud.ovh.net/models/mistral-nemo-instruct-2407", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "ovhcloud/Mistral-Small-3.2-24B-Instruct-2506": { + "input_cost_per_token": 9e-08, + "litellm_provider": "ovhcloud", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.8e-07, + "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 + }, + "ovhcloud/Mixtral-8x7B-Instruct-v0.1": { + "input_cost_per_token": 6.3e-07, + "litellm_provider": "ovhcloud", + "max_input_tokens": 32000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 6.3e-07, + "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 + }, + "ovhcloud/Qwen2.5-Coder-32B-Instruct": { + "input_cost_per_token": 8.7e-07, + "litellm_provider": "ovhcloud", + "max_input_tokens": 32000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 8.7e-07, + "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 + }, + "ovhcloud/Qwen2.5-VL-72B-Instruct": { + "input_cost_per_token": 9.1e-07, + "litellm_provider": "ovhcloud", + "max_input_tokens": 32000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 9.1e-07, + "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 + }, + "ovhcloud/Qwen3-32B": { + "input_cost_per_token": 8e-08, + "litellm_provider": "ovhcloud", + "max_input_tokens": 32000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 2.3e-07, + "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 + }, + "ovhcloud/gpt-oss-120b": { + "input_cost_per_token": 8e-08, + "litellm_provider": "ovhcloud", + "max_input_tokens": 131000, + "max_output_tokens": 131000, + "max_tokens": 131000, + "mode": "chat", + "output_cost_per_token": 4e-07, + "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 + }, + "ovhcloud/gpt-oss-20b": { + "input_cost_per_token": 4e-08, + "litellm_provider": "ovhcloud", + "max_input_tokens": 131000, + "max_output_tokens": 131000, + "max_tokens": 131000, + "mode": "chat", + "output_cost_per_token": 1.5e-07, + "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 + }, + "ovhcloud/llava-v1.6-mistral-7b-hf": { + "input_cost_per_token": 2.9e-07, + "litellm_provider": "ovhcloud", + "max_input_tokens": 32000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 2.9e-07, + "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 + }, + "ovhcloud/mamba-codestral-7B-v0.1": { + "input_cost_per_token": 1.9e-07, + "litellm_provider": "ovhcloud", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 1.9e-07, + "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 + }, + "palm/chat-bison": { + "input_cost_per_token": 1.25e-07, + "litellm_provider": "palm", + "max_input_tokens": 8192, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.25e-07, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" + }, + "palm/chat-bison-001": { + "input_cost_per_token": 1.25e-07, + "litellm_provider": "palm", + "max_input_tokens": 8192, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.25e-07, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" + }, + "palm/text-bison": { + "input_cost_per_token": 1.25e-07, + "litellm_provider": "palm", + "max_input_tokens": 8192, + "max_output_tokens": 1024, + "max_tokens": 1024, + "mode": "completion", + "output_cost_per_token": 1.25e-07, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" + }, + "palm/text-bison-001": { + "input_cost_per_token": 1.25e-07, + "litellm_provider": "palm", + "max_input_tokens": 8192, + "max_output_tokens": 1024, + "max_tokens": 1024, + "mode": "completion", + "output_cost_per_token": 1.25e-07, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" + }, + "palm/text-bison-safety-off": { + "input_cost_per_token": 1.25e-07, + "litellm_provider": "palm", + "max_input_tokens": 8192, + "max_output_tokens": 1024, + "max_tokens": 1024, + "mode": "completion", + "output_cost_per_token": 1.25e-07, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" + }, + "palm/text-bison-safety-recitation-off": { + "input_cost_per_token": 1.25e-07, + "litellm_provider": "palm", + "max_input_tokens": 8192, + "max_output_tokens": 1024, + "max_tokens": 1024, + "mode": "completion", + "output_cost_per_token": 1.25e-07, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" + }, + "perplexity/codellama-34b-instruct": { + "input_cost_per_token": 3.5e-07, + "litellm_provider": "perplexity", + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.4e-06 + }, + "perplexity/codellama-70b-instruct": { + "input_cost_per_token": 7e-07, + "litellm_provider": "perplexity", + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 2.8e-06 + }, + "perplexity/llama-2-70b-chat": { + "input_cost_per_token": 7e-07, + "litellm_provider": "perplexity", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2.8e-06 + }, + "perplexity/llama-3.1-70b-instruct": { + "input_cost_per_token": 1e-06, + "litellm_provider": "perplexity", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1e-06 + }, + "perplexity/llama-3.1-8b-instruct": { + "input_cost_per_token": 2e-07, + "litellm_provider": "perplexity", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2e-07 + }, + "perplexity/llama-3.1-sonar-huge-128k-online": { + "deprecation_date": "2025-02-22", + "input_cost_per_token": 5e-06, + "litellm_provider": "perplexity", + "max_input_tokens": 127072, + "max_output_tokens": 127072, + "max_tokens": 127072, + "mode": "chat", + "output_cost_per_token": 5e-06 + }, + "perplexity/llama-3.1-sonar-large-128k-chat": { + "deprecation_date": "2025-02-22", + "input_cost_per_token": 1e-06, + "litellm_provider": "perplexity", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1e-06 + }, + "perplexity/llama-3.1-sonar-large-128k-online": { + "deprecation_date": "2025-02-22", + "input_cost_per_token": 1e-06, + "litellm_provider": "perplexity", + "max_input_tokens": 127072, + "max_output_tokens": 127072, + "max_tokens": 127072, + "mode": "chat", + "output_cost_per_token": 1e-06 + }, + "perplexity/llama-3.1-sonar-small-128k-chat": { + "deprecation_date": "2025-02-22", + "input_cost_per_token": 2e-07, + "litellm_provider": "perplexity", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2e-07 + }, + "perplexity/llama-3.1-sonar-small-128k-online": { + "deprecation_date": "2025-02-22", + "input_cost_per_token": 2e-07, + "litellm_provider": "perplexity", + "max_input_tokens": 127072, + "max_output_tokens": 127072, + "max_tokens": 127072, + "mode": "chat", + "output_cost_per_token": 2e-07 + }, + "perplexity/mistral-7b-instruct": { + "input_cost_per_token": 7e-08, + "litellm_provider": "perplexity", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2.8e-07 + }, + "perplexity/mixtral-8x7b-instruct": { + "input_cost_per_token": 7e-08, + "litellm_provider": "perplexity", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2.8e-07 + }, + "perplexity/pplx-70b-chat": { + "input_cost_per_token": 7e-07, + "litellm_provider": "perplexity", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2.8e-06 + }, + "perplexity/pplx-70b-online": { + "input_cost_per_request": 0.005, + "input_cost_per_token": 0.0, + "litellm_provider": "perplexity", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2.8e-06 + }, + "perplexity/pplx-7b-chat": { + "input_cost_per_token": 7e-08, + "litellm_provider": "perplexity", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2.8e-07 + }, + "perplexity/pplx-7b-online": { + "input_cost_per_request": 0.005, + "input_cost_per_token": 0.0, + "litellm_provider": "perplexity", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2.8e-07 + }, + "perplexity/sonar": { + "input_cost_per_token": 1e-06, + "litellm_provider": "perplexity", + "max_input_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-06, + "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 + }, + "perplexity/sonar-deep-research": { + "citation_cost_per_token": 2e-06, + "input_cost_per_token": 2e-06, + "litellm_provider": "perplexity", + "max_input_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_reasoning_token": 3e-06, + "output_cost_per_token": 8e-06, + "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 + }, + "perplexity/sonar-medium-chat": { + "input_cost_per_token": 6e-07, + "litellm_provider": "perplexity", + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.8e-06 + }, + "perplexity/sonar-medium-online": { + "input_cost_per_request": 0.005, + "input_cost_per_token": 0, + "litellm_provider": "perplexity", + "max_input_tokens": 12000, + "max_output_tokens": 12000, + "max_tokens": 12000, + "mode": "chat", + "output_cost_per_token": 1.8e-06 + }, + "perplexity/sonar-pro": { + "input_cost_per_token": 3e-06, + "litellm_provider": "perplexity", + "max_input_tokens": 200000, + "max_output_tokens": 8000, + "max_tokens": 8000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "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 + }, + "perplexity/sonar-reasoning": { + "input_cost_per_token": 1e-06, + "litellm_provider": "perplexity", + "max_input_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-06, + "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 + }, + "perplexity/sonar-reasoning-pro": { + "input_cost_per_token": 2e-06, + "litellm_provider": "perplexity", + "max_input_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 8e-06, + "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 + }, + "perplexity/sonar-small-chat": { + "input_cost_per_token": 7e-08, + "litellm_provider": "perplexity", + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 2.8e-07 + }, + "perplexity/sonar-small-online": { + "input_cost_per_request": 0.005, + "input_cost_per_token": 0, + "litellm_provider": "perplexity", + "max_input_tokens": 12000, + "max_output_tokens": 12000, + "max_tokens": 12000, + "mode": "chat", + "output_cost_per_token": 2.8e-07 + }, + "qwen.qwen3-coder-480b-a35b-v1:0": { + "input_cost_per_token": 2.2e-07, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 262000, + "max_output_tokens": 65536, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 1.8e-06, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "qwen.qwen3-235b-a22b-2507-v1:0": { + "input_cost_per_token": 2.2e-07, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 262144, + "max_output_tokens": 131072, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 8.8e-07, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "qwen.qwen3-coder-30b-a3b-v1:0": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 262144, + "max_output_tokens": 131072, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 6.0e-07, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "qwen.qwen3-32b-v1:0": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 131072, + "max_output_tokens": 16384, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 6.0e-07, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "recraft/recraftv2": { + "litellm_provider": "recraft", + "mode": "image_generation", + "output_cost_per_image": 0.022, + "source": "https://www.recraft.ai/docs#pricing", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "recraft/recraftv3": { + "litellm_provider": "recraft", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://www.recraft.ai/docs#pricing", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "replicate/meta/llama-2-13b": { + "input_cost_per_token": 1e-07, + "litellm_provider": "replicate", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 5e-07, + "supports_tool_choice": true + }, + "replicate/meta/llama-2-13b-chat": { + "input_cost_per_token": 1e-07, + "litellm_provider": "replicate", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 5e-07, + "supports_tool_choice": true + }, + "replicate/meta/llama-2-70b": { + "input_cost_per_token": 6.5e-07, + "litellm_provider": "replicate", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2.75e-06, + "supports_tool_choice": true + }, + "replicate/meta/llama-2-70b-chat": { + "input_cost_per_token": 6.5e-07, + "litellm_provider": "replicate", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2.75e-06, + "supports_tool_choice": true + }, + "replicate/meta/llama-2-7b": { + "input_cost_per_token": 5e-08, + "litellm_provider": "replicate", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2.5e-07, + "supports_tool_choice": true + }, + "replicate/meta/llama-2-7b-chat": { + "input_cost_per_token": 5e-08, + "litellm_provider": "replicate", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2.5e-07, + "supports_tool_choice": true + }, + "replicate/meta/llama-3-70b": { + "input_cost_per_token": 6.5e-07, + "litellm_provider": "replicate", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2.75e-06, + "supports_tool_choice": true + }, + "replicate/meta/llama-3-70b-instruct": { + "input_cost_per_token": 6.5e-07, + "litellm_provider": "replicate", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2.75e-06, + "supports_tool_choice": true + }, + "replicate/meta/llama-3-8b": { + "input_cost_per_token": 5e-08, + "litellm_provider": "replicate", + "max_input_tokens": 8086, + "max_output_tokens": 8086, + "max_tokens": 8086, + "mode": "chat", + "output_cost_per_token": 2.5e-07, + "supports_tool_choice": true + }, + "replicate/meta/llama-3-8b-instruct": { + "input_cost_per_token": 5e-08, + "litellm_provider": "replicate", + "max_input_tokens": 8086, + "max_output_tokens": 8086, + "max_tokens": 8086, + "mode": "chat", + "output_cost_per_token": 2.5e-07, + "supports_tool_choice": true + }, + "replicate/mistralai/mistral-7b-instruct-v0.2": { + "input_cost_per_token": 5e-08, + "litellm_provider": "replicate", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2.5e-07, + "supports_tool_choice": true + }, + "replicate/mistralai/mistral-7b-v0.1": { + "input_cost_per_token": 5e-08, + "litellm_provider": "replicate", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2.5e-07, + "supports_tool_choice": true + }, + "replicate/mistralai/mixtral-8x7b-instruct-v0.1": { + "input_cost_per_token": 3e-07, + "litellm_provider": "replicate", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1e-06, + "supports_tool_choice": true + }, + "rerank-english-v2.0": { + "input_cost_per_query": 0.002, + "input_cost_per_token": 0.0, + "litellm_provider": "cohere", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_query_tokens": 2048, + "max_tokens": 4096, + "mode": "rerank", + "output_cost_per_token": 0.0 + }, + "rerank-english-v3.0": { + "input_cost_per_query": 0.002, + "input_cost_per_token": 0.0, + "litellm_provider": "cohere", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_query_tokens": 2048, + "max_tokens": 4096, + "mode": "rerank", + "output_cost_per_token": 0.0 + }, + "rerank-multilingual-v2.0": { + "input_cost_per_query": 0.002, + "input_cost_per_token": 0.0, + "litellm_provider": "cohere", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_query_tokens": 2048, + "max_tokens": 4096, + "mode": "rerank", + "output_cost_per_token": 0.0 + }, + "rerank-multilingual-v3.0": { + "input_cost_per_query": 0.002, + "input_cost_per_token": 0.0, + "litellm_provider": "cohere", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_query_tokens": 2048, + "max_tokens": 4096, + "mode": "rerank", + "output_cost_per_token": 0.0 + }, + "rerank-v3.5": { + "input_cost_per_query": 0.002, + "input_cost_per_token": 0.0, + "litellm_provider": "cohere", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_query_tokens": 2048, + "max_tokens": 4096, + "mode": "rerank", + "output_cost_per_token": 0.0 + }, + "sagemaker/meta-textgeneration-llama-2-13b": { + "input_cost_per_token": 0.0, + "litellm_provider": "sagemaker", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "completion", + "output_cost_per_token": 0.0 + }, + "sagemaker/meta-textgeneration-llama-2-13b-f": { + "input_cost_per_token": 0.0, + "litellm_provider": "sagemaker", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.0 + }, + "sagemaker/meta-textgeneration-llama-2-70b": { + "input_cost_per_token": 0.0, + "litellm_provider": "sagemaker", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "completion", + "output_cost_per_token": 0.0 + }, + "sagemaker/meta-textgeneration-llama-2-70b-b-f": { + "input_cost_per_token": 0.0, + "litellm_provider": "sagemaker", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.0 + }, + "sagemaker/meta-textgeneration-llama-2-7b": { + "input_cost_per_token": 0.0, + "litellm_provider": "sagemaker", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "completion", + "output_cost_per_token": 0.0 + }, + "sagemaker/meta-textgeneration-llama-2-7b-f": { + "input_cost_per_token": 0.0, + "litellm_provider": "sagemaker", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.0 + }, + "sambanova/DeepSeek-R1": { + "input_cost_per_token": 5e-06, + "litellm_provider": "sambanova", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 7e-06, + "source": "https://cloud.sambanova.ai/plans/pricing" + }, + "sambanova/DeepSeek-R1-Distill-Llama-70B": { + "input_cost_per_token": 7e-07, + "litellm_provider": "sambanova", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.4e-06, + "source": "https://cloud.sambanova.ai/plans/pricing" + }, + "sambanova/DeepSeek-V3-0324": { + "input_cost_per_token": 3e-06, + "litellm_provider": "sambanova", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 4.5e-06, + "source": "https://cloud.sambanova.ai/plans/pricing", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "sambanova/Llama-4-Maverick-17B-128E-Instruct": { + "input_cost_per_token": 6.3e-07, + "litellm_provider": "sambanova", + "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": 1.8e-06, + "source": "https://cloud.sambanova.ai/plans/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "sambanova/Llama-4-Scout-17B-16E-Instruct": { + "input_cost_per_token": 4e-07, + "litellm_provider": "sambanova", + "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-07, + "source": "https://cloud.sambanova.ai/plans/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "sambanova/Meta-Llama-3.1-405B-Instruct": { + "input_cost_per_token": 5e-06, + "litellm_provider": "sambanova", + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1e-05, + "source": "https://cloud.sambanova.ai/plans/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "sambanova/Meta-Llama-3.1-8B-Instruct": { + "input_cost_per_token": 1e-07, + "litellm_provider": "sambanova", + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 2e-07, + "source": "https://cloud.sambanova.ai/plans/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "sambanova/Meta-Llama-3.2-1B-Instruct": { + "input_cost_per_token": 4e-08, + "litellm_provider": "sambanova", + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 8e-08, + "source": "https://cloud.sambanova.ai/plans/pricing" + }, + "sambanova/Meta-Llama-3.2-3B-Instruct": { + "input_cost_per_token": 8e-08, + "litellm_provider": "sambanova", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.6e-07, + "source": "https://cloud.sambanova.ai/plans/pricing" + }, + "sambanova/Meta-Llama-3.3-70B-Instruct": { + "input_cost_per_token": 6e-07, + "litellm_provider": "sambanova", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://cloud.sambanova.ai/plans/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "sambanova/Meta-Llama-Guard-3-8B": { + "input_cost_per_token": 3e-07, + "litellm_provider": "sambanova", + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 3e-07, + "source": "https://cloud.sambanova.ai/plans/pricing" + }, + "sambanova/QwQ-32B": { + "input_cost_per_token": 5e-07, + "litellm_provider": "sambanova", + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1e-06, + "source": "https://cloud.sambanova.ai/plans/pricing" + }, + "sambanova/Qwen2-Audio-7B-Instruct": { + "input_cost_per_token": 5e-07, + "litellm_provider": "sambanova", + "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 + }, + "sambanova/Qwen3-32B": { + "input_cost_per_token": 4e-07, + "litellm_provider": "sambanova", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 8e-07, + "source": "https://cloud.sambanova.ai/plans/pricing", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "sambanova/DeepSeek-V3.1": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 3e-06, + "output_cost_per_token": 4.5e-06, + "litellm_provider": "sambanova", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "source": "https://cloud.sambanova.ai/plans/pricing" + }, + "sambanova/gpt-oss-120b": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 3e-06, + "output_cost_per_token": 4.5e-06, + "litellm_provider": "sambanova", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "source": "https://cloud.sambanova.ai/plans/pricing" + }, + "sample_spec": { + "code_interpreter_cost_per_session": 0.0, + "computer_use_input_cost_per_1k_tokens": 0.0, + "computer_use_output_cost_per_1k_tokens": 0.0, + "deprecation_date": "date when the model becomes deprecated in the format YYYY-MM-DD", + "file_search_cost_per_1k_calls": 0.0, + "file_search_cost_per_gb_per_day": 0.0, + "input_cost_per_audio_token": 0.0, + "input_cost_per_token": 0.0, + "litellm_provider": "one of https://docs.litellm.ai/docs/providers", + "max_input_tokens": "max input tokens, if the provider specifies it. if not default to max_tokens", + "max_output_tokens": "max output tokens, if the provider specifies it. if not default to max_tokens", + "max_tokens": "LEGACY parameter. set to max_output_tokens if provider specifies it. IF not set to max_input_tokens, if provider specifies it.", + "mode": "one of: chat, embedding, completion, image_generation, audio_transcription, audio_speech, image_generation, moderation, rerank", + "output_cost_per_reasoning_token": 0.0, + "output_cost_per_token": 0.0, + "search_context_cost_per_query": { + "search_context_size_high": 0.0, + "search_context_size_low": 0.0, + "search_context_size_medium": 0.0 + }, + "supported_regions": [ + "global", + "us-west-2", + "eu-west-1", + "ap-southeast-1", + "ap-northeast-1" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_vision": true, + "supports_web_search": true, + "vector_store_cost_per_gb_per_day": 0.0 + }, + "snowflake/claude-3-5-sonnet": { + "litellm_provider": "snowflake", + "max_input_tokens": 18000, + "max_output_tokens": 8192, + "max_tokens": 18000, + "mode": "chat", + "supports_computer_use": true + }, + "snowflake/deepseek-r1": { + "litellm_provider": "snowflake", + "max_input_tokens": 32768, + "max_output_tokens": 8192, + "max_tokens": 32768, + "mode": "chat", + "supports_reasoning": true + }, + "snowflake/gemma-7b": { + "litellm_provider": "snowflake", + "max_input_tokens": 8000, + "max_output_tokens": 8192, + "max_tokens": 8000, + "mode": "chat" + }, + "snowflake/jamba-1.5-large": { + "litellm_provider": "snowflake", + "max_input_tokens": 256000, + "max_output_tokens": 8192, + "max_tokens": 256000, + "mode": "chat" + }, + "snowflake/jamba-1.5-mini": { + "litellm_provider": "snowflake", + "max_input_tokens": 256000, + "max_output_tokens": 8192, + "max_tokens": 256000, + "mode": "chat" + }, + "snowflake/jamba-instruct": { + "litellm_provider": "snowflake", + "max_input_tokens": 256000, + "max_output_tokens": 8192, + "max_tokens": 256000, + "mode": "chat" + }, + "snowflake/llama2-70b-chat": { + "litellm_provider": "snowflake", + "max_input_tokens": 4096, + "max_output_tokens": 8192, + "max_tokens": 4096, + "mode": "chat" + }, + "snowflake/llama3-70b": { + "litellm_provider": "snowflake", + "max_input_tokens": 8000, + "max_output_tokens": 8192, + "max_tokens": 8000, + "mode": "chat" + }, + "snowflake/llama3-8b": { + "litellm_provider": "snowflake", + "max_input_tokens": 8000, + "max_output_tokens": 8192, + "max_tokens": 8000, + "mode": "chat" + }, + "snowflake/llama3.1-405b": { + "litellm_provider": "snowflake", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 128000, + "mode": "chat" + }, + "snowflake/llama3.1-70b": { + "litellm_provider": "snowflake", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 128000, + "mode": "chat" + }, + "snowflake/llama3.1-8b": { + "litellm_provider": "snowflake", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 128000, + "mode": "chat" + }, + "snowflake/llama3.2-1b": { + "litellm_provider": "snowflake", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 128000, + "mode": "chat" + }, + "snowflake/llama3.2-3b": { + "litellm_provider": "snowflake", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 128000, + "mode": "chat" + }, + "snowflake/llama3.3-70b": { + "litellm_provider": "snowflake", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 128000, + "mode": "chat" + }, + "snowflake/mistral-7b": { + "litellm_provider": "snowflake", + "max_input_tokens": 32000, + "max_output_tokens": 8192, + "max_tokens": 32000, + "mode": "chat" + }, + "snowflake/mistral-large": { + "litellm_provider": "snowflake", + "max_input_tokens": 32000, + "max_output_tokens": 8192, + "max_tokens": 32000, + "mode": "chat" + }, + "snowflake/mistral-large2": { + "litellm_provider": "snowflake", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 128000, + "mode": "chat" + }, + "snowflake/mixtral-8x7b": { + "litellm_provider": "snowflake", + "max_input_tokens": 32000, + "max_output_tokens": 8192, + "max_tokens": 32000, + "mode": "chat" + }, + "snowflake/reka-core": { + "litellm_provider": "snowflake", + "max_input_tokens": 32000, + "max_output_tokens": 8192, + "max_tokens": 32000, + "mode": "chat" + }, + "snowflake/reka-flash": { + "litellm_provider": "snowflake", + "max_input_tokens": 100000, + "max_output_tokens": 8192, + "max_tokens": 100000, + "mode": "chat" + }, + "snowflake/snowflake-arctic": { + "litellm_provider": "snowflake", + "max_input_tokens": 4096, + "max_output_tokens": 8192, + "max_tokens": 4096, + "mode": "chat" + }, + "snowflake/snowflake-llama-3.1-405b": { + "litellm_provider": "snowflake", + "max_input_tokens": 8000, + "max_output_tokens": 8192, + "max_tokens": 8000, + "mode": "chat" + }, + "snowflake/snowflake-llama-3.3-70b": { + "litellm_provider": "snowflake", + "max_input_tokens": 8000, + "max_output_tokens": 8192, + "max_tokens": 8000, + "mode": "chat" + }, + "stability.sd3-5-large-v1:0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "max_tokens": 77, + "mode": "image_generation", + "output_cost_per_image": 0.08 + }, + "stability.sd3-large-v1:0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "max_tokens": 77, + "mode": "image_generation", + "output_cost_per_image": 0.08 + }, + "stability.stable-image-core-v1:0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "max_tokens": 77, + "mode": "image_generation", + "output_cost_per_image": 0.04 + }, + "stability.stable-image-core-v1:1": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "max_tokens": 77, + "mode": "image_generation", + "output_cost_per_image": 0.04 + }, + "stability.stable-image-ultra-v1:0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "max_tokens": 77, + "mode": "image_generation", + "output_cost_per_image": 0.14 + }, + "stability.stable-image-ultra-v1:1": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "max_tokens": 77, + "mode": "image_generation", + "output_cost_per_image": 0.14 + }, + "standard/1024-x-1024/dall-e-3": { + "input_cost_per_pixel": 3.81469e-08, + "litellm_provider": "openai", + "mode": "image_generation", + "output_cost_per_pixel": 0.0 + }, + "standard/1024-x-1792/dall-e-3": { + "input_cost_per_pixel": 4.359e-08, + "litellm_provider": "openai", + "mode": "image_generation", + "output_cost_per_pixel": 0.0 + }, + "standard/1792-x-1024/dall-e-3": { + "input_cost_per_pixel": 4.359e-08, + "litellm_provider": "openai", + "mode": "image_generation", + "output_cost_per_pixel": 0.0 + }, + "text-bison": { + "input_cost_per_character": 2.5e-07, + "litellm_provider": "vertex_ai-text-models", + "max_input_tokens": 8192, + "max_output_tokens": 2048, + "max_tokens": 2048, + "mode": "completion", + "output_cost_per_character": 5e-07, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" + }, + "text-bison32k": { + "input_cost_per_character": 2.5e-07, + "input_cost_per_token": 1.25e-07, + "litellm_provider": "vertex_ai-text-models", + "max_input_tokens": 8192, + "max_output_tokens": 1024, + "max_tokens": 1024, + "mode": "completion", + "output_cost_per_character": 5e-07, + "output_cost_per_token": 1.25e-07, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" + }, + "text-bison32k@002": { + "input_cost_per_character": 2.5e-07, + "input_cost_per_token": 1.25e-07, + "litellm_provider": "vertex_ai-text-models", + "max_input_tokens": 8192, + "max_output_tokens": 1024, + "max_tokens": 1024, + "mode": "completion", + "output_cost_per_character": 5e-07, + "output_cost_per_token": 1.25e-07, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" + }, + "text-bison@001": { + "input_cost_per_character": 2.5e-07, + "litellm_provider": "vertex_ai-text-models", + "max_input_tokens": 8192, + "max_output_tokens": 1024, + "max_tokens": 1024, + "mode": "completion", + "output_cost_per_character": 5e-07, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" + }, + "text-bison@002": { + "input_cost_per_character": 2.5e-07, + "litellm_provider": "vertex_ai-text-models", + "max_input_tokens": 8192, + "max_output_tokens": 1024, + "max_tokens": 1024, + "mode": "completion", + "output_cost_per_character": 5e-07, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" + }, + "text-completion-codestral/codestral-2405": { + "input_cost_per_token": 0.0, + "litellm_provider": "text-completion-codestral", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "completion", + "output_cost_per_token": 0.0, + "source": "https://docs.mistral.ai/capabilities/code_generation/" + }, + "text-completion-codestral/codestral-latest": { + "input_cost_per_token": 0.0, + "litellm_provider": "text-completion-codestral", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "completion", + "output_cost_per_token": 0.0, + "source": "https://docs.mistral.ai/capabilities/code_generation/" + }, + "text-embedding-004": { + "input_cost_per_character": 2.5e-08, + "input_cost_per_token": 1e-07, + "litellm_provider": "vertex_ai-embedding-models", + "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" + }, + "text-embedding-005": { + "input_cost_per_character": 2.5e-08, + "input_cost_per_token": 1e-07, + "litellm_provider": "vertex_ai-embedding-models", + "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" + }, + "text-embedding-3-large": { + "input_cost_per_token": 1.3e-07, + "input_cost_per_token_batches": 6.5e-08, + "litellm_provider": "openai", + "max_input_tokens": 8191, + "max_tokens": 8191, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_cost_per_token_batches": 0.0, + "output_vector_size": 3072 + }, + "text-embedding-3-small": { + "input_cost_per_token": 2e-08, + "input_cost_per_token_batches": 1e-08, + "litellm_provider": "openai", + "max_input_tokens": 8191, + "max_tokens": 8191, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_cost_per_token_batches": 0.0, + "output_vector_size": 1536 + }, + "text-embedding-ada-002": { + "input_cost_per_token": 1e-07, + "litellm_provider": "openai", + "max_input_tokens": 8191, + "max_tokens": 8191, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 1536 + }, + "text-embedding-ada-002-v2": { + "input_cost_per_token": 1e-07, + "input_cost_per_token_batches": 5e-08, + "litellm_provider": "openai", + "max_input_tokens": 8191, + "max_tokens": 8191, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_cost_per_token_batches": 0.0 + }, + "text-embedding-large-exp-03-07": { + "input_cost_per_character": 2.5e-08, + "input_cost_per_token": 1e-07, + "litellm_provider": "vertex_ai-embedding-models", + "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" + }, + "text-embedding-preview-0409": { + "input_cost_per_token": 6.25e-09, + "input_cost_per_token_batch_requests": 5e-09, + "litellm_provider": "vertex_ai-embedding-models", + "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" + }, + "text-moderation-007": { + "input_cost_per_token": 0.0, + "litellm_provider": "openai", + "max_input_tokens": 32768, + "max_output_tokens": 0, + "max_tokens": 32768, + "mode": "moderation", + "output_cost_per_token": 0.0 + }, + "text-moderation-latest": { + "input_cost_per_token": 0.0, + "litellm_provider": "openai", + "max_input_tokens": 32768, + "max_output_tokens": 0, + "max_tokens": 32768, + "mode": "moderation", + "output_cost_per_token": 0.0 + }, + "text-moderation-stable": { + "input_cost_per_token": 0.0, + "litellm_provider": "openai", + "max_input_tokens": 32768, + "max_output_tokens": 0, + "max_tokens": 32768, + "mode": "moderation", + "output_cost_per_token": 0.0 + }, + "text-multilingual-embedding-002": { + "input_cost_per_character": 2.5e-08, + "input_cost_per_token": 1e-07, + "litellm_provider": "vertex_ai-embedding-models", + "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" + }, + "text-multilingual-embedding-preview-0409": { + "input_cost_per_token": 6.25e-09, + "litellm_provider": "vertex_ai-embedding-models", + "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" + }, + "text-unicorn": { + "input_cost_per_token": 1e-05, + "litellm_provider": "vertex_ai-text-models", + "max_input_tokens": 8192, + "max_output_tokens": 1024, + "max_tokens": 1024, + "mode": "completion", + "output_cost_per_token": 2.8e-05, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" + }, + "text-unicorn@001": { + "input_cost_per_token": 1e-05, + "litellm_provider": "vertex_ai-text-models", + "max_input_tokens": 8192, + "max_output_tokens": 1024, + "max_tokens": 1024, + "mode": "completion", + "output_cost_per_token": 2.8e-05, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" + }, + "textembedding-gecko": { + "input_cost_per_character": 2.5e-08, + "input_cost_per_token": 1e-07, + "litellm_provider": "vertex_ai-embedding-models", + "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" + }, + "textembedding-gecko-multilingual": { + "input_cost_per_character": 2.5e-08, + "input_cost_per_token": 1e-07, + "litellm_provider": "vertex_ai-embedding-models", + "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" + }, + "textembedding-gecko-multilingual@001": { + "input_cost_per_character": 2.5e-08, + "input_cost_per_token": 1e-07, + "litellm_provider": "vertex_ai-embedding-models", + "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" + }, + "textembedding-gecko@001": { + "input_cost_per_character": 2.5e-08, + "input_cost_per_token": 1e-07, + "litellm_provider": "vertex_ai-embedding-models", + "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" + }, + "textembedding-gecko@003": { + "input_cost_per_character": 2.5e-08, + "input_cost_per_token": 1e-07, + "litellm_provider": "vertex_ai-embedding-models", + "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" + }, + "together-ai-21.1b-41b": { + "input_cost_per_token": 8e-07, + "litellm_provider": "together_ai", + "mode": "chat", + "output_cost_per_token": 8e-07 + }, + "together-ai-4.1b-8b": { + "input_cost_per_token": 2e-07, + "litellm_provider": "together_ai", + "mode": "chat", + "output_cost_per_token": 2e-07 + }, + "together-ai-41.1b-80b": { + "input_cost_per_token": 9e-07, + "litellm_provider": "together_ai", + "mode": "chat", + "output_cost_per_token": 9e-07 + }, + "together-ai-8.1b-21b": { + "input_cost_per_token": 3e-07, + "litellm_provider": "together_ai", + "max_tokens": 1000, + "mode": "chat", + "output_cost_per_token": 3e-07 + }, + "together-ai-81.1b-110b": { + "input_cost_per_token": 1.8e-06, + "litellm_provider": "together_ai", + "mode": "chat", + "output_cost_per_token": 1.8e-06 + }, + "together-ai-embedding-151m-to-350m": { + "input_cost_per_token": 1.6e-08, + "litellm_provider": "together_ai", + "mode": "embedding", + "output_cost_per_token": 0.0 + }, + "together-ai-embedding-up-to-150m": { + "input_cost_per_token": 8e-09, + "litellm_provider": "together_ai", + "mode": "embedding", + "output_cost_per_token": 0.0 + }, + "together-ai-up-to-4b": { + "input_cost_per_token": 1e-07, + "litellm_provider": "together_ai", + "mode": "chat", + "output_cost_per_token": 1e-07 + }, + "together_ai/Qwen/Qwen2.5-72B-Instruct-Turbo": { + "litellm_provider": "together_ai", + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "together_ai/Qwen/Qwen2.5-7B-Instruct-Turbo": { + "litellm_provider": "together_ai", + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "together_ai/Qwen/Qwen3-235B-A22B-Instruct-2507-tput": { + "input_cost_per_token": 2e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 262000, + "mode": "chat", + "output_cost_per_token": 6e-06, + "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 + }, + "together_ai/Qwen/Qwen3-235B-A22B-Thinking-2507": { + "input_cost_per_token": 6.5e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 3e-06, + "source": "https://www.together.ai/models/qwen3-235b-a22b-thinking-2507", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "together_ai/Qwen/Qwen3-235B-A22B-fp8-tput": { + "input_cost_per_token": 2e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 40000, + "mode": "chat", + "output_cost_per_token": 6e-07, + "source": "https://www.together.ai/models/qwen3-235b-a22b-fp8-tput", + "supports_function_calling": false, + "supports_parallel_function_calling": false, + "supports_tool_choice": false + }, + "together_ai/Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8": { + "input_cost_per_token": 2e-06, + "litellm_provider": "together_ai", + "max_input_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 2e-06, + "source": "https://www.together.ai/models/qwen3-coder-480b-a35b-instruct", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "together_ai/deepseek-ai/DeepSeek-R1": { + "input_cost_per_token": 3e-06, + "litellm_provider": "together_ai", + "max_input_tokens": 128000, + "max_output_tokens": 20480, + "max_tokens": 20480, + "mode": "chat", + "output_cost_per_token": 7e-06, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "together_ai/deepseek-ai/DeepSeek-R1-0528-tput": { + "input_cost_per_token": 5.5e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.19e-06, + "source": "https://www.together.ai/models/deepseek-r1-0528-throughput", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "together_ai/deepseek-ai/DeepSeek-V3": { + "input_cost_per_token": 1.25e-06, + "litellm_provider": "together_ai", + "max_input_tokens": 65536, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.25e-06, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "together_ai/deepseek-ai/DeepSeek-V3.1": { + "input_cost_per_token": 6e-07, + "litellm_provider": "together_ai", + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.7e-06, + "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 + }, + "together_ai/meta-llama/Llama-3.2-3B-Instruct-Turbo": { + "litellm_provider": "together_ai", + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "together_ai/meta-llama/Llama-3.3-70B-Instruct-Turbo": { + "input_cost_per_token": 8.8e-07, + "litellm_provider": "together_ai", + "mode": "chat", + "output_cost_per_token": 8.8e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "together_ai/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free": { + "input_cost_per_token": 0, + "litellm_provider": "together_ai", + "mode": "chat", + "output_cost_per_token": 0, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "together_ai/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8": { + "input_cost_per_token": 2.7e-07, + "litellm_provider": "together_ai", + "mode": "chat", + "output_cost_per_token": 8.5e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "together_ai/meta-llama/Llama-4-Scout-17B-16E-Instruct": { + "input_cost_per_token": 1.8e-07, + "litellm_provider": "together_ai", + "mode": "chat", + "output_cost_per_token": 5.9e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "together_ai/meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo": { + "input_cost_per_token": 3.5e-06, + "litellm_provider": "together_ai", + "mode": "chat", + "output_cost_per_token": 3.5e-06, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "together_ai/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo": { + "input_cost_per_token": 8.8e-07, + "litellm_provider": "together_ai", + "mode": "chat", + "output_cost_per_token": 8.8e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "together_ai/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo": { + "input_cost_per_token": 1.8e-07, + "litellm_provider": "together_ai", + "mode": "chat", + "output_cost_per_token": 1.8e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "together_ai/mistralai/Mistral-7B-Instruct-v0.1": { + "litellm_provider": "together_ai", + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "together_ai/mistralai/Mistral-Small-24B-Instruct-2501": { + "litellm_provider": "together_ai", + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "together_ai/mistralai/Mixtral-8x7B-Instruct-v0.1": { + "input_cost_per_token": 6e-07, + "litellm_provider": "together_ai", + "mode": "chat", + "output_cost_per_token": 6e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "together_ai/moonshotai/Kimi-K2-Instruct": { + "input_cost_per_token": 1e-06, + "litellm_provider": "together_ai", + "mode": "chat", + "output_cost_per_token": 3e-06, + "source": "https://www.together.ai/models/kimi-k2-instruct", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "together_ai/openai/gpt-oss-120b": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-07, + "source": "https://www.together.ai/models/gpt-oss-120b", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "together_ai/openai/gpt-oss-20b": { + "input_cost_per_token": 5e-08, + "litellm_provider": "together_ai", + "max_input_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2e-07, + "source": "https://www.together.ai/models/gpt-oss-20b", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "together_ai/togethercomputer/CodeLlama-34b-Instruct": { + "litellm_provider": "together_ai", + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "together_ai/zai-org/GLM-4.5-Air-FP8": { + "input_cost_per_token": 2e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.1e-06, + "source": "https://www.together.ai/models/glm-4-5-air", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "tts-1": { + "input_cost_per_character": 1.5e-05, + "litellm_provider": "openai", + "mode": "audio_speech", + "supported_endpoints": [ + "/v1/audio/speech" + ] + }, + "tts-1-hd": { + "input_cost_per_character": 3e-05, + "litellm_provider": "openai", + "mode": "audio_speech", + "supported_endpoints": [ + "/v1/audio/speech" + ] + }, + "us.amazon.nova-lite-v1:0": { + "input_cost_per_token": 6e-08, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 300000, + "max_output_tokens": 10000, + "max_tokens": 10000, + "mode": "chat", + "output_cost_per_token": 2.4e-07, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_vision": true + }, + "us.amazon.nova-micro-v1:0": { + "input_cost_per_token": 3.5e-08, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 128000, + "max_output_tokens": 10000, + "max_tokens": 10000, + "mode": "chat", + "output_cost_per_token": 1.4e-07, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true + }, + "us.amazon.nova-premier-v1:0": { + "input_cost_per_token": 2.5e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 10000, + "max_tokens": 10000, + "mode": "chat", + "output_cost_per_token": 1.25e-05, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": false, + "supports_response_schema": true, + "supports_vision": true + }, + "us.amazon.nova-pro-v1:0": { + "input_cost_per_token": 8e-07, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 300000, + "max_output_tokens": 10000, + "max_tokens": 10000, + "mode": "chat", + "output_cost_per_token": 3.2e-06, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_vision": true + }, + "us.anthropic.claude-3-5-haiku-20241022-v1:0": { + "cache_creation_input_token_cost": 1e-06, + "cache_read_input_token_cost": 8e-08, + "input_cost_per_token": 8e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 4e-06, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "us.anthropic.claude-3-5-sonnet-20240620-v1:0": { + "input_cost_per_token": 3e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "us.anthropic.claude-3-5-sonnet-20241022-v2:0": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "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 + }, + "us.anthropic.claude-3-7-sonnet-20250219-v1:0": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "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 + }, + "us.anthropic.claude-3-haiku-20240307-v1:0": { + "input_cost_per_token": 2.5e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.25e-06, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "us.anthropic.claude-3-opus-20240229-v1:0": { + "input_cost_per_token": 1.5e-05, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "us.anthropic.claude-3-sonnet-20240229-v1:0": { + "input_cost_per_token": 3e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "us.anthropic.claude-opus-4-1-20250805-v1:0": { + "cache_creation_input_token_cost": 1.875e-05, + "cache_read_input_token_cost": 1.5e-06, + "input_cost_per_token": 1.5e-05, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 200000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "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 + }, + "us.anthropic.claude-sonnet-4-5-20250929-v1:0": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 200000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "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 + }, + "us.anthropic.claude-opus-4-20250514-v1:0": { + "cache_creation_input_token_cost": 1.875e-05, + "cache_read_input_token_cost": 1.5e-06, + "input_cost_per_token": 1.5e-05, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 200000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "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 + }, + "us.anthropic.claude-sonnet-4-20250514-v1:0": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "input_cost_per_token_above_200k_tokens": 6e-06, + "output_cost_per_token_above_200k_tokens": 2.25e-05, + "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, + "cache_read_input_token_cost_above_200k_tokens": 6e-07, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "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 + }, + "us.deepseek.r1-v1:0": { + "input_cost_per_token": 1.35e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 5.4e-06, + "supports_function_calling": false, + "supports_reasoning": true, + "supports_tool_choice": false + }, + "us.meta.llama3-1-405b-instruct-v1:0": { + "input_cost_per_token": 5.32e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.6e-05, + "supports_function_calling": true, + "supports_tool_choice": false + }, + "us.meta.llama3-1-70b-instruct-v1:0": { + "input_cost_per_token": 9.9e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 2048, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 9.9e-07, + "supports_function_calling": true, + "supports_tool_choice": false + }, + "us.meta.llama3-1-8b-instruct-v1:0": { + "input_cost_per_token": 2.2e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 2048, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.2e-07, + "supports_function_calling": true, + "supports_tool_choice": false + }, + "us.meta.llama3-2-11b-instruct-v1:0": { + "input_cost_per_token": 3.5e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3.5e-07, + "supports_function_calling": true, + "supports_tool_choice": false, + "supports_vision": true + }, + "us.meta.llama3-2-1b-instruct-v1:0": { + "input_cost_per_token": 1e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-07, + "supports_function_calling": true, + "supports_tool_choice": false + }, + "us.meta.llama3-2-3b-instruct-v1:0": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.5e-07, + "supports_function_calling": true, + "supports_tool_choice": false + }, + "us.meta.llama3-2-90b-instruct-v1:0": { + "input_cost_per_token": 2e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2e-06, + "supports_function_calling": true, + "supports_tool_choice": false, + "supports_vision": true + }, + "us.meta.llama3-3-70b-instruct-v1:0": { + "input_cost_per_token": 7.2e-07, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 7.2e-07, + "supports_function_calling": true, + "supports_tool_choice": false + }, + "us.meta.llama4-maverick-17b-instruct-v1:0": { + "input_cost_per_token": 2.4e-07, + "input_cost_per_token_batches": 1.2e-07, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 9.7e-07, + "output_cost_per_token_batches": 4.85e-07, + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text", + "code" + ], + "supports_function_calling": true, + "supports_tool_choice": false + }, + "us.meta.llama4-scout-17b-instruct-v1:0": { + "input_cost_per_token": 1.7e-07, + "input_cost_per_token_batches": 8.5e-08, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 6.6e-07, + "output_cost_per_token_batches": 3.3e-07, + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text", + "code" + ], + "supports_function_calling": true, + "supports_tool_choice": false + }, + "us.mistral.pixtral-large-2502-v1:0": { + "input_cost_per_token": 2e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-06, + "supports_function_calling": true, + "supports_tool_choice": false + }, + "v0/v0-1.0-md": { + "input_cost_per_token": 3e-06, + "litellm_provider": "v0", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "v0/v0-1.5-lg": { + "input_cost_per_token": 1.5e-05, + "litellm_provider": "v0", + "max_input_tokens": 512000, + "max_output_tokens": 512000, + "max_tokens": 512000, + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "v0/v0-1.5-md": { + "input_cost_per_token": 3e-06, + "litellm_provider": "v0", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "vercel_ai_gateway/alibaba/qwen-3-14b": { + "input_cost_per_token": 8e-08, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 40960, + "max_output_tokens": 16384, + "max_tokens": 40960, + "mode": "chat", + "output_cost_per_token": 2.4e-07 + }, + "vercel_ai_gateway/alibaba/qwen-3-235b": { + "input_cost_per_token": 2e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 40960, + "max_output_tokens": 16384, + "max_tokens": 40960, + "mode": "chat", + "output_cost_per_token": 6e-07 + }, + "vercel_ai_gateway/alibaba/qwen-3-30b": { + "input_cost_per_token": 1e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 40960, + "max_output_tokens": 16384, + "max_tokens": 40960, + "mode": "chat", + "output_cost_per_token": 3e-07 + }, + "vercel_ai_gateway/alibaba/qwen-3-32b": { + "input_cost_per_token": 1e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 40960, + "max_output_tokens": 16384, + "max_tokens": 40960, + "mode": "chat", + "output_cost_per_token": 3e-07 + }, + "vercel_ai_gateway/alibaba/qwen3-coder": { + "input_cost_per_token": 4e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 262144, + "max_output_tokens": 66536, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 1.6e-06 + }, + "vercel_ai_gateway/amazon/nova-lite": { + "input_cost_per_token": 6e-08, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 300000, + "max_output_tokens": 8192, + "max_tokens": 300000, + "mode": "chat", + "output_cost_per_token": 2.4e-07 + }, + "vercel_ai_gateway/amazon/nova-micro": { + "input_cost_per_token": 3.5e-08, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.4e-07 + }, + "vercel_ai_gateway/amazon/nova-pro": { + "input_cost_per_token": 8e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 300000, + "max_output_tokens": 8192, + "max_tokens": 300000, + "mode": "chat", + "output_cost_per_token": 3.2e-06 + }, + "vercel_ai_gateway/amazon/titan-embed-text-v2": { + "input_cost_per_token": 2e-08, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 0, + "max_output_tokens": 0, + "max_tokens": 0, + "mode": "chat", + "output_cost_per_token": 0.0 + }, + "vercel_ai_gateway/anthropic/claude-3-haiku": { + "cache_creation_input_token_cost": 3e-07, + "cache_read_input_token_cost": 3e-08, + "input_cost_per_token": 2.5e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 200000, + "mode": "chat", + "output_cost_per_token": 1.25e-06 + }, + "vercel_ai_gateway/anthropic/claude-3-opus": { + "cache_creation_input_token_cost": 1.875e-05, + "cache_read_input_token_cost": 1.5e-06, + "input_cost_per_token": 1.5e-05, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 200000, + "mode": "chat", + "output_cost_per_token": 7.5e-05 + }, + "vercel_ai_gateway/anthropic/claude-3.5-haiku": { + "cache_creation_input_token_cost": 1e-06, + "cache_read_input_token_cost": 8e-08, + "input_cost_per_token": 8e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 200000, + "mode": "chat", + "output_cost_per_token": 4e-06 + }, + "vercel_ai_gateway/anthropic/claude-3.5-sonnet": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 200000, + "mode": "chat", + "output_cost_per_token": 1.5e-05 + }, + "vercel_ai_gateway/anthropic/claude-3.7-sonnet": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 200000, + "mode": "chat", + "output_cost_per_token": 1.5e-05 + }, + "vercel_ai_gateway/anthropic/claude-4-opus": { + "cache_creation_input_token_cost": 1.875e-05, + "cache_read_input_token_cost": 1.5e-06, + "input_cost_per_token": 1.5e-05, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 200000, + "max_output_tokens": 32000, + "max_tokens": 200000, + "mode": "chat", + "output_cost_per_token": 7.5e-05 + }, + "vercel_ai_gateway/anthropic/claude-4-sonnet": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 200000, + "mode": "chat", + "output_cost_per_token": 1.5e-05 + }, + "vercel_ai_gateway/cohere/command-a": { + "input_cost_per_token": 2.5e-06, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 256000, + "max_output_tokens": 8000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 1e-05 + }, + "vercel_ai_gateway/cohere/command-r": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-07 + }, + "vercel_ai_gateway/cohere/command-r-plus": { + "input_cost_per_token": 2.5e-06, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05 + }, + "vercel_ai_gateway/cohere/embed-v4.0": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 0, + "max_output_tokens": 0, + "max_tokens": 0, + "mode": "chat", + "output_cost_per_token": 0.0 + }, + "vercel_ai_gateway/deepseek/deepseek-r1": { + "input_cost_per_token": 5.5e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.19e-06 + }, + "vercel_ai_gateway/deepseek/deepseek-r1-distill-llama-70b": { + "input_cost_per_token": 7.5e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 9.9e-07 + }, + "vercel_ai_gateway/deepseek/deepseek-v3": { + "input_cost_per_token": 9e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 9e-07 + }, + "vercel_ai_gateway/google/gemini-2.0-flash": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 6e-07 + }, + "vercel_ai_gateway/google/gemini-2.0-flash-lite": { + "input_cost_per_token": 7.5e-08, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 3e-07 + }, + "vercel_ai_gateway/google/gemini-2.5-flash": { + "input_cost_per_token": 3e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 1000000, + "max_output_tokens": 65536, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 2.5e-06 + }, + "vercel_ai_gateway/google/gemini-2.5-pro": { + "input_cost_per_token": 2.5e-06, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 1e-05 + }, + "vercel_ai_gateway/google/gemini-embedding-001": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 0, + "max_output_tokens": 0, + "max_tokens": 0, + "mode": "embedding", + "output_cost_per_token": 0.0 + }, + "vercel_ai_gateway/google/gemma-2-9b": { + "input_cost_per_token": 2e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2e-07 + }, + "vercel_ai_gateway/google/text-embedding-005": { + "input_cost_per_token": 2.5e-08, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 0, + "max_output_tokens": 0, + "max_tokens": 0, + "mode": "embedding", + "output_cost_per_token": 0.0 + }, + "vercel_ai_gateway/google/text-multilingual-embedding-002": { + "input_cost_per_token": 2.5e-08, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 0, + "max_output_tokens": 0, + "max_tokens": 0, + "mode": "embedding", + "output_cost_per_token": 0.0 + }, + "vercel_ai_gateway/inception/mercury-coder-small": { + "input_cost_per_token": 2.5e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 32000, + "max_output_tokens": 16384, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 1e-06 + }, + "vercel_ai_gateway/meta/llama-3-70b": { + "input_cost_per_token": 5.9e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 7.9e-07 + }, + "vercel_ai_gateway/meta/llama-3-8b": { + "input_cost_per_token": 5e-08, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 8e-08 + }, + "vercel_ai_gateway/meta/llama-3.1-70b": { + "input_cost_per_token": 7.2e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 7.2e-07 + }, + "vercel_ai_gateway/meta/llama-3.1-8b": { + "input_cost_per_token": 5e-08, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 131000, + "max_output_tokens": 131072, + "max_tokens": 131000, + "mode": "chat", + "output_cost_per_token": 8e-08 + }, + "vercel_ai_gateway/meta/llama-3.2-11b": { + "input_cost_per_token": 1.6e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.6e-07 + }, + "vercel_ai_gateway/meta/llama-3.2-1b": { + "input_cost_per_token": 1e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-07 + }, + "vercel_ai_gateway/meta/llama-3.2-3b": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.5e-07 + }, + "vercel_ai_gateway/meta/llama-3.2-90b": { + "input_cost_per_token": 7.2e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 7.2e-07 + }, + "vercel_ai_gateway/meta/llama-3.3-70b": { + "input_cost_per_token": 7.2e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 7.2e-07 + }, + "vercel_ai_gateway/meta/llama-4-maverick": { + "input_cost_per_token": 2e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 131072, + "max_output_tokens": 8192, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 6e-07 + }, + "vercel_ai_gateway/meta/llama-4-scout": { + "input_cost_per_token": 1e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 131072, + "max_output_tokens": 8192, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 3e-07 + }, + "vercel_ai_gateway/mistral/codestral": { + "input_cost_per_token": 3e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 256000, + "max_output_tokens": 4000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 9e-07 + }, + "vercel_ai_gateway/mistral/codestral-embed": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 0, + "max_output_tokens": 0, + "max_tokens": 0, + "mode": "chat", + "output_cost_per_token": 0.0 + }, + "vercel_ai_gateway/mistral/devstral-small": { + "input_cost_per_token": 7e-08, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.8e-07 + }, + "vercel_ai_gateway/mistral/magistral-medium": { + "input_cost_per_token": 2e-06, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, + "max_output_tokens": 64000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-06 + }, + "vercel_ai_gateway/mistral/magistral-small": { + "input_cost_per_token": 5e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, + "max_output_tokens": 64000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.5e-06 + }, + "vercel_ai_gateway/mistral/ministral-3b": { + "input_cost_per_token": 4e-08, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, + "max_output_tokens": 4000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4e-08 + }, + "vercel_ai_gateway/mistral/ministral-8b": { + "input_cost_per_token": 1e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, + "max_output_tokens": 4000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-07 + }, + "vercel_ai_gateway/mistral/mistral-embed": { + "input_cost_per_token": 1e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 0, + "max_output_tokens": 0, + "max_tokens": 0, + "mode": "chat", + "output_cost_per_token": 0.0 + }, + "vercel_ai_gateway/mistral/mistral-large": { + "input_cost_per_token": 2e-06, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 32000, + "max_output_tokens": 4000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 6e-06 + }, + "vercel_ai_gateway/mistral/mistral-saba-24b": { + "input_cost_per_token": 7.9e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 7.9e-07 + }, + "vercel_ai_gateway/mistral/mistral-small": { + "input_cost_per_token": 1e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 32000, + "max_output_tokens": 4000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 3e-07 + }, + "vercel_ai_gateway/mistral/mixtral-8x22b-instruct": { + "input_cost_per_token": 1.2e-06, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 65536, + "max_output_tokens": 2048, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1.2e-06 + }, + "vercel_ai_gateway/mistral/pixtral-12b": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, + "max_output_tokens": 4000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.5e-07 + }, + "vercel_ai_gateway/mistral/pixtral-large": { + "input_cost_per_token": 2e-06, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, + "max_output_tokens": 4000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-06 + }, + "vercel_ai_gateway/moonshotai/kimi-k2": { + "input_cost_per_token": 5.5e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 131072, + "max_output_tokens": 16384, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.2e-06 + }, + "vercel_ai_gateway/morph/morph-v3-fast": { + "input_cost_per_token": 8e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 32768, + "max_output_tokens": 16384, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 1.2e-06 + }, + "vercel_ai_gateway/morph/morph-v3-large": { + "input_cost_per_token": 9e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 32768, + "max_output_tokens": 16384, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 1.9e-06 + }, + "vercel_ai_gateway/openai/gpt-3.5-turbo": { + "input_cost_per_token": 5e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 16385, + "max_output_tokens": 4096, + "max_tokens": 16385, + "mode": "chat", + "output_cost_per_token": 1.5e-06 + }, + "vercel_ai_gateway/openai/gpt-3.5-turbo-instruct": { + "input_cost_per_token": 1.5e-06, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 8192, + "max_output_tokens": 4096, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2e-06 + }, + "vercel_ai_gateway/openai/gpt-4-turbo": { + "input_cost_per_token": 1e-05, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3e-05 + }, + "vercel_ai_gateway/openai/gpt-4.1": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 1047576, + "mode": "chat", + "output_cost_per_token": 8e-06 + }, + "vercel_ai_gateway/openai/gpt-4.1-mini": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 4e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 1047576, + "mode": "chat", + "output_cost_per_token": 1.6e-06 + }, + "vercel_ai_gateway/openai/gpt-4.1-nano": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 2.5e-08, + "input_cost_per_token": 1e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 1047576, + "mode": "chat", + "output_cost_per_token": 4e-07 + }, + "vercel_ai_gateway/openai/gpt-4o": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 1.25e-06, + "input_cost_per_token": 2.5e-06, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05 + }, + "vercel_ai_gateway/openai/gpt-4o-mini": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-07 + }, + "vercel_ai_gateway/openai/o1": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 7.5e-06, + "input_cost_per_token": 1.5e-05, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 200000, + "mode": "chat", + "output_cost_per_token": 6e-05 + }, + "vercel_ai_gateway/openai/o3": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 200000, + "mode": "chat", + "output_cost_per_token": 8e-06 + }, + "vercel_ai_gateway/openai/o3-mini": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 5.5e-07, + "input_cost_per_token": 1.1e-06, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 200000, + "mode": "chat", + "output_cost_per_token": 4.4e-06 + }, + "vercel_ai_gateway/openai/o4-mini": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 2.75e-07, + "input_cost_per_token": 1.1e-06, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 200000, + "mode": "chat", + "output_cost_per_token": 4.4e-06 + }, + "vercel_ai_gateway/openai/text-embedding-3-large": { + "input_cost_per_token": 1.3e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 0, + "max_output_tokens": 0, + "max_tokens": 0, + "mode": "embedding", + "output_cost_per_token": 0.0 + }, + "vercel_ai_gateway/openai/text-embedding-3-small": { + "input_cost_per_token": 2e-08, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 0, + "max_output_tokens": 0, + "max_tokens": 0, + "mode": "embedding", + "output_cost_per_token": 0.0 + }, + "vercel_ai_gateway/openai/text-embedding-ada-002": { + "input_cost_per_token": 1e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 0, + "max_output_tokens": 0, + "max_tokens": 0, + "mode": "embedding", + "output_cost_per_token": 0.0 + }, + "vercel_ai_gateway/perplexity/sonar": { + "input_cost_per_token": 1e-06, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 127000, + "max_output_tokens": 8000, + "max_tokens": 127000, + "mode": "chat", + "output_cost_per_token": 1e-06 + }, + "vercel_ai_gateway/perplexity/sonar-pro": { + "input_cost_per_token": 3e-06, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 200000, + "max_output_tokens": 8000, + "max_tokens": 200000, + "mode": "chat", + "output_cost_per_token": 1.5e-05 + }, + "vercel_ai_gateway/perplexity/sonar-reasoning": { + "input_cost_per_token": 1e-06, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 127000, + "max_output_tokens": 8000, + "max_tokens": 127000, + "mode": "chat", + "output_cost_per_token": 5e-06 + }, + "vercel_ai_gateway/perplexity/sonar-reasoning-pro": { + "input_cost_per_token": 2e-06, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 127000, + "max_output_tokens": 8000, + "max_tokens": 127000, + "mode": "chat", + "output_cost_per_token": 8e-06 + }, + "vercel_ai_gateway/vercel/v0-1.0-md": { + "input_cost_per_token": 3e-06, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, + "max_output_tokens": 32000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.5e-05 + }, + "vercel_ai_gateway/vercel/v0-1.5-md": { + "input_cost_per_token": 3e-06, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, + "max_output_tokens": 32768, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.5e-05 + }, + "vercel_ai_gateway/xai/grok-2": { + "input_cost_per_token": 2e-06, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 131072, + "max_output_tokens": 4000, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1e-05 + }, + "vercel_ai_gateway/xai/grok-2-vision": { + "input_cost_per_token": 2e-06, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 1e-05 + }, + "vercel_ai_gateway/xai/grok-3": { + "input_cost_per_token": 3e-06, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.5e-05 + }, + "vercel_ai_gateway/xai/grok-3-fast": { + "input_cost_per_token": 5e-06, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.5e-05 + }, + "vercel_ai_gateway/xai/grok-3-mini": { + "input_cost_per_token": 3e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 5e-07 + }, + "vercel_ai_gateway/xai/grok-3-mini-fast": { + "input_cost_per_token": 6e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4e-06 + }, + "vercel_ai_gateway/xai/grok-4": { + "input_cost_per_token": 3e-06, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 1.5e-05 + }, + "vercel_ai_gateway/zai/glm-4.5": { + "input_cost_per_token": 6e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.2e-06 + }, + "vercel_ai_gateway/zai/glm-4.5-air": { + "input_cost_per_token": 2e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, + "max_output_tokens": 96000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.1e-06 + }, + "vertex_ai/claude-3-5-haiku": { + "input_cost_per_token": 1e-06, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 5e-06, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_tool_choice": true + }, + "vertex_ai/claude-3-5-haiku@20241022": { + "input_cost_per_token": 1e-06, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 5e-06, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_tool_choice": true + }, + "vertex_ai/claude-3-5-sonnet": { + "input_cost_per_token": 3e-06, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "vertex_ai/claude-3-5-sonnet-v2": { + "input_cost_per_token": 3e-06, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "vertex_ai/claude-3-5-sonnet-v2@20241022": { + "input_cost_per_token": 3e-06, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "vertex_ai/claude-3-5-sonnet@20240620": { + "input_cost_per_token": 3e-06, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "vertex_ai/claude-3-7-sonnet@20250219": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_read_input_token_cost": 3e-07, + "deprecation_date": "2025-06-01", + "input_cost_per_token": 3e-06, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "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 + }, + "vertex_ai/claude-3-haiku": { + "input_cost_per_token": 2.5e-07, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.25e-06, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "vertex_ai/claude-3-haiku@20240307": { + "input_cost_per_token": 2.5e-07, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.25e-06, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "vertex_ai/claude-3-opus": { + "input_cost_per_token": 1.5e-05, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "vertex_ai/claude-3-opus@20240229": { + "input_cost_per_token": 1.5e-05, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "vertex_ai/claude-3-sonnet": { + "input_cost_per_token": 3e-06, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "vertex_ai/claude-3-sonnet@20240229": { + "input_cost_per_token": 3e-06, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "vertex_ai/claude-opus-4": { + "cache_creation_input_token_cost": 1.875e-05, + "cache_read_input_token_cost": 1.5e-06, + "input_cost_per_token": 1.5e-05, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 200000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "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 + }, + "vertex_ai/claude-opus-4-1": { + "cache_creation_input_token_cost": 1.875e-05, + "cache_read_input_token_cost": 1.5e-06, + "input_cost_per_token": 1.5e-05, + "input_cost_per_token_batches": 7.5e-06, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "output_cost_per_token_batches": 3.75e-05, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "vertex_ai/claude-opus-4-1@20250805": { + "cache_creation_input_token_cost": 1.875e-05, + "cache_read_input_token_cost": 1.5e-06, + "input_cost_per_token": 1.5e-05, + "input_cost_per_token_batches": 7.5e-06, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "output_cost_per_token_batches": 3.75e-05, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "vertex_ai/claude-sonnet-4-5": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "input_cost_per_token_batches": 1.5e-06, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 200000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "output_cost_per_token_batches": 7.5e-06, + "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 + }, + "vertex_ai/claude-sonnet-4-5@20250929": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "input_cost_per_token_batches": 1.5e-06, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 200000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "output_cost_per_token_batches": 7.5e-06, + "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 + }, + "vertex_ai/claude-opus-4@20250514": { + "cache_creation_input_token_cost": 1.875e-05, + "cache_read_input_token_cost": 1.5e-06, + "input_cost_per_token": 1.5e-05, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 200000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "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 + }, + "vertex_ai/claude-sonnet-4": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "input_cost_per_token_above_200k_tokens": 6e-06, + "output_cost_per_token_above_200k_tokens": 2.25e-05, + "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, + "cache_read_input_token_cost_above_200k_tokens": 6e-07, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 1000000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "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 + }, + "vertex_ai/claude-sonnet-4@20250514": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "input_cost_per_token_above_200k_tokens": 6e-06, + "output_cost_per_token_above_200k_tokens": 2.25e-05, + "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, + "cache_read_input_token_cost_above_200k_tokens": 6e-07, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 1000000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "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 + }, + "vertex_ai/codestral-2501": { + "input_cost_per_token": 2e-07, + "litellm_provider": "vertex_ai-mistral_models", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-07, + "supports_function_calling": true, + "supports_tool_choice": true + }, + "vertex_ai/codestral@2405": { + "input_cost_per_token": 2e-07, + "litellm_provider": "vertex_ai-mistral_models", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-07, + "supports_function_calling": true, + "supports_tool_choice": true + }, + "vertex_ai/codestral@latest": { + "input_cost_per_token": 2e-07, + "litellm_provider": "vertex_ai-mistral_models", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-07, + "supports_function_calling": true, + "supports_tool_choice": true + }, + "vertex_ai/deepseek-ai/deepseek-v3.1-maas": { + "input_cost_per_token": 1.35e-06, + "litellm_provider": "vertex_ai-deepseek_models", + "max_input_tokens": 163840, + "max_output_tokens": 32768, + "max_tokens": 163840, + "mode": "chat", + "output_cost_per_token": 5.4e-06, + "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 + }, + "vertex_ai/deepseek-ai/deepseek-r1-0528-maas": { + "input_cost_per_token": 1.35e-06, + "litellm_provider": "vertex_ai-deepseek_models", + "max_input_tokens": 65336, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 5.4e-06, + "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 + }, + "vertex_ai/imagegeneration@006": { + "litellm_provider": "vertex_ai-image-models", + "mode": "image_generation", + "output_cost_per_image": 0.02, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" + }, + "vertex_ai/imagen-3.0-fast-generate-001": { + "litellm_provider": "vertex_ai-image-models", + "mode": "image_generation", + "output_cost_per_image": 0.02, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" + }, + "vertex_ai/imagen-3.0-generate-001": { + "litellm_provider": "vertex_ai-image-models", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" + }, + "vertex_ai/imagen-3.0-generate-002": { + "litellm_provider": "vertex_ai-image-models", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" + }, + "vertex_ai/imagen-4.0-fast-generate-001": { + "litellm_provider": "vertex_ai-image-models", + "mode": "image_generation", + "output_cost_per_image": 0.02, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" + }, + "vertex_ai/imagen-4.0-generate-001": { + "litellm_provider": "vertex_ai-image-models", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" + }, + "vertex_ai/imagen-4.0-ultra-generate-001": { + "litellm_provider": "vertex_ai-image-models", + "mode": "image_generation", + "output_cost_per_image": 0.06, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" + }, + "vertex_ai/jamba-1.5": { + "input_cost_per_token": 2e-07, + "litellm_provider": "vertex_ai-ai21_models", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 4e-07, + "supports_tool_choice": true + }, + "vertex_ai/jamba-1.5-large": { + "input_cost_per_token": 2e-06, + "litellm_provider": "vertex_ai-ai21_models", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 8e-06, + "supports_tool_choice": true + }, + "vertex_ai/jamba-1.5-large@001": { + "input_cost_per_token": 2e-06, + "litellm_provider": "vertex_ai-ai21_models", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 8e-06, + "supports_tool_choice": true + }, + "vertex_ai/jamba-1.5-mini": { + "input_cost_per_token": 2e-07, + "litellm_provider": "vertex_ai-ai21_models", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 4e-07, + "supports_tool_choice": true + }, + "vertex_ai/jamba-1.5-mini@001": { + "input_cost_per_token": 2e-07, + "litellm_provider": "vertex_ai-ai21_models", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 4e-07, + "supports_tool_choice": true + }, + "vertex_ai/meta/llama-3.1-405b-instruct-maas": { + "input_cost_per_token": 5e-06, + "litellm_provider": "vertex_ai-llama_models", + "max_input_tokens": 128000, + "max_output_tokens": 2048, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.6e-05, + "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 + }, + "vertex_ai/meta/llama-3.1-70b-instruct-maas": { + "input_cost_per_token": 0.0, + "litellm_provider": "vertex_ai-llama_models", + "max_input_tokens": 128000, + "max_output_tokens": 2048, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.0, + "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 + }, + "vertex_ai/meta/llama-3.1-8b-instruct-maas": { + "input_cost_per_token": 0.0, + "litellm_provider": "vertex_ai-llama_models", + "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": 0.0, + "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 + }, + "vertex_ai/meta/llama-3.2-90b-vision-instruct-maas": { + "input_cost_per_token": 0.0, + "litellm_provider": "vertex_ai-llama_models", + "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": 0.0, + "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 + }, + "vertex_ai/meta/llama-4-maverick-17b-128e-instruct-maas": { + "input_cost_per_token": 3.5e-07, + "litellm_provider": "vertex_ai-llama_models", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 1.15e-06, + "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 + }, + "vertex_ai/meta/llama-4-maverick-17b-16e-instruct-maas": { + "input_cost_per_token": 3.5e-07, + "litellm_provider": "vertex_ai-llama_models", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 1.15e-06, + "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 + }, + "vertex_ai/meta/llama-4-scout-17b-128e-instruct-maas": { + "input_cost_per_token": 2.5e-07, + "litellm_provider": "vertex_ai-llama_models", + "max_input_tokens": 10000000, + "max_output_tokens": 10000000, + "max_tokens": 10000000, + "mode": "chat", + "output_cost_per_token": 7e-07, + "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 + }, + "vertex_ai/meta/llama-4-scout-17b-16e-instruct-maas": { + "input_cost_per_token": 2.5e-07, + "litellm_provider": "vertex_ai-llama_models", + "max_input_tokens": 10000000, + "max_output_tokens": 10000000, + "max_tokens": 10000000, + "mode": "chat", + "output_cost_per_token": 7e-07, + "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 + }, + "vertex_ai/meta/llama3-405b-instruct-maas": { + "input_cost_per_token": 0.0, + "litellm_provider": "vertex_ai-llama_models", + "max_input_tokens": 32000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 0.0, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", + "supports_tool_choice": true + }, + "vertex_ai/meta/llama3-70b-instruct-maas": { + "input_cost_per_token": 0.0, + "litellm_provider": "vertex_ai-llama_models", + "max_input_tokens": 32000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 0.0, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", + "supports_tool_choice": true + }, + "vertex_ai/meta/llama3-8b-instruct-maas": { + "input_cost_per_token": 0.0, + "litellm_provider": "vertex_ai-llama_models", + "max_input_tokens": 32000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 0.0, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", + "supports_tool_choice": true + }, + "vertex_ai/mistral-large-2411": { + "input_cost_per_token": 2e-06, + "litellm_provider": "vertex_ai-mistral_models", + "max_input_tokens": 128000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 6e-06, + "supports_function_calling": true, + "supports_tool_choice": true + }, + "vertex_ai/mistral-large@2407": { + "input_cost_per_token": 2e-06, + "litellm_provider": "vertex_ai-mistral_models", + "max_input_tokens": 128000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 6e-06, + "supports_function_calling": true, + "supports_tool_choice": true + }, + "vertex_ai/mistral-large@2411-001": { + "input_cost_per_token": 2e-06, + "litellm_provider": "vertex_ai-mistral_models", + "max_input_tokens": 128000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 6e-06, + "supports_function_calling": true, + "supports_tool_choice": true + }, + "vertex_ai/mistral-large@latest": { + "input_cost_per_token": 2e-06, + "litellm_provider": "vertex_ai-mistral_models", + "max_input_tokens": 128000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 6e-06, + "supports_function_calling": true, + "supports_tool_choice": true + }, + "vertex_ai/mistral-nemo@2407": { + "input_cost_per_token": 3e-06, + "litellm_provider": "vertex_ai-mistral_models", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3e-06, + "supports_function_calling": true, + "supports_tool_choice": true + }, + "vertex_ai/mistral-nemo@latest": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "vertex_ai-mistral_models", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.5e-07, + "supports_function_calling": true, + "supports_tool_choice": true + }, + "vertex_ai/mistral-small-2503": { + "input_cost_per_token": 1e-06, + "litellm_provider": "vertex_ai-mistral_models", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3e-06, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "vertex_ai/mistral-small-2503@001": { + "input_cost_per_token": 1e-06, + "litellm_provider": "vertex_ai-mistral_models", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 3e-06, + "supports_function_calling": true, + "supports_tool_choice": true + }, + "vertex_ai/openai/gpt-oss-120b-maas": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "vertex_ai-openai_models", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 6e-07, + "source": "https://console.cloud.google.com/vertex-ai/publishers/openai/model-garden/gpt-oss-120b-maas", + "supports_reasoning": true + }, + "vertex_ai/openai/gpt-oss-20b-maas": { + "input_cost_per_token": 7.5e-08, + "litellm_provider": "vertex_ai-openai_models", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 3e-07, + "source": "https://console.cloud.google.com/vertex-ai/publishers/openai/model-garden/gpt-oss-120b-maas", + "supports_reasoning": true + }, + "vertex_ai/qwen/qwen3-235b-a22b-instruct-2507-maas": { + "input_cost_per_token": 2.5e-07, + "litellm_provider": "vertex_ai-qwen_models", + "max_input_tokens": 262144, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1e-06, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "supports_function_calling": true, + "supports_tool_choice": true + }, + "vertex_ai/qwen/qwen3-coder-480b-a35b-instruct-maas": { + "input_cost_per_token": 1e-06, + "litellm_provider": "vertex_ai-qwen_models", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 4e-06, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "supports_function_calling": true, + "supports_tool_choice": true + }, + "vertex_ai/qwen/qwen3-next-80b-a3b-instruct-maas": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "vertex_ai-qwen_models", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "supports_function_calling": true, + "supports_tool_choice": true + }, + "vertex_ai/qwen/qwen3-next-80b-a3b-thinking-maas": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "vertex_ai-qwen_models", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "supports_function_calling": true, + "supports_tool_choice": true + }, + "vertex_ai/veo-2.0-generate-001": { + "litellm_provider": "vertex_ai-video-models", + "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" + ] + }, + "vertex_ai/veo-3.0-fast-generate-preview": { + "litellm_provider": "vertex_ai-video-models", + "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" + ] + }, + "vertex_ai/veo-3.0-generate-preview": { + "litellm_provider": "vertex_ai-video-models", + "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" + ] + }, + "voyage/rerank-2": { + "input_cost_per_query": 5e-08, + "input_cost_per_token": 5e-08, + "litellm_provider": "voyage", + "max_input_tokens": 16000, + "max_output_tokens": 16000, + "max_query_tokens": 16000, + "max_tokens": 16000, + "mode": "rerank", + "output_cost_per_token": 0.0 + }, + "voyage/rerank-2-lite": { + "input_cost_per_query": 2e-08, + "input_cost_per_token": 2e-08, + "litellm_provider": "voyage", + "max_input_tokens": 8000, + "max_output_tokens": 8000, + "max_query_tokens": 8000, + "max_tokens": 8000, + "mode": "rerank", + "output_cost_per_token": 0.0 + }, + "voyage/voyage-2": { + "input_cost_per_token": 1e-07, + "litellm_provider": "voyage", + "max_input_tokens": 4000, + "max_tokens": 4000, + "mode": "embedding", + "output_cost_per_token": 0.0 + }, + "voyage/voyage-3": { + "input_cost_per_token": 6e-08, + "litellm_provider": "voyage", + "max_input_tokens": 32000, + "max_tokens": 32000, + "mode": "embedding", + "output_cost_per_token": 0.0 + }, + "voyage/voyage-3-large": { + "input_cost_per_token": 1.8e-07, + "litellm_provider": "voyage", + "max_input_tokens": 32000, + "max_tokens": 32000, + "mode": "embedding", + "output_cost_per_token": 0.0 + }, + "voyage/voyage-3-lite": { + "input_cost_per_token": 2e-08, + "litellm_provider": "voyage", + "max_input_tokens": 32000, + "max_tokens": 32000, + "mode": "embedding", + "output_cost_per_token": 0.0 + }, + "voyage/voyage-code-2": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "voyage", + "max_input_tokens": 16000, + "max_tokens": 16000, + "mode": "embedding", + "output_cost_per_token": 0.0 + }, + "voyage/voyage-code-3": { + "input_cost_per_token": 1.8e-07, + "litellm_provider": "voyage", + "max_input_tokens": 32000, + "max_tokens": 32000, + "mode": "embedding", + "output_cost_per_token": 0.0 + }, + "voyage/voyage-context-3": { + "input_cost_per_token": 1.8e-07, + "litellm_provider": "voyage", + "max_input_tokens": 120000, + "max_tokens": 120000, + "mode": "embedding", + "output_cost_per_token": 0.0 + }, + "voyage/voyage-finance-2": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "voyage", + "max_input_tokens": 32000, + "max_tokens": 32000, + "mode": "embedding", + "output_cost_per_token": 0.0 + }, + "voyage/voyage-large-2": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "voyage", + "max_input_tokens": 16000, + "max_tokens": 16000, + "mode": "embedding", + "output_cost_per_token": 0.0 + }, + "voyage/voyage-law-2": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "voyage", + "max_input_tokens": 16000, + "max_tokens": 16000, + "mode": "embedding", + "output_cost_per_token": 0.0 + }, + "voyage/voyage-lite-01": { + "input_cost_per_token": 1e-07, + "litellm_provider": "voyage", + "max_input_tokens": 4096, + "max_tokens": 4096, + "mode": "embedding", + "output_cost_per_token": 0.0 + }, + "voyage/voyage-lite-02-instruct": { + "input_cost_per_token": 1e-07, + "litellm_provider": "voyage", + "max_input_tokens": 4000, + "max_tokens": 4000, + "mode": "embedding", + "output_cost_per_token": 0.0 + }, + "voyage/voyage-multimodal-3": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "voyage", + "max_input_tokens": 32000, + "max_tokens": 32000, + "mode": "embedding", + "output_cost_per_token": 0.0 + }, + "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, + "litellm_provider": "wandb", + "mode": "chat" + }, + "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, + "litellm_provider": "wandb", + "mode": "chat" + }, + "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, + "litellm_provider": "wandb", + "mode": "chat" + }, + "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, + "litellm_provider": "wandb", + "mode": "chat" + }, + "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, + "litellm_provider": "wandb", + "mode": "chat" + }, + "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, + "litellm_provider": "wandb", + "mode": "chat" + }, + "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, + "litellm_provider": "wandb", + "mode": "chat" + }, + "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, + "litellm_provider": "wandb", + "mode": "chat" + }, + "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, + "litellm_provider": "wandb", + "mode": "chat" + }, + "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, + "litellm_provider": "wandb", + "mode": "chat" + }, + "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, + "litellm_provider": "wandb", + "mode": "chat" + }, + "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, + "litellm_provider": "wandb", + "mode": "chat" + }, + "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, + "litellm_provider": "wandb", + "mode": "chat" + }, + "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, + "litellm_provider": "wandb", + "mode": "chat" + }, + "watsonx/ibm/granite-3-8b-instruct": { + "input_cost_per_token": 0.0002, + "litellm_provider": "watsonx", + "max_input_tokens": 8192, + "max_output_tokens": 1024, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.0002, + "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 + }, + "watsonx/mistralai/mistral-large": { + "input_cost_per_token": 3e-06, + "litellm_provider": "watsonx", + "max_input_tokens": 131072, + "max_output_tokens": 16384, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1e-05, + "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 + }, + "whisper-1": { + "input_cost_per_second": 0.0001, + "litellm_provider": "openai", + "mode": "audio_transcription", + "output_cost_per_second": 0.0001, + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "vertex_ai/qwen/qwen3-next-80b-a3b-instruct-maas": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "vertex_ai-qwen_models", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "supports_function_calling": true, + "supports_tool_choice": true + }, + "vertex_ai/qwen/qwen3-next-80b-a3b-thinking-maas": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "vertex_ai-qwen_models", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "supports_function_calling": true, + "supports_tool_choice": true + }, + "xai/grok-2": { + "input_cost_per_token": 2e-06, + "litellm_provider": "xai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1e-05, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_web_search": true + }, + "xai/grok-2-1212": { + "input_cost_per_token": 2e-06, + "litellm_provider": "xai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1e-05, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_web_search": true + }, + "xai/grok-2-latest": { + "input_cost_per_token": 2e-06, + "litellm_provider": "xai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1e-05, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_web_search": true + }, + "xai/grok-2-vision": { + "input_cost_per_image": 2e-06, + "input_cost_per_token": 2e-06, + "litellm_provider": "xai", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 1e-05, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "xai/grok-2-vision-1212": { + "input_cost_per_image": 2e-06, + "input_cost_per_token": 2e-06, + "litellm_provider": "xai", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 1e-05, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "xai/grok-2-vision-latest": { + "input_cost_per_image": 2e-06, + "input_cost_per_token": 2e-06, + "litellm_provider": "xai", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 1e-05, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "xai/grok-3": { + "input_cost_per_token": 3e-06, + "litellm_provider": "xai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "source": "https://x.ai/api#pricing", + "supports_function_calling": true, + "supports_response_schema": false, + "supports_tool_choice": true, + "supports_web_search": true + }, + "xai/grok-3-beta": { + "input_cost_per_token": 3e-06, + "litellm_provider": "xai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "source": "https://x.ai/api#pricing", + "supports_function_calling": true, + "supports_response_schema": false, + "supports_tool_choice": true, + "supports_web_search": true + }, + "xai/grok-3-fast-beta": { + "input_cost_per_token": 5e-06, + "litellm_provider": "xai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.5e-05, + "source": "https://x.ai/api#pricing", + "supports_function_calling": true, + "supports_response_schema": false, + "supports_tool_choice": true, + "supports_web_search": true + }, + "xai/grok-3-fast-latest": { + "input_cost_per_token": 5e-06, + "litellm_provider": "xai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.5e-05, + "source": "https://x.ai/api#pricing", + "supports_function_calling": true, + "supports_response_schema": false, + "supports_tool_choice": true, + "supports_web_search": true + }, + "xai/grok-3-latest": { + "input_cost_per_token": 3e-06, + "litellm_provider": "xai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "source": "https://x.ai/api#pricing", + "supports_function_calling": true, + "supports_response_schema": false, + "supports_tool_choice": true, + "supports_web_search": true + }, + "xai/grok-3-mini": { + "input_cost_per_token": 3e-07, + "litellm_provider": "xai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 5e-07, + "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 + }, + "xai/grok-3-mini-beta": { + "input_cost_per_token": 3e-07, + "litellm_provider": "xai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 5e-07, + "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 + }, + "xai/grok-3-mini-fast": { + "input_cost_per_token": 6e-07, + "litellm_provider": "xai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4e-06, + "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 + }, + "xai/grok-3-mini-fast-beta": { + "input_cost_per_token": 6e-07, + "litellm_provider": "xai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4e-06, + "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 + }, + "xai/grok-3-mini-fast-latest": { + "input_cost_per_token": 6e-07, + "litellm_provider": "xai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4e-06, + "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 + }, + "xai/grok-3-mini-latest": { + "input_cost_per_token": 3e-07, + "litellm_provider": "xai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 5e-07, + "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 + }, + "xai/grok-4": { + "input_cost_per_token": 3e-06, + "litellm_provider": "xai", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "source": "https://docs.x.ai/docs/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_web_search": true + }, + "xai/grok-4-fast-reasoning": { + "litellm_provider": "xai", + "max_input_tokens": 2e6, + "max_output_tokens": 2e6, + "max_tokens": 2e6, + "mode": "chat", + "input_cost_per_token": 0.2e-06, + "output_cost_per_token": 0.5e-06, + "cache_read_input_token_cost": 0.05e-06, + "source": "https://docs.x.ai/docs/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_web_search": true + }, + "xai/grok-4-fast-non-reasoning": { + "litellm_provider": "xai", + "max_input_tokens": 2e6, + "max_output_tokens": 2e6, + "cache_read_input_token_cost": 0.05e-06, + "max_tokens": 2e6, + "mode": "chat", + "input_cost_per_token": 0.2e-06, + "output_cost_per_token": 0.5e-06, + "source": "https://docs.x.ai/docs/models", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_web_search": true + }, + "xai/grok-4-0709": { + "input_cost_per_token": 3e-06, + "litellm_provider": "xai", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "source": "https://docs.x.ai/docs/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_web_search": true + }, + "xai/grok-4-latest": { + "input_cost_per_token": 3e-06, + "litellm_provider": "xai", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "source": "https://docs.x.ai/docs/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_web_search": true + }, + "xai/grok-beta": { + "input_cost_per_token": 5e-06, + "litellm_provider": "xai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "xai/grok-code-fast": { + "cache_read_input_token_cost": 2e-08, + "input_cost_per_token": 2e-07, + "litellm_provider": "xai", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 1.5e-06, + "source": "https://docs.x.ai/docs/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "xai/grok-code-fast-1": { + "cache_read_input_token_cost": 2e-08, + "input_cost_per_token": 2e-07, + "litellm_provider": "xai", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 1.5e-06, + "source": "https://docs.x.ai/docs/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "xai/grok-code-fast-1-0825": { + "cache_read_input_token_cost": 2e-08, + "input_cost_per_token": 2e-07, + "litellm_provider": "xai", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 1.5e-06, + "source": "https://docs.x.ai/docs/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "xai/grok-vision-beta": { + "input_cost_per_image": 5e-06, + "input_cost_per_token": 5e-06, + "litellm_provider": "xai", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + } +} diff --git a/model_prices_and_context_window.sha256 b/model_prices_and_context_window.sha256 new file mode 100644 index 00000000..1cd539c2 --- /dev/null +++ b/model_prices_and_context_window.sha256 @@ -0,0 +1 @@ +eb63a796c771cee4945cd2546a4bdb8fd9615a57a9ba3e29cf98b682db772ebb